Does bkit auto-invoke its skills?

Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.

Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.

Testing

Plugin

bkit

A Claude Code plugin that verifies AI-generated code against its own design specs. Three commands. Anyone — even someone vibe-coding for the first time — can ship robust, production-quality software.

FLOW.md

popup-studio-ai@popup-studio-ai

GitHub

Plugin Signal93/100Strong

maintained100

capable96

documented100

adopted59

Install on Claude Code

> /plugin marketplace add popup-studio-ai/bkit-claude-code

Stats

JavaScript React React Native Next.js HTML

+7 tags

Docker Kubernetes Terraform GitHub CI/CD Anthropic MCP

589

Stars

149

Forks

Active

Maintenance

JavaScript

Language

Apache-2.0

License

18h ago

Last commit

7mo ago

Created

Repo: popup-studio-ai/bkit-claude-code

In this plugin

44 skills 34 agents 21 hooks 2 commands

See everything inside

What's inside

Skills

/auditView audit logs, decision traces, and session history for AI transparency. ACTION_TYPES (19 entries) include PDCA events (phase_transition, gate_passed/failed, agent_spawned/completed/failed, rollback_executed, destructive_blocked) and Sprint events (sprint_paused,/bkend-authbkend.ai authentication — email/social login, JWT tokens, RBAC, session management. Triggers: bkend auth, bkend login, bkend signup, bkend JWT, bkend RBAC /bkend-cookbookbkend.ai project tutorials (todo to SaaS) and common error troubleshooting. Triggers: bkend tutorial, bkend cookbook, bkend troubleshooting /bkend-databkend.ai database — CRUD, column types, filtering, sorting, relations, indexing. Triggers: bkend table, bkend CRUD, bkend column, bkend relation, bkend data /bkend-quickstartbkend.ai onboarding — MCP setup, resource hierarchy, tenant/user model, first project. Triggers: bkend quickstart, bkend onboarding, bkend setup, bkend MCP /bkend-storagebkend.ai file storage — upload (presigned URL), download (CDN), visibility levels, buckets. Triggers: bkend file, bkend upload, bkend download, bkend storage, bkend presigned URL

Show all 44 skills

/bkit-evalsRun skill evals via evals/runner.js — wrapper validates skill names, captures stdout/stderr, persists JSON results. Triggers: bkit evals, evals run, skill quality, eval runner /bkit-exploreBrowse installed bkit skills, agents, and evals via lib/discovery/explorer.js (filesystem scan, no subprocess). Triggers: bkit explore, list skills, skill discovery, browse skills /bkit-rulesCore rules for bkit — PDCA methodology, level detection, agent triggering, quality standards, Sprint management (8-phase container with 4 auto-pause triggers, v2.1.13), and Trust Level scope (L0-L4 gates PDCA + Sprint auto-run). Triggers: bkit rules, core rules, methodology /bkit-templatesPDCA + Sprint document templates — Plan, Design, Analysis, Report for individual features plus templates/sprint/{master-plan, prd, plan, design, iterate, qa, report}.template.md for sprint-level documents (v2.1.13). Triggers: template, plan document, design template /bkitbkit plugin help - list available functions including /pdca (9-phase feature cycle), /sprint (8-phase feature container, v2.1.13), /control (Trust L0-L4 + SPRINT_AUTORUN_SCOPE), /bkit-explore, and 40+ specialized skills. Use "/bkit" or "bkit help". Triggers: bkit help, bkit /btwBy-The-Way: capture improvement ideas the moment they surface, without derailing the task in progress. Triggers: /bkit:btw, /bkit:btw list, /bkit:btw analyze, /bkit:btw promote, /bkit:btw stats, btw, suggestion, improve, idea, feedback /cc-version-analysisCC CLI version upgrade impact analysis — research changes, analyze bkit impact, generate report. Triggers: cc-version-analysis, CC upgrade, version analysis /claude-code-learningClaude Code learning — configure and optimize Claude Code settings, tips, and workflows. Triggers: learn, setup, claude code, optimize /code-reviewCode review — analyze quality, detect bugs, ensure best practices with actionable feedback. Triggers: code review, quality check, bug detection /controlControl bkit automation level (L0-L4), view trust score, and manage guardrails. Trust level directly drives SPRINT_AUTORUN_SCOPE (v2.1.13): L0 manual+stopAfter=prd, L4 full-auto+stopAfter=archived. Also gates PDCA phase transitions and destructive operations. Triggers: control,/deployDeploy feature to target environment (dev/staging/prod) with level-based strategy. Triggers: deploy, /pdca deploy /desktop-appDesktop app development guide — Electron and Tauri for cross-platform apps. Triggers: desktop app, Electron, Tauri, mac app, windows app /development-pipelineComplete 9-phase development pipeline guide — from schema to deployment. Pipeline phases (1-schema → 9-deployment) are orthogonal to PDCA's 9-phase per-feature cycle and Sprint's 8-phase container; each pipeline phase may host PDCA cycles for individual features, and /dynamicFullstack development with bkend.ai BaaS — authentication, database, API integration. Triggers: fullstack, BaaS, login, signup, database, web app /enterpriseEnterprise-grade systems with microservices, Kubernetes, Terraform, and AI Native methodology. For multi-feature initiatives spanning a release timeline, combine with /sprint master-plan (v2.1.13) to group features into a single 8-phase sprint container with shared scope/budget /mobile-appMobile app development guide — React Native, Flutter, Expo for cross-platform. Triggers: mobile app, React Native, Flutter, Expo, iOS, Android /pdca-batchManage multiple PDCA features as independent parallel cycles (no shared scope/budget). For multiple features that share scope, budget, or timeline as one cohesive initiative, use /sprint (v2.1.13) — sprint groups features into a single 8-phase container, while pdca-batch keeps /pdca-fast-trackDaniel-mode fast-track auto-approves Checkpoint 1-8 when Trust ≥ 80, fastTrack on, Design doc exists. Else L2 + manual gates. Triggers: pdca fast-track, skip checkpoints, auto approve /pdca-watchLive PDCA dashboard ticking every 30s — reads pdca-status.json + token-ledger.ndjson tail, renders fixed-width panel via CC /loop. Triggers: pdca watch, live dashboard, watch progress /pdcaUnified PDCA cycle management — plan, design, do, analyze, iterate, report. PDCA runs per-feature (9-phase: pm→plan→design→do→check→act→qa→report→archive); for multi-feature scope/budget grouping use /sprint (v2.1.13, 8-phase container that may host PDCA cycles inside)./phase-1-schemaDefine project terminology, data structures, entities, and relationships. Triggers: schema, data model, entity, terminology /phase-2-conventionDefine coding rules, conventions, and standards for AI collaboration. Triggers: convention, coding style, lint, rules /phase-3-mockupCreate UI/UX mockups and HTML/CSS/JS prototypes without a designer. Triggers: mockup, prototype, wireframe, UI design default: bkit:pipeline-guide frontend: bkit:frontend-architect /phase-4-apiDesign and implement backend APIs with Zero Script QA validation. Triggers: API design, REST API, backend, endpoint /phase-5-design-systemBuild platform-independent design systems and consistent component libraries. Triggers: design system, component library, design tokens default: bkit:pipeline-guide frontend: bkit:frontend-architect /phase-6-ui-integrationImplement frontend UI and integrate with backend APIs — state management and API clients. Triggers: UI integration, frontend-backend, API client default: bkit:pipeline-guide frontend: bkit:frontend-architect /phase-7-seo-securityEnhance SEO (meta tags, semantic HTML) and security (vulnerability checks, hardening). Triggers: SEO, security, meta tags, vulnerability default: bkit:code-analyzer security: bkit:security-architect /phase-8-reviewVerify codebase quality — architecture consistency, convention compliance, gap analysis. Triggers: code review, architecture check, quality, gap analysis default: bkit:code-analyzer validate: bkit:design-validator gap: bkit:gap-detector qa: bkit:qa-strategist team: bkit:cto-lead /phase-9-deploymentDeploy to production — CI/CD pipelines, environment config, deployment strategies. Triggers: deployment, CI/CD, production, Vercel /plan-plusBrainstorming-enhanced PDCA planning with intent discovery and YAGNI review. For a single feature's plan use /plan-plus; for grouping multiple features under one scope/budget see /sprint master-plan (v2.1.13). Triggers: plan-plus, brainstorm, plan plus, intent /pm-discoveryPM Agent Team — automated product discovery, strategy, and PRD generation with 4 PM agents (for a single feature). For multi-feature initiatives with shared scope/budget/timeline, use /sprint master-plan which generates a sprint-level PRD via sprint-master-planner agent /qa-phaseQA Phase execution — L1-L5 test planning, generation, execution, and reporting for a single feature. For sprint-level QA (7-Layer dataFlowIntegrity / S1 gate across multiple features) use /sprint qa <sprintId> which delegates to sprint-qa-flow agent (v2.1.13). Triggers: qa /rollbackManage PDCA checkpoints and rollback — create, list, restore for safe recovery. Rollback events are recorded via lib/audit/audit-logger ACTION_TYPES.rollback_executed. For sprint-level recovery, individual feature rollbacks may be triggered from within sprint phases (sprint /skill-createInteractive skill creation workflow for project-local skills. Triggers: skill-create, create skill /skill-statusShow loaded skill inventory — bkit core vs project-local, conflicts, coverage gaps. Triggers: skill-status, skill list /sprintSprint Management — generic sprint capability for ANY bkit user. 16 sub-actions: init, start, status, watch, phase, iterate, qa, report, archive, list, feature, pause, resume, fork, help, master-plan. Triggers: sprint, sprint start, sprint init, sprint status, sprint list,/starterStatic web development for beginners — HTML/CSS/JS and Next.js App Router. Triggers: static website, portfolio, landing page, beginner /zero-script-qaZero Script QA — test without scripts using structured JSON logging and Docker monitoring. Triggers: zero-script-qa, log testing, docker logs, QA

Agents

bkend-expertbkend.ai BaaS platform expert agent. Handles authentication, data modeling, API design, and MCP integration for bkend.ai projects. Use proactively when user mentions login, signup, authentication, database operations, or fullstack development with a BaaS platform. Triggers:bkit-impact-analystbkit plugin architecture and impact analysis specialist agent. Deeply understands bkit's codebase, philosophy, and component architecture to assess how external changes (CC version upgrades) affect bkit. Use proactively when CC version changes need to be mapped to bkit impact,cc-version-researcherClaude Code CLI version change researcher agent. Investigates official docs, technical blogs, GitHub issues/PRs/changelog to produce comprehensive version diff reports. Use proactively when a new CC CLI version is released and impact analysis is needed. Triggers: CC version, CLI code-analyzerAgent that analyzes code quality and architecture compliance. Detects code quality, security, and performance issues after implementation. Use proactively when user requests code review, quality check, security scan, or asks to verify implementation quality before PR or cto-leadCTO-level team lead agent that orchestrates the entire PDCA workflow. Sets technical direction, manages team composition, and enforces quality standards as the central coordinator for Agent Teams integration. Use proactively when user starts a new project, requests team design-validatorAgent that validates design document completeness and consistency. Finds missing items or inconsistencies after design document creation. Use proactively when user creates or modifies design documents in docs/02-design/, or requests validation of specifications before

Show all 34 agents

Commands

/bkitbkit plugin help - Show all available bkit functions. Workaround for skills autocomplete issue. Use "/bkit" or just type "bkit help" to see available functions list. Triggers: bkit, bkit help, bkit functions, show bkit commands, 도움말, 기능 목록, ヘルプ, 機能一覧, 帮助, 功能列表, ayuda, lista de /output-style-setupInstall bkit output styles to your project or user directory. Copies output style files from bkit plugin to the appropriate location. Triggers: output style setup, install output style, setup style, 아웃풋 스타일 설치, 스타일 설정, 出力スタイル設定, 输出样式安装, instalar estilo, installer style, Stil

Hooks

SessionStartRuns on the SessionStart event.PreToolUseRuns on the PreToolUse event.PostToolUseRuns on the PostToolUse event.StopRuns on the Stop event.StopFailureRuns on the StopFailure event.UserPromptSubmitRuns on the UserPromptSubmit event.

Show all 21 hooks

UserPromptExpansionRuns on the UserPromptExpansion event.PreCompactRuns on the PreCompact event.PostCompactRuns on the PostCompact event.TaskCompletedRuns on the TaskCompleted event.SubagentStartRuns on the SubagentStart event.SubagentStopRuns on the SubagentStop event.TeammateIdleRuns on the TeammateIdle event.SessionEndRuns on the SessionEnd event.PostToolUseFailureRuns on the PostToolUseFailure event.InstructionsLoadedRuns on the InstructionsLoaded event.ConfigChangeRuns on the ConfigChange event.PermissionRequestRuns on the PermissionRequest event.NotificationRuns on the Notification event.CwdChangedRuns on the CwdChanged event.TaskCreatedRuns on the TaskCreated event.

README

Read on GitHub

bkit — AI Native Development OS

A Claude Code plugin that verifies AI-generated code against its own design specs.

Three commands. Anyone — even someone vibe-coding for the first time — can ship robust, production-quality software. bkit turns Claude Code into a Context Engineering system: 44 skills, 34 specialist agents, 11 quality gates, and a memory that survives across sessions deliver the right context to the AI at the right moment, so you don't have to know prompts, commands, or PDCA to get high-quality results.

Requirement: bkit requires Claude Code v2.1.143 or later (the strict plugin-manifest path recognizes the official displayName field only from v2.1.143). On older Claude Code you will see Validation errors: Unrecognized key: "displayName" during claude plugin install. Run npm install -g @anthropic-ai/claude-code@latest to upgrade, or see docs/06-guide/cc-compatibility.guide.md.

Who bkit is for

You are…	bkit gives you
🌱 First-time vibe coder — you describe what you want and AI codes for you, but you don't yet know how to tell if the result is correct	A safety net. AI proposes, bkit measures the result against its own design spec, and auto-repairs the gap when it drifts. You can ship without becoming a senior engineer first.
👤 Solo developer / indie builder	A team-in-a-box. `/pdca team` spawns 4–6 specialist agents in parallel — frontend, backend, QA, security — orchestrated by an AI tech lead.
👥 Team lead planning a release	Sprint Management. `/sprint master-plan` splits your release into context-budgeted sprints so a single Claude Code session can finish each one without running out of memory, and resumes after any session interruption.
🌐 Non-English speaker	8-language auto-detection. Type "로그인 기능 만들어줘" or "作成新功能" and bkit picks the right command for you.

What you'll achieve with bkit

The promise: anyone — including non-developers — can build robust, production-quality software by using bkit. bkit replaces the senior engineer's intuition with a workflow.

Without bkit	With bkit
AI gives you plausible code; you have no way to know if it really matches what you asked for	`gap-detector` measures match rate between your design spec and the generated code. Below 90 % → bkit auto-repairs (up to 5 cycles).
You only spot drift at PR review — by then the cleanup is expensive	11 Quality Gates halt the workflow before drift compounds (match rate, critical issues, convention, test coverage, security, dataFlow integrity, …)
Long projects exceed Claude Code's session window and you lose context	bkit splits the project into context-budgeted Sprints (≤ 75 K tokens each); memory + Task Management lets any session resume where the last one stopped
You don't know which command, agent, or skill to use	8-language auto-trigger + intent-router pick the right skill / agent automatically. You just describe what you want.
AI ships code, you ship hope; nobody documents what changed	Docs = Code philosophy: every feature produces a PRD + plan + design + analysis + completion report. The history is the audit trail.

The 4-step experience

This is the canonical workflow when you use bkit. You describe a release; bkit handles the rest.

flowchart TB
    You(["You: describe the release"])
    You --> S1["Step 1<br/>/sprint master-plan my-release<br/>--features auth, billing, reports"]
    S1 --> Auto1["bkit auto-action<br/>• sprint-master-planner agent investigates code + web in depth<br/>• Splits features into context-budgeted Sprints (&le; 75K tokens each)<br/>• Writes the master plan with Context Anchor"]
    Auto1 --> S2["Step 2<br/>You approve the plan"]
    S2 --> Auto2["bkit auto-action<br/>• Every sprint registered in Task Management<br/>• Memory saved — survives session clear"]
    Auto2 --> S3["Step 3<br/>/sprint start sprint-1"]
    S3 --> Auto3["bkit auto-action — full PDCA per feature:<br/>PRD/Plan → Design → Do → Iterate (target 100%, gated) →<br/>QA (gated) → Report. /pdca pm, /pdca team, /pdca qa as needed."]
    Auto3 --> Gate{"All quality<br/>gates pass?"}
    Gate -- "no, auto-fix" --> Repair["pdca-iterator self-repair<br/>(max 5 cycles)"]
    Repair --> Gate
    Gate -- "yes" --> Done(["Release-ready code + docs"])
    Ctrl["Step 4<br/>/control level 0..4"] -.->|"set how much<br/>runs unattended"| Auto1
    Ctrl -.->|"applies"| Auto3

    style You fill:#e3f2fd
    style S1 fill:#fff3e0
    style S2 fill:#fff8e1
    style S3 fill:#fff3e0
    style Auto3 fill:#fce4ec
    style Repair fill:#ffe0b2
    style Done fill:#c8e6c9
    style Ctrl fill:#f3e5f5

Step 1 — Plan the release in depth

You type: /sprint master-plan my-release --features auth, billing, reports.

bkit's sprint-master-planner agent investigates carefully — not quickly. Depending on what you're building, it reads your existing code base in depth or researches the web, then writes a master plan. Critically, it splits your features into context-budgeted Sprints: each sprint is sized so a single Claude Code session can finish it without overflowing the context window (the default is ≤ 75 K tokens per sprint, dependency-aware via Kahn topological sort + greedy bin-packing).

You can also call specialist agents directly when you want more depth: /pdca pm runs 4 product-management agents in parallel with 43 frameworks; /pdca team spawns a multi-specialist implementation team; /pdca qa runs a 5-agent QA team.

Step 2 — Approve, register, remember

You read the master plan. When you approve, bkit registers every sprint in its Task Management System with the right dependency order (Kahn-topologically sorted). It also writes to memory.

This means: if your laptop crashes, your session clears, or you start a new Claude Code session next week — bkit picks up exactly where you stopped. The plan and progress are durable.

Step 3 — Auto-run each sprint through PDCA

You type: /sprint start sprint-1.

bkit runs the 8-phase Sprint lifecycle (prd → plan → design → do → iterate → qa → report → archived). Inside the do phase, bkit runs the full PDCA loop once per feature:

Phase	What runs	Output
PRD / Plan	`pm-lead` orchestrates 4 PM agents (discovery, strategy, research, prd) with 43 frameworks	Comprehensive PRD + plan with Context Anchor
Design	`cto-lead` proposes 3 architecture options; you pick one (the only required user input)	Detailed design doc
Do	`/pdca team` spawns 4–6 specialist agents in parallel (developer, qa, frontend, backend, security, architect)	Working code
Iterate	Target 100 % match between design and code. `gap-detector` measures; `pdca-iterator` self-repairs until quality gate M1 (matchRate ≥ 90 %) passes. Max 5 cycles.	Repaired code + iteration report
QA	`qa-lead` runs 4 QA agents through L1–L5 tests + dataFlow integrity (S1 gate, 7-layer hop check)	QA report
Report	`report-generator` writes the completion report	Final report with KPI + lessons learned

Every phase is gated by quality thresholds. If anything fails — match rate too low, critical issue found, dataFlow broken — bkit pauses and tells you why. You don't have to remember to verify; verification is automatic.

Step 4 — Govern with one dial

/control level N is the single autonomy knob. It decides how far the orchestrator runs before stopping. The same dial controls both Sprint and PDCA — no second knob to manage.

Level	What it means
L0 Manual	Ask me at every phase. Best for your first sprint — inspect each output.
L2 Semi-Auto (default)	Plan/Design/Do auto; ask me on QA and Report.
L4 Full-Auto	Wake me when the sprint is done. Pauses only on a quality gate failure or one of 4 auto-pause triggers.

L1 (Guided) and L3 (Auto) sit between. bkit also computes a Trust Score (0–100) from your track record and can recommend a level — but you stay in charge.

How the bkit author actually uses bkit

The 4-step experience above is the canonical flow. Here's the concrete recipe the person who built bkit uses every day — two steps — so you can copy it without needing to understand the full machinery underneath.

Step A — Use Claude Code as a thinking amplifier before the master plan

The master plan is the single most important artifact in a sprint. Garbage in, garbage out. So don't write it alone, and don't let bkit write it cold either.

Open a fresh Claude Code session.
Talk through the release in plain language — what's the goal, who is it for, what could go wrong, what depends on what, what's still unknown? Let Claude Code push back.
Have it investigate — read your repo, search the web, surface edge cases you hadn't considered.
Then run /sprint master-plan my-release --features .... By the time you do, your context is already saturated; the master plan reflects what you really meant, not a generic template.

This is what Context Engineering looks like in practice: you don't tune the perfect prompt — you saturate the context first, then let bkit synthesise.

Step B — Hand the rest to Trust Level 4

Once you approve the master plan, the keyboard goes quiet until the final report lands. The bkit author picks one of two patterns based on release size:

Release size	What you type	What happens
Small–medium — a few related features, single context budget	`/control level 4`, then `/sprint start <project>` once	bkit runs every sprint and every PDCA phase straight through to `archived`. You read the final report.
Large — many sprints, large total token budget, or cross-sprint dependencies	`/control level 4`, then `/sprint start <sprint-id>` per sprint in dependency order	Each sprint runs full-auto. You skim the sprint report before launching the next sprint — a natural checkpoint between context windows.

Trust Level 4 is not "no safety". The 11 quality gates and 4 auto-pause triggers still fire. bkit halts and asks for you only when a measurable rule fails. The dial removes the unnecessary pauses, not the necessary ones.

The outcome, repeatable: AI plans, designs, codes, self-verifies, self-repairs, tests, and writes the completion report. You provide intent — and the final ship/no-ship decision. Nothing else.

The three commands

Command	When to use	What it spawns	Output
`/sprint`	Multi-feature release (quarter, milestone, multiple linked features)	`sprint-master-planner`, `sprint-orchestrator`, `sprint-qa-flow`, `sprint-report-writer`	Master plan + 8-phase per sprint + cumulative report
`/pdca`	A single feature (or runs inside a sprint per feature)	`pm-lead`, `cto-lead`, `gap-detector`, `pdca-iterator`, `qa-lead`, `report-generator` (any of 34 agents)	PRD + plan + design + code + analysis + report
`/control`	Anytime — set autonomy	—	Updates Trust Level scope; affects both `/sprint` and `/pdca`

How bkit closes the AI-coding gap — Context Engineering

bkit is more than commands. It is a Context Engineering system that solves the root cause of AI-coding failures: the AI doesn't have the right context.

The AI coding problem	bkit's Context Engineering answer
AI hallucinates because it doesn't know your conventions	44 skills (PDCA, Sprint, PM frameworks, …) auto-injected based on intent
AI loses focus as the session grows	Memory + Task Management resumes across sessions; Sprints are context-budgeted
AI ships code that drifts from the spec	11 Quality Gates + `gap-detector` measurement + `pdca-iterator` auto-repair
You only catch bugs at PR review	Phase-by-phase gating: drift is caught at every transition, not at the end
You need to remember the right command	8-language auto-trigger + intent-router; type "login 만들어줘" or "build login" and bkit picks the path
AI sessions are ephemeral; no audit trail	Audit log + Token Ledger + `Docs = Code` philosophy: every decision is on disk

bkit's three philosophies (from `bkit-system/philosophy/core-mission.md`)

Principle	What it means for you
Automation First	You don't need to know PDCA, Sprint, or any command. Type what you want; bkit picks the right workflow. The state machine + workflow engine drive the rest.
No Guessing	If bkit isn't sure, it checks the docs. If still unsure, it asks you. It never makes up an answer. `gap-detector`, `design-validator`, and 11 quality gates enforce this.
Docs = Code	Every feature produces docs (PRD + plan + design + analysis + report). The docs are the contract; bkit verifies that the code matches. `scripts/docs-code-sync.js` enforces 0 drift in CI.

Quick start

# 1. Install (one time)
claude plugin install bkit

# 2. Enable parallel team execution (optional, recommended)
export CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1

# 3. Your very first run — single feature
/pdca pm my-feature        # Describes what you want; bkit handles the rest

# 4. When you're ready for a multi-feature release
/sprint master-plan my-release --name "Q2 Launch" --features auth, billing, reports
# (You approve the plan)
/sprint start my-release-s1

Recommended Claude Code runtime: v2.1.220 (bkit explicitly handles v2.1.218's context: fork background-by-default change and v2.1.219's nested-subagent depth-3 default; Claude 5 alias resolution — sonnet → Sonnet 5 needs ≥ v2.1.197). Model floor: v2.1.170+ required by the 6 Fable-pinned agents (below it they fail to spawn; bkit shows a SessionStart advisory with a workaround). Install minimum v2.1.143; runtime minimum v2.1.78.

Quality gates — the safety net explained

A "quality gate" is a hard stop that won't let the workflow advance until a measurable condition is true. bkit ships 11 of them. The ones that matter most for new users:

Gate	What it measures	If it fails
M1 matchRate	How much of your design actually appears in the code, 0–100 %	Below 90 % → `pdca-iterator` automatically rewrites the code (up to 5 cycles)
M3 critical issues	Security or correctness bugs flagged by `code-analyzer`	Any critical → workflow pauses, you decide
S1 dataFlow integrity	7-layer check: UI → Client → API → Validation → DB → Response → Client → UI	Below 85 % → 7 hops re-verified one by one

Full M1–M10 + S1 catalog in README-FULL.md §5.

Architecture at a glance

44 skills · 34 agents · 21 hook events / 24 blocks across 28 handlers · 2 MCP servers (19 tools) · 198 lib modules across 22 subdirs · 62 scripts · 40 templates · 381 test files. Clean Architecture 4-Layer · Defense-in-Depth 4-Layer · Invocation Contract L1–L6, where L6 is host integration: a real claude -p --plugin-dir run whose recorded evidence CI checks against the shipped hooks.json.

Agents run on a 4-tier role-based model matrix: fable (long-horizon orchestration — leads), opus (deep reasoning, security & high-frequency PDCA verifiers), sonnet (implementers), haiku (monitors). The repeated Check/iterate verifiers (gap-detector, design-validator, pdca-iterator) run on Opus 4.8 — strong verification at half Fable's cost.

Full architecture deep-dive: README-FULL.md §9.

Documentation

Path	What's there
README-FULL.md	Full command reference, deep workflow internals, agent teams, architecture, Skill Evals
CHANGELOG.md	Release history (single source of truth — latest release: v2.1.34)
CUSTOMIZATION-GUIDE.md	Override any bkit component in your `.claude/` directory
AI-NATIVE-DEVELOPMENT.md	The 6 AI-Native principles and how bkit implements them
`bkit-system/philosophy/`	Core mission, Context Engineering, PDCA methodology, AI-Native principles
`docs/06-guide/sprint-management.guide.md`	Sprint Management deep-dive (English)
`docs/06-guide/sprint-migration.guide.md`	PDCA ↔ Sprint migration mapping (English)

🌟 Real User Hall of Fame

bkit's quality is measured by how well it responds to real users running bkit in production on their own projects. This section recognizes external dogfooders whose precise bug reports + reproduction scripts have been absorbed directly into bkit's regression test suite (test/e2e/external-dogfood/).

v2.1.19 (2026-05-30 — first entry)

@pruge (James Kim) — dandi-village-ledger project. 10 GitHub issues over 1.5 days (#92–#107) driving bkit v2.1.17, v2.1.18 closes + the entire v2.1.19 Quality Maturation Sprint. 5 reproduction scenarios absorbed as E2E tests at test/e2e/external-dogfood/dandi-*.test.js. See docs/external-dogfooders/pruge.md for the full contribution archive. Thank you for trusting bkit with your production sprint. 🙏

v2.1.20 (2026-05-26 — second entry, first-follower effect validated)

@bj (정병진) — bkit v2.1.14 install incident (2026-05-26, Validation errors: : Unrecognized key: "displayName"). Precise error message + cache path + Cursor IDE environment metadata sharing drove the entire v2.1.20 Marketplace Recovery Sprint (14 features / 3 sub-sprints / 3 new ENH 321/322/323 / 1 new ADR 0011 Plugin Manifest Schema Compliance Policy). Reproduction absorbed at test/e2e/external-dogfood/cc-min-version.test.js (5 TC, Lifecycle Stage 4 Regression Lock achieved). Triggered ADR 0006 § Empirical Validation Gate recovery (~30-day wire delay closed). See docs/external-dogfooders/bj.md for the full contribution archive. Thank you for sharing the precise error message that scoped the entire sprint correctly. 🙏

🚀 bkit Early Adopter Program

Running bkit on a non-trivial production project and willing to file detailed bug reports with reproductions makes you part of bkit's quality system, not just a bug reporter.

Established v2.1.19 (master plan §15.4 DA-1~DA-4, ENH-318 차별화 7/7).

Benefits:

🏆 Public recognition in this README + dedicated archive
🔒 Your reproduction scripts become permanent E2E regression tests
📊 Your activity directly powers bkit's Trust Score (externalDogfoodFeedbackResponseRate component, weight 0.05)
📝 CHANGELOG attribution on every release where your scenarios were absorbed
🤝 Direct line to bkit maintainers — priority issue triage, reproduction-script-first response

How to join: file your first detailed issue at bkit-claude-code/issues with bkit version, reproduction steps, expected vs actual behavior, and file:line references. See docs/external-dogfooders/_README.md for the full 5-stage User-Feedback Lifecycle and program structure.

DA-4 acquisition goal: by v2.1.20 (30 days post-v2.1.19 GA), measure dogfooder population. DA-4 status (v2.1.20): N=2 confirmed (@pruge + @bj) — first-follower effect validated. v2.1.21+ continues active outreach (CC marketplace narrative, community engagement) to grow N≥3.

License

Apache 2.0 — see LICENSE and NOTICE. POPUP STUDIO PTE. LTD. · kay@popupstudio.ai

File tree

1604

popup-studio-ai/bkit-claude-codeView on GitHub

.claude/
.claude-plugin/
  marketplace.json
  plugin.json
  CLAUDE.md
.github/
  workflows/
    cc-regression-reconcile.yml
    contract-check.yml
.gitignore
.prettierrc
agents/
AGENTS.md
  bkend-expert.md
  bkit-impact-analyst.md
  cc-version-researcher.md
  code-analyzer.md
  cto-lead.md
  design-validator.md
  enterprise-expert.md
  frontend-architect.md
  gap-detector.md
  infra-architect.md
  pdca-iterator.md
  pipeline-guide.md
  pm-discovery.md
  pm-lead-skill-patch.md
  pm-lead.md
  pm-prd.md
  pm-research.md
  pm-strategy.md
  product-manager.md
  qa-debug-analyst.md
  qa-lead.md
  qa-monitor.md
  qa-strategist.md
  qa-test-generator.md
  qa-test-planner.md
  report-generator.md
  security-architect.md
  self-healing.md
  skill-needs-extractor.md
  sprint-master-planner.md
  sprint-orchestrator.md
  sprint-qa-flow.md
  sprint-report-writer.md
  starter-guide.md
AI-NATIVE-DEVELOPMENT.md
assets/
  error-dict.en.json
  error-dict.ko.json
bkit-infra-architecture.html
bkit-infra-architecture.pdf
bkit-system/
  _GRAPH-INDEX.md
  .obsidian/
    app.json
    appearance.json
    core-plugins.json
  components/
    agents/
      _agents-overview.md
    hooks/
      _hooks-overview.md
    scripts/
      _scripts-overview.md
    skills/
      _skills-overview.md
  philosophy/
    ai-native-principles.md
    context-engineering.md
    core-mission.md
    pdca-methodology.md
  README.md
  scenarios/
    scenario-discover-features.md
    scenario-new-feature.md
    scenario-qa.md
    scenario-sprint.md
    scenario-write-code.md
  testing/
    test-checklist.md
  triggers/
    priority-rules.md
    trigger-matrix.md
bkit.config.json
CHANGELOG.md
CODE_OF_CONDUCT.md
commands/
  bkit.md
  output-style-setup.md
CONTRIBUTING.md
CONTRIBUTORS.md
CUSTOMIZATION-GUIDE.md
docs/
  00-pm/
    claude-model-alignment.prd.en.md
    claude-model-alignment.prd.ko.md
    features/
      s0-sqm-baseline.prd.md
      s1-foundation.prd.md
      s2-defense.prd.md
      s3-polish.prd.md
      s4-proactive.prd.md
      s5-measurement.prd.md
      v2118-sprint-trust-ux-fix.prd.md
    skill-post-slash-reach.prd.en.md
    skill-post-slash-reach.prd.ko.md
    v2121-issue-response.prd.md
    v2126-issue-response.prd.en.md
    v2126-issue-response.prd.ko.md
  01-plan/
    features/
      cc-stop-hook-schema-compliance.plan.md
      cc-v2159-response.plan.md
      cc-v2218-compat.plan.en.md
      cc-v2218-compat.plan.ko.md
      claude-model-alignment.plan.en.md
      claude-model-alignment.plan.ko.md
      cross-platform-mac-windows.plan.md
      ctx-eng-godfile-split.plan.md
      ctx-eng-layer-consolidation.plan.md
      final-qa-i18n-docs-sync.plan.md
      issue-89-pdca-status-fix.plan.md
      pdca-task-completion-chain.plan.en.md
      pdca-task-completion-chain.plan.ko.md
      s0-sqm-baseline.plan.md
      s1-foundation.plan.md
      s2-defense.plan.md
      s3-polish.plan.md
      s4-proactive.plan.md
      s5-measurement.plan.md
      skill-guidance-runtime-phase.plan.en.md
      skill-guidance-runtime-phase.plan.ko.md
      skill-post-slash-reach.plan.en.md
      skill-post-slash-reach.plan.ko.md
      stop-hook-stdin-block-139.plan.en.md
      stop-hook-stdin-block-139.plan.ko.md
      tech-debt-deadcode-elimination.plan.md
      v2.1.22-hardening.master-plan.md
      v2116-issue-fixes.master-plan.md
      v2116-release-hardening.plan.md
      v2117-ci-cd-hardening.plan.md
      v2118-carryover-cleanup.plan.md
      v2118-sprint-trust-ux-fix.plan.md
      v2119-bkit-quality-maturation.master-plan.md
      v2121-issue-response.master-plan.md
      v2126-issue-response.plan.en.md
      v2126-issue-response.plan.ko.md
      v2133-defect-response.master-plan.en.md
      v2133-defect-response.master-plan.ko.md
  02-design/
    features/
      cc-stop-hook-schema-compliance.design.md
      cc-v2218-compat.design.en.md
      cc-v2218-compat.design.ko.md
      claude-model-alignment.design.en.md
      claude-model-alignment.design.ko.md
      cross-platform-mac-windows.design.md
      ctx-eng-godfile-split.design.md
      ctx-eng-layer-consolidation.design.md
      final-qa-i18n-docs-sync.design.md
      issue-89-pdca-status-fix.design.md
      pdca-task-completion-chain.design.en.md
      pdca-task-completion-chain.design.ko.md
      s0-sqm-baseline.design.md
      s1-foundation.design.md
      s2-defense.design.md
      s3-polish.design.md
      s4-proactive.design.md
      s5-measurement.design.md
      skill-guidance-runtime-phase.design.en.md
      skill-guidance-runtime-phase.design.ko.md
      skill-post-slash-reach.design.en.md
      skill-post-slash-reach.design.ko.md
      stop-hook-stdin-block-139.design.en.md
      stop-hook-stdin-block-139.design.ko.md
      tech-debt-deadcode-elimination.design.md
      v2116-release-hardening.design.md
      v2117-ci-cd-hardening.design.md
      v2118-carryover-cleanup.design.md
      v2118-sprint-trust-ux-fix.design.md
      v2126-issue-response.design.en.md
      v2126-issue-response.design.ko.md
    LIVING-CONTEXT-GUIDE.md
  03-analysis/
    bkit-architecture-completeness.analysis.md
    bkit-plugin-vibecoding-ux.analysis.md
    cc-v2146-v2150-strict-manifest-validation.analysis.md
    claude-model-alignment.analysis.en.md
    claude-model-alignment.analysis.ko.md
    features/
      cc-stop-hook-schema-compliance.analysis.md
      cc-version-issue-response.analysis.md
      skill-guidance-runtime-phase.analysis.en.md
      skill-guidance-runtime-phase.analysis.ko.md
      skill-post-slash-reach.analysis.md
      stop-hook-stdin-block-139.analysis.en.md
      stop-hook-stdin-block-139.analysis.ko.md
      v2113-sprint-1-domain.iterate.md
      v2113-sprint-2-application.iterate.md
      v2113-sprint-3-infrastructure.iterate.md
      v2113-sprint-4-presentation.iterate.md
      v2113-sprint-5-quality-docs.iterate.md
      v2117-ci-cd-hardening.analysis.md
      v2118-carryover-cleanup.analysis.md
      v2134-hook-reachability.analysis.en.md
      v2134-hook-reachability.analysis.ko.md
    pdca-task-completion-chain.analysis.en.md
    pdca-task-completion-chain.analysis.ko.md
    prompt-caching-optimization.md
    s0-sqm-baseline-gate-fail-plan-2026-05-21T09-59-25-546Z.md
    s0-sqm-baseline-gate-fail-plan-2026-05-21T09-59-32-172Z.md
    security-architecture.md
    v2113-dead-code-and-sprint-integration.analysis.md
    v2118-sqm-baseline.analysis.md
    v2126-issue-response.analysis.en.md
    v2126-issue-response.analysis.ko.md
    zero-script-qa-fork-v2116-verification.md
  04-report/
    bkit-v2112-deep-functional-qa-issues.report.md
    changelog.md
    claude-model-alignment.report.en.md
    claude-model-alignment.report.ko.md
    features/
      bkit-v200-test.report.md
      cc-stop-hook-schema-compliance.report.md
      cc-v2139-v2140-impact-analysis.report.md
      cc-v2140-v2141-impact-analysis.report.md
      cc-v2141-v2142-impact-analysis.report.md
      cc-v2142-v2143-impact-analysis.report.md
      cc-v2143-v2144-impact-analysis.report.md
      cc-v2144-v2145-impact-analysis.report.md
      cc-v2145-v2146-impact-analysis.report.md
      cc-v2146-v2159-impact-analysis.report.md
      cc-v2159-response.report.md
      cc-v2159-v2161-impact-analysis.report.md
      cc-v2161-v2162-impact-analysis.report.md
      cc-v2162-v2168-impact-analysis.report.md
      cc-v2168-v2169-impact-analysis.report.md
      cc-v2169-v2179-impact-analysis.report.md
      cc-v2179-v2181-impact-analysis.report.md
      cc-v2181-v2191-impact-analysis.report.md
      cc-v2191-v2196-impact-analysis.report.md
      cc-v2196-v2198-impact-analysis.report.md
      cc-v2199-v2204-impact-analysis.report.md
      cc-v2205-v2207-impact-analysis.report.md
      cc-v2208-v2210-impact-analysis.report.md
      cc-v2211-impact-analysis.report.md
      cc-v2212-v2214-impact-analysis.report.md
      cc-v2214-v2215-impact-analysis.report.en.md
      cc-v2214-v2215-impact-analysis.report.ko.md
      cc-v2216-v2217-impact-analysis.report.en.md
      cc-v2216-v2217-impact-analysis.report.ko.md
      cc-v2218-impact-analysis.report.en.md
      cc-v2218-impact-analysis.report.ko.md
      cc-v2219-v2220-impact-analysis.report.en.md
      cc-v2219-v2220-impact-analysis.report.ko.md
      cc-v2220-v2221-impact-analysis.report.en.md
      cc-v2220-v2221-impact-analysis.report.ko.md
      cc-v2222-v2223-impact-analysis.report.en.md
      cc-v2222-v2223-impact-analysis.report.ko.md
      cc-v2223-v2224-impact-analysis.report.en.md
      cc-v2223-v2224-impact-analysis.report.ko.md
      cc-v2224-v2225-impact-analysis.report.en.md
      cc-v2224-v2225-impact-analysis.report.ko.md
      cc-v2225-v2226-impact-analysis.report.ko.md
      cross-platform-mac-windows.report.md
      ctx-eng-godfile-split.report.md
      ctx-eng-layer-consolidation.report.md
      final-qa-i18n-docs-sync.report.md
      issue-89-pdca-status-fix.report.md
      pdca-task-completion-chain.report.en.md
      pdca-task-completion-chain.report.ko.md
      s0-sqm-baseline.report.md
      s1-foundation.report.md
      s2-defense.report.md
      s3-polish.report.md
      s4-proactive.report.md
      s5-measurement.report.md
      skill-guidance-runtime-phase.report.en.md
      skill-guidance-runtime-phase.report.ko.md
      stop-hook-stdin-block-139.report.en.md
      stop-hook-stdin-block-139.report.ko.md
      tech-debt-deadcode-elimination.report.md
      v2114-alwaysload-measurement.report.md
      v2116-issue-fixes.report.md
      v2116-release-hardening.report.md
      v2117-ci-cd-hardening.report.md
      v2118-carryover-cleanup.report.md
      v2118-sprint-trust-ux-fix.report.md
      v2120-marketplace-recovery.report.md
      v2121-issue-response.report.md
    v2113-sprint-integration-final-qa.report.md
    v2126-issue-response.report.en.md
    v2126-issue-response.report.ko.md
  05-qa/
    claude-model-alignment.qa-report.en.md
    claude-model-alignment.qa-report.ko.md
    features/
      skill-guidance-runtime-phase.qa-report.en.md
      skill-guidance-runtime-phase.qa-report.ko.md
      stop-hook-stdin-block-139.qa-report.en.md
      stop-hook-stdin-block-139.qa-report.ko.md
    v2118-sprint-trust-ux-fix.qa-report.md
    v2126-issue-response.qa-report.en.md
    v2126-issue-response.qa-report.ko.md
    v2133-defect-response.qa-report.en.md
    v2133-defect-response.qa-report.ko.md
    v2134-hook-reachability.qa-report.en.md
    v2134-hook-reachability.qa-report.ko.md
  05-research/
    external-dogfooders/
      jbjeong-2026-05-26-displayName-reject.md
  06-guide/
    branch-protection-setup.guide.md
    cc-compatibility.guide.md
    cc-version-monitoring.guide.md
    contract-baseline-rollforward.guide.md
    eval-rebaseline.guide.en.md
    eval-rebaseline.guide.ko.md
    sprint-management.guide.md
    sprint-migration.guide.md
    test-file-tracking-policy.guide.md
    version-policy.guide.md
  adr/
    0003-cc-version-impact-empirical-validation.md
    0004-agent-hook-multi-event-deferral.md
    0005-application-layer-pilot.md
    0006-cc-upgrade-policy.md
    0007-sprint-as-meta-container.md
    0008-sprint-phase-enum.md
    0009-sprint-autorun-trust-scope.md
    0010-effort-aware-invariant.md
    0011-plugin-manifest-schema-compliance.md
    0012-sprint-stop-hook-output-enforcement.md
    0013-context-engineering-factoring.md
    0014-deprecation-registry.en.md
    0014-deprecation-registry.ko.md
    0015-locale-scoped-trigger-deferral.en.md
    0015-locale-scoped-trigger-deferral.ko.md
  ai-agent-security-audit-2026.report.md
  ai-native-role-redistribution.md
  archive/
    2026-05/
      00-pm/
        bkit-v2112-evals-wrapper-hotfix.prd.md
        bkit-v218-bug-fixes.prd.md
        v2113-docs-sync.prd.md
      01-plan/
        features/
          bkit-v2110-compatibility-policy.plan.md
          bkit-v2110-gap-closure-plan-plus.plan.md
          bkit-v2110-integrated-enhancement.plan.md
          bkit-v2110-invocation-contract-addendum.plan.md
          bkit-v2111-integrated-enhancement.plan.md
          bkit-v2112-evals-wrapper-hotfix.plan.md
          bkit-v216-enhancement.plan.md
          bkit-v216-integrated-enhancement.plan.md
          bkit-v217-issue-79-hotfix.plan.md
          bkit-v217-issue-79-hotfix.prd.md
          bkit-v219-docs-sync.plan.md
          cc-v2110-v2112-issue81-response.plan.md
          cc-v2112-v2114-impact-analysis.plan.md
          cc-v2114-v2116-impact-analysis.plan.md
          cc-v2116-v2117-impact-analysis.plan.md
          s1-ux.plan.md
          s1-ux.prd.md
          s2-ux.plan.md
          s2-ux.prd.md
          s3-ux.plan.md
          s3-ux.prd.md
          s4-ux.plan.md
          s4-ux.prd.md
          sprint-management.master-plan.md
          sprint-ux-improvement.master-plan.md
          v2110-docs-sync.plan.md
          v2113-docs-sync.master-plan.md
          v2113-docs-sync.plan.md
          v2113-sprint-1-domain.plan.md
          v2113-sprint-1-domain.prd.md
          v2113-sprint-2-application.plan.md
          v2113-sprint-2-application.prd.md
          v2113-sprint-3-infrastructure.plan.md
          v2113-sprint-3-infrastructure.prd.md
          v2113-sprint-4-presentation.plan.md
          v2113-sprint-4-presentation.prd.md
          v2113-sprint-5-quality-docs.plan.md
          v2113-sprint-5-quality-docs.prd.md
      02-design/
        features/
          bkit-v2110-gap-closure.design.md
          bkit-v2110-integrated-enhancement.design.md
          bkit-v2110-orchestration-integrity.design.md
          bkit-v2111-integrated-enhancement.design.md
          bkit-v2111-sprint-alpha.design.md
          bkit-v2111-sprint-beta.design.md
          bkit-v2111-sprint-delta.design.md
          bkit-v2111-sprint-gamma.design.md
          bkit-v2112-evals-wrapper-hotfix.design.md
... 1478 more

FAQ

bkit is a Claude Code plugin with 44 hand-picked skills for testing work, indexed on Flowy. Install it with the command on its page. It includes audit, bkend-auth, bkend-cookbook. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.

What is bkit?: A Claude Code plugin that verifies AI-generated code against its own design specs. Three commands. Anyone — even someone vibe-coding for the first time — can ship robust, production-quality software.
How do I install bkit?: Run these in Claude Code: /plugin marketplace add popup-studio-ai/bkit-claude-code. Then prompt normally.
Does bkit auto-invoke its skills?: Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
Is bkit free?: Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.

Testing

Plugin

bkit

FLOW.md

popup-studio-ai@popup-studio-ai

GitHub

Plugin Signal93/100Strong

maintained100

capable96

documented100

adopted59

Install on Claude Code

> /plugin marketplace add popup-studio-ai/bkit-claude-code

Stats

JavaScript React React Native Next.js HTML

+7 tags

Docker Kubernetes Terraform GitHub CI/CD Anthropic MCP

589

Stars

149

Forks

Active

Maintenance

JavaScript

Language

Apache-2.0

License

18h ago

Last commit

7mo ago

Created

Repo: popup-studio-ai/bkit-claude-code

In this plugin

44 skills 34 agents 21 hooks 2 commands

See everything inside

What's inside

Skills

Show all 44 skills

Agents

Show all 34 agents

Commands

Hooks

Show all 21 hooks

README

Read on GitHub

bkit — AI Native Development OS

A Claude Code plugin that verifies AI-generated code against its own design specs.

Requirement: bkit requires Claude Code v2.1.143 or later (the strict plugin-manifest path recognizes the official displayName field only from v2.1.143). On older Claude Code you will see Validation errors: Unrecognized key: "displayName" during claude plugin install. Run npm install -g @anthropic-ai/claude-code@latest to upgrade, or see docs/06-guide/cc-compatibility.guide.md.

Who bkit is for

You are…	bkit gives you
🌱 First-time vibe coder — you describe what you want and AI codes for you, but you don't yet know how to tell if the result is correct	A safety net. AI proposes, bkit measures the result against its own design spec, and auto-repairs the gap when it drifts. You can ship without becoming a senior engineer first.
👤 Solo developer / indie builder	A team-in-a-box. `/pdca team` spawns 4–6 specialist agents in parallel — frontend, backend, QA, security — orchestrated by an AI tech lead.
👥 Team lead planning a release	Sprint Management. `/sprint master-plan` splits your release into context-budgeted sprints so a single Claude Code session can finish each one without running out of memory, and resumes after any session interruption.
🌐 Non-English speaker	8-language auto-detection. Type "로그인 기능 만들어줘" or "作成新功能" and bkit picks the right command for you.

What you'll achieve with bkit

The promise: anyone — including non-developers — can build robust, production-quality software by using bkit. bkit replaces the senior engineer's intuition with a workflow.

Without bkit	With bkit
AI gives you plausible code; you have no way to know if it really matches what you asked for	`gap-detector` measures match rate between your design spec and the generated code. Below 90 % → bkit auto-repairs (up to 5 cycles).
You only spot drift at PR review — by then the cleanup is expensive	11 Quality Gates halt the workflow before drift compounds (match rate, critical issues, convention, test coverage, security, dataFlow integrity, …)
Long projects exceed Claude Code's session window and you lose context	bkit splits the project into context-budgeted Sprints (≤ 75 K tokens each); memory + Task Management lets any session resume where the last one stopped
You don't know which command, agent, or skill to use	8-language auto-trigger + intent-router pick the right skill / agent automatically. You just describe what you want.
AI ships code, you ship hope; nobody documents what changed	Docs = Code philosophy: every feature produces a PRD + plan + design + analysis + completion report. The history is the audit trail.

The 4-step experience

This is the canonical workflow when you use bkit. You describe a release; bkit handles the rest.

flowchart TB
    You(["You: describe the release"])
    You --> S1["Step 1<br/>/sprint master-plan my-release<br/>--features auth, billing, reports"]
    S1 --> Auto1["bkit auto-action<br/>• sprint-master-planner agent investigates code + web in depth<br/>• Splits features into context-budgeted Sprints (&le; 75K tokens each)<br/>• Writes the master plan with Context Anchor"]
    Auto1 --> S2["Step 2<br/>You approve the plan"]
    S2 --> Auto2["bkit auto-action<br/>• Every sprint registered in Task Management<br/>• Memory saved — survives session clear"]
    Auto2 --> S3["Step 3<br/>/sprint start sprint-1"]
    S3 --> Auto3["bkit auto-action — full PDCA per feature:<br/>PRD/Plan → Design → Do → Iterate (target 100%, gated) →<br/>QA (gated) → Report. /pdca pm, /pdca team, /pdca qa as needed."]
    Auto3 --> Gate{"All quality<br/>gates pass?"}
    Gate -- "no, auto-fix" --> Repair["pdca-iterator self-repair<br/>(max 5 cycles)"]
    Repair --> Gate
    Gate -- "yes" --> Done(["Release-ready code + docs"])
    Ctrl["Step 4<br/>/control level 0..4"] -.->|"set how much<br/>runs unattended"| Auto1
    Ctrl -.->|"applies"| Auto3

    style You fill:#e3f2fd
    style S1 fill:#fff3e0
    style S2 fill:#fff8e1
    style S3 fill:#fff3e0
    style Auto3 fill:#fce4ec
    style Repair fill:#ffe0b2
    style Done fill:#c8e6c9
    style Ctrl fill:#f3e5f5

Step 1 — Plan the release in depth

You type: /sprint master-plan my-release --features auth, billing, reports.

Step 2 — Approve, register, remember

You read the master plan. When you approve, bkit registers every sprint in its Task Management System with the right dependency order (Kahn-topologically sorted). It also writes to memory.

This means: if your laptop crashes, your session clears, or you start a new Claude Code session next week — bkit picks up exactly where you stopped. The plan and progress are durable.

Step 3 — Auto-run each sprint through PDCA

You type: /sprint start sprint-1.

bkit runs the 8-phase Sprint lifecycle (prd → plan → design → do → iterate → qa → report → archived). Inside the do phase, bkit runs the full PDCA loop once per feature:

Phase	What runs	Output
PRD / Plan	`pm-lead` orchestrates 4 PM agents (discovery, strategy, research, prd) with 43 frameworks	Comprehensive PRD + plan with Context Anchor
Design	`cto-lead` proposes 3 architecture options; you pick one (the only required user input)	Detailed design doc
Do	`/pdca team` spawns 4–6 specialist agents in parallel (developer, qa, frontend, backend, security, architect)	Working code
Iterate	Target 100 % match between design and code. `gap-detector` measures; `pdca-iterator` self-repairs until quality gate M1 (matchRate ≥ 90 %) passes. Max 5 cycles.	Repaired code + iteration report
QA	`qa-lead` runs 4 QA agents through L1–L5 tests + dataFlow integrity (S1 gate, 7-layer hop check)	QA report
Report	`report-generator` writes the completion report	Final report with KPI + lessons learned

Step 4 — Govern with one dial

/control level N is the single autonomy knob. It decides how far the orchestrator runs before stopping. The same dial controls both Sprint and PDCA — no second knob to manage.

Level	What it means
L0 Manual	Ask me at every phase. Best for your first sprint — inspect each output.
L2 Semi-Auto (default)	Plan/Design/Do auto; ask me on QA and Report.
L4 Full-Auto	Wake me when the sprint is done. Pauses only on a quality gate failure or one of 4 auto-pause triggers.

L1 (Guided) and L3 (Auto) sit between. bkit also computes a Trust Score (0–100) from your track record and can recommend a level — but you stay in charge.

How the bkit author actually uses bkit

Step A — Use Claude Code as a thinking amplifier before the master plan

The master plan is the single most important artifact in a sprint. Garbage in, garbage out. So don't write it alone, and don't let bkit write it cold either.

Open a fresh Claude Code session.
Talk through the release in plain language — what's the goal, who is it for, what could go wrong, what depends on what, what's still unknown? Let Claude Code push back.
Have it investigate — read your repo, search the web, surface edge cases you hadn't considered.
Then run /sprint master-plan my-release --features .... By the time you do, your context is already saturated; the master plan reflects what you really meant, not a generic template.

This is what Context Engineering looks like in practice: you don't tune the perfect prompt — you saturate the context first, then let bkit synthesise.

Step B — Hand the rest to Trust Level 4

Once you approve the master plan, the keyboard goes quiet until the final report lands. The bkit author picks one of two patterns based on release size:

Release size	What you type	What happens
Small–medium — a few related features, single context budget	`/control level 4`, then `/sprint start <project>` once	bkit runs every sprint and every PDCA phase straight through to `archived`. You read the final report.
Large — many sprints, large total token budget, or cross-sprint dependencies	`/control level 4`, then `/sprint start <sprint-id>` per sprint in dependency order	Each sprint runs full-auto. You skim the sprint report before launching the next sprint — a natural checkpoint between context windows.

The outcome, repeatable: AI plans, designs, codes, self-verifies, self-repairs, tests, and writes the completion report. You provide intent — and the final ship/no-ship decision. Nothing else.

The three commands

Command	When to use	What it spawns	Output
`/sprint`	Multi-feature release (quarter, milestone, multiple linked features)	`sprint-master-planner`, `sprint-orchestrator`, `sprint-qa-flow`, `sprint-report-writer`	Master plan + 8-phase per sprint + cumulative report
`/pdca`	A single feature (or runs inside a sprint per feature)	`pm-lead`, `cto-lead`, `gap-detector`, `pdca-iterator`, `qa-lead`, `report-generator` (any of 34 agents)	PRD + plan + design + code + analysis + report
`/control`	Anytime — set autonomy	—	Updates Trust Level scope; affects both `/sprint` and `/pdca`

How bkit closes the AI-coding gap — Context Engineering

bkit is more than commands. It is a Context Engineering system that solves the root cause of AI-coding failures: the AI doesn't have the right context.

The AI coding problem	bkit's Context Engineering answer
AI hallucinates because it doesn't know your conventions	44 skills (PDCA, Sprint, PM frameworks, …) auto-injected based on intent
AI loses focus as the session grows	Memory + Task Management resumes across sessions; Sprints are context-budgeted
AI ships code that drifts from the spec	11 Quality Gates + `gap-detector` measurement + `pdca-iterator` auto-repair
You only catch bugs at PR review	Phase-by-phase gating: drift is caught at every transition, not at the end
You need to remember the right command	8-language auto-trigger + intent-router; type "login 만들어줘" or "build login" and bkit picks the path
AI sessions are ephemeral; no audit trail	Audit log + Token Ledger + `Docs = Code` philosophy: every decision is on disk

bkit's three philosophies (from `bkit-system/philosophy/core-mission.md`)

Principle	What it means for you
Automation First	You don't need to know PDCA, Sprint, or any command. Type what you want; bkit picks the right workflow. The state machine + workflow engine drive the rest.
No Guessing	If bkit isn't sure, it checks the docs. If still unsure, it asks you. It never makes up an answer. `gap-detector`, `design-validator`, and 11 quality gates enforce this.
Docs = Code	Every feature produces docs (PRD + plan + design + analysis + report). The docs are the contract; bkit verifies that the code matches. `scripts/docs-code-sync.js` enforces 0 drift in CI.

Quick start

# 1. Install (one time)
claude plugin install bkit

# 2. Enable parallel team execution (optional, recommended)
export CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1

# 3. Your very first run — single feature
/pdca pm my-feature        # Describes what you want; bkit handles the rest

# 4. When you're ready for a multi-feature release
/sprint master-plan my-release --name "Q2 Launch" --features auth, billing, reports
# (You approve the plan)
/sprint start my-release-s1

Quality gates — the safety net explained

A "quality gate" is a hard stop that won't let the workflow advance until a measurable condition is true. bkit ships 11 of them. The ones that matter most for new users:

Gate	What it measures	If it fails
M1 matchRate	How much of your design actually appears in the code, 0–100 %	Below 90 % → `pdca-iterator` automatically rewrites the code (up to 5 cycles)
M3 critical issues	Security or correctness bugs flagged by `code-analyzer`	Any critical → workflow pauses, you decide
S1 dataFlow integrity	7-layer check: UI → Client → API → Validation → DB → Response → Client → UI	Below 85 % → 7 hops re-verified one by one

Full M1–M10 + S1 catalog in README-FULL.md §5.

Architecture at a glance

Full architecture deep-dive: README-FULL.md §9.

Documentation

Path	What's there
README-FULL.md	Full command reference, deep workflow internals, agent teams, architecture, Skill Evals
CHANGELOG.md	Release history (single source of truth — latest release: v2.1.34)
CUSTOMIZATION-GUIDE.md	Override any bkit component in your `.claude/` directory
AI-NATIVE-DEVELOPMENT.md	The 6 AI-Native principles and how bkit implements them
`bkit-system/philosophy/`	Core mission, Context Engineering, PDCA methodology, AI-Native principles
`docs/06-guide/sprint-management.guide.md`	Sprint Management deep-dive (English)
`docs/06-guide/sprint-migration.guide.md`	PDCA ↔ Sprint migration mapping (English)

🌟 Real User Hall of Fame

v2.1.19 (2026-05-30 — first entry)

@pruge (James Kim) — dandi-village-ledger project. 10 GitHub issues over 1.5 days (#92–#107) driving bkit v2.1.17, v2.1.18 closes + the entire v2.1.19 Quality Maturation Sprint. 5 reproduction scenarios absorbed as E2E tests at test/e2e/external-dogfood/dandi-*.test.js. See docs/external-dogfooders/pruge.md for the full contribution archive. Thank you for trusting bkit with your production sprint. 🙏

v2.1.20 (2026-05-26 — second entry, first-follower effect validated)

@bj (정병진) — bkit v2.1.14 install incident (2026-05-26, Validation errors: : Unrecognized key: "displayName"). Precise error message + cache path + Cursor IDE environment metadata sharing drove the entire v2.1.20 Marketplace Recovery Sprint (14 features / 3 sub-sprints / 3 new ENH 321/322/323 / 1 new ADR 0011 Plugin Manifest Schema Compliance Policy). Reproduction absorbed at test/e2e/external-dogfood/cc-min-version.test.js (5 TC, Lifecycle Stage 4 Regression Lock achieved). Triggered ADR 0006 § Empirical Validation Gate recovery (~30-day wire delay closed). See docs/external-dogfooders/bj.md for the full contribution archive. Thank you for sharing the precise error message that scoped the entire sprint correctly. 🙏

🚀 bkit Early Adopter Program

Running bkit on a non-trivial production project and willing to file detailed bug reports with reproductions makes you part of bkit's quality system, not just a bug reporter.

Established v2.1.19 (master plan §15.4 DA-1~DA-4, ENH-318 차별화 7/7).

Benefits:

🏆 Public recognition in this README + dedicated archive
🔒 Your reproduction scripts become permanent E2E regression tests
📊 Your activity directly powers bkit's Trust Score (externalDogfoodFeedbackResponseRate component, weight 0.05)
📝 CHANGELOG attribution on every release where your scenarios were absorbed
🤝 Direct line to bkit maintainers — priority issue triage, reproduction-script-first response

DA-4 acquisition goal: by v2.1.20 (30 days post-v2.1.19 GA), measure dogfooder population. DA-4 status (v2.1.20): N=2 confirmed (@pruge + @bj) — first-follower effect validated. v2.1.21+ continues active outreach (CC marketplace narrative, community engagement) to grow N≥3.

License

Apache 2.0 — see LICENSE and NOTICE. POPUP STUDIO PTE. LTD. · kay@popupstudio.ai

File tree

1604

popup-studio-ai/bkit-claude-codeView on GitHub

.claude/
.claude-plugin/
  marketplace.json
  plugin.json
  CLAUDE.md
.github/
  workflows/
    cc-regression-reconcile.yml
    contract-check.yml
.gitignore
.prettierrc
agents/
AGENTS.md
  bkend-expert.md
  bkit-impact-analyst.md
  cc-version-researcher.md
  code-analyzer.md
  cto-lead.md
  design-validator.md
  enterprise-expert.md
  frontend-architect.md
  gap-detector.md
  infra-architect.md
  pdca-iterator.md
  pipeline-guide.md
  pm-discovery.md
  pm-lead-skill-patch.md
  pm-lead.md
  pm-prd.md
  pm-research.md
  pm-strategy.md
  product-manager.md
  qa-debug-analyst.md
  qa-lead.md
  qa-monitor.md
  qa-strategist.md
  qa-test-generator.md
  qa-test-planner.md
  report-generator.md
  security-architect.md
  self-healing.md
  skill-needs-extractor.md
  sprint-master-planner.md
  sprint-orchestrator.md
  sprint-qa-flow.md
  sprint-report-writer.md
  starter-guide.md
AI-NATIVE-DEVELOPMENT.md
assets/
  error-dict.en.json
  error-dict.ko.json
bkit-infra-architecture.html
bkit-infra-architecture.pdf
bkit-system/
  _GRAPH-INDEX.md
  .obsidian/
    app.json
    appearance.json
    core-plugins.json
  components/
    agents/
      _agents-overview.md
    hooks/
      _hooks-overview.md
    scripts/
      _scripts-overview.md
    skills/
      _skills-overview.md
  philosophy/
    ai-native-principles.md
    context-engineering.md
    core-mission.md
    pdca-methodology.md
  README.md
  scenarios/
    scenario-discover-features.md
    scenario-new-feature.md
    scenario-qa.md
    scenario-sprint.md
    scenario-write-code.md
  testing/
    test-checklist.md
  triggers/
    priority-rules.md
    trigger-matrix.md
bkit.config.json
CHANGELOG.md
CODE_OF_CONDUCT.md
commands/
  bkit.md
  output-style-setup.md
CONTRIBUTING.md
CONTRIBUTORS.md
CUSTOMIZATION-GUIDE.md
docs/
  00-pm/
    claude-model-alignment.prd.en.md
    claude-model-alignment.prd.ko.md
    features/
      s0-sqm-baseline.prd.md
      s1-foundation.prd.md
      s2-defense.prd.md
      s3-polish.prd.md
      s4-proactive.prd.md
      s5-measurement.prd.md
      v2118-sprint-trust-ux-fix.prd.md
    skill-post-slash-reach.prd.en.md
    skill-post-slash-reach.prd.ko.md
    v2121-issue-response.prd.md
    v2126-issue-response.prd.en.md
    v2126-issue-response.prd.ko.md
  01-plan/
    features/
      cc-stop-hook-schema-compliance.plan.md
      cc-v2159-response.plan.md
      cc-v2218-compat.plan.en.md
      cc-v2218-compat.plan.ko.md
      claude-model-alignment.plan.en.md
      claude-model-alignment.plan.ko.md
      cross-platform-mac-windows.plan.md
      ctx-eng-godfile-split.plan.md
      ctx-eng-layer-consolidation.plan.md
      final-qa-i18n-docs-sync.plan.md
      issue-89-pdca-status-fix.plan.md
      pdca-task-completion-chain.plan.en.md
      pdca-task-completion-chain.plan.ko.md
      s0-sqm-baseline.plan.md
      s1-foundation.plan.md
      s2-defense.plan.md
      s3-polish.plan.md
      s4-proactive.plan.md
      s5-measurement.plan.md
      skill-guidance-runtime-phase.plan.en.md
      skill-guidance-runtime-phase.plan.ko.md
      skill-post-slash-reach.plan.en.md
      skill-post-slash-reach.plan.ko.md
      stop-hook-stdin-block-139.plan.en.md
      stop-hook-stdin-block-139.plan.ko.md
      tech-debt-deadcode-elimination.plan.md
      v2.1.22-hardening.master-plan.md
      v2116-issue-fixes.master-plan.md
      v2116-release-hardening.plan.md
      v2117-ci-cd-hardening.plan.md
      v2118-carryover-cleanup.plan.md
      v2118-sprint-trust-ux-fix.plan.md
      v2119-bkit-quality-maturation.master-plan.md
      v2121-issue-response.master-plan.md
      v2126-issue-response.plan.en.md
      v2126-issue-response.plan.ko.md
      v2133-defect-response.master-plan.en.md
      v2133-defect-response.master-plan.ko.md
  02-design/
    features/
      cc-stop-hook-schema-compliance.design.md
      cc-v2218-compat.design.en.md
      cc-v2218-compat.design.ko.md
      claude-model-alignment.design.en.md
      claude-model-alignment.design.ko.md
      cross-platform-mac-windows.design.md
      ctx-eng-godfile-split.design.md
      ctx-eng-layer-consolidation.design.md
      final-qa-i18n-docs-sync.design.md
      issue-89-pdca-status-fix.design.md
      pdca-task-completion-chain.design.en.md
      pdca-task-completion-chain.design.ko.md
      s0-sqm-baseline.design.md
      s1-foundation.design.md
      s2-defense.design.md
      s3-polish.design.md
      s4-proactive.design.md
      s5-measurement.design.md
      skill-guidance-runtime-phase.design.en.md
      skill-guidance-runtime-phase.design.ko.md
      skill-post-slash-reach.design.en.md
      skill-post-slash-reach.design.ko.md
      stop-hook-stdin-block-139.design.en.md
      stop-hook-stdin-block-139.design.ko.md
      tech-debt-deadcode-elimination.design.md
      v2116-release-hardening.design.md
      v2117-ci-cd-hardening.design.md
      v2118-carryover-cleanup.design.md
      v2118-sprint-trust-ux-fix.design.md
      v2126-issue-response.design.en.md
      v2126-issue-response.design.ko.md
    LIVING-CONTEXT-GUIDE.md
  03-analysis/
    bkit-architecture-completeness.analysis.md
    bkit-plugin-vibecoding-ux.analysis.md
    cc-v2146-v2150-strict-manifest-validation.analysis.md
    claude-model-alignment.analysis.en.md
    claude-model-alignment.analysis.ko.md
    features/
      cc-stop-hook-schema-compliance.analysis.md
      cc-version-issue-response.analysis.md
      skill-guidance-runtime-phase.analysis.en.md
      skill-guidance-runtime-phase.analysis.ko.md
      skill-post-slash-reach.analysis.md
      stop-hook-stdin-block-139.analysis.en.md
      stop-hook-stdin-block-139.analysis.ko.md
      v2113-sprint-1-domain.iterate.md
      v2113-sprint-2-application.iterate.md
      v2113-sprint-3-infrastructure.iterate.md
      v2113-sprint-4-presentation.iterate.md
      v2113-sprint-5-quality-docs.iterate.md
      v2117-ci-cd-hardening.analysis.md
      v2118-carryover-cleanup.analysis.md
      v2134-hook-reachability.analysis.en.md
      v2134-hook-reachability.analysis.ko.md
    pdca-task-completion-chain.analysis.en.md
    pdca-task-completion-chain.analysis.ko.md
    prompt-caching-optimization.md
    s0-sqm-baseline-gate-fail-plan-2026-05-21T09-59-25-546Z.md
    s0-sqm-baseline-gate-fail-plan-2026-05-21T09-59-32-172Z.md
    security-architecture.md
    v2113-dead-code-and-sprint-integration.analysis.md
    v2118-sqm-baseline.analysis.md
    v2126-issue-response.analysis.en.md
    v2126-issue-response.analysis.ko.md
    zero-script-qa-fork-v2116-verification.md
  04-report/
    bkit-v2112-deep-functional-qa-issues.report.md
    changelog.md
    claude-model-alignment.report.en.md
    claude-model-alignment.report.ko.md
    features/
      bkit-v200-test.report.md
      cc-stop-hook-schema-compliance.report.md
      cc-v2139-v2140-impact-analysis.report.md
      cc-v2140-v2141-impact-analysis.report.md
      cc-v2141-v2142-impact-analysis.report.md
      cc-v2142-v2143-impact-analysis.report.md
      cc-v2143-v2144-impact-analysis.report.md
      cc-v2144-v2145-impact-analysis.report.md
      cc-v2145-v2146-impact-analysis.report.md
      cc-v2146-v2159-impact-analysis.report.md
      cc-v2159-response.report.md
      cc-v2159-v2161-impact-analysis.report.md
      cc-v2161-v2162-impact-analysis.report.md
      cc-v2162-v2168-impact-analysis.report.md
      cc-v2168-v2169-impact-analysis.report.md
      cc-v2169-v2179-impact-analysis.report.md
      cc-v2179-v2181-impact-analysis.report.md
      cc-v2181-v2191-impact-analysis.report.md
      cc-v2191-v2196-impact-analysis.report.md
      cc-v2196-v2198-impact-analysis.report.md
      cc-v2199-v2204-impact-analysis.report.md
      cc-v2205-v2207-impact-analysis.report.md
      cc-v2208-v2210-impact-analysis.report.md
      cc-v2211-impact-analysis.report.md
      cc-v2212-v2214-impact-analysis.report.md
      cc-v2214-v2215-impact-analysis.report.en.md
      cc-v2214-v2215-impact-analysis.report.ko.md
      cc-v2216-v2217-impact-analysis.report.en.md
      cc-v2216-v2217-impact-analysis.report.ko.md
      cc-v2218-impact-analysis.report.en.md
      cc-v2218-impact-analysis.report.ko.md
      cc-v2219-v2220-impact-analysis.report.en.md
      cc-v2219-v2220-impact-analysis.report.ko.md
      cc-v2220-v2221-impact-analysis.report.en.md
      cc-v2220-v2221-impact-analysis.report.ko.md
      cc-v2222-v2223-impact-analysis.report.en.md
      cc-v2222-v2223-impact-analysis.report.ko.md
      cc-v2223-v2224-impact-analysis.report.en.md
      cc-v2223-v2224-impact-analysis.report.ko.md
      cc-v2224-v2225-impact-analysis.report.en.md
      cc-v2224-v2225-impact-analysis.report.ko.md
      cc-v2225-v2226-impact-analysis.report.ko.md
      cross-platform-mac-windows.report.md
      ctx-eng-godfile-split.report.md
      ctx-eng-layer-consolidation.report.md
      final-qa-i18n-docs-sync.report.md
      issue-89-pdca-status-fix.report.md
      pdca-task-completion-chain.report.en.md
      pdca-task-completion-chain.report.ko.md
      s0-sqm-baseline.report.md
      s1-foundation.report.md
      s2-defense.report.md
      s3-polish.report.md
      s4-proactive.report.md
      s5-measurement.report.md
      skill-guidance-runtime-phase.report.en.md
      skill-guidance-runtime-phase.report.ko.md
      stop-hook-stdin-block-139.report.en.md
      stop-hook-stdin-block-139.report.ko.md
      tech-debt-deadcode-elimination.report.md
      v2114-alwaysload-measurement.report.md
      v2116-issue-fixes.report.md
      v2116-release-hardening.report.md
      v2117-ci-cd-hardening.report.md
      v2118-carryover-cleanup.report.md
      v2118-sprint-trust-ux-fix.report.md
      v2120-marketplace-recovery.report.md
      v2121-issue-response.report.md
    v2113-sprint-integration-final-qa.report.md
    v2126-issue-response.report.en.md
    v2126-issue-response.report.ko.md
  05-qa/
    claude-model-alignment.qa-report.en.md
    claude-model-alignment.qa-report.ko.md
    features/
      skill-guidance-runtime-phase.qa-report.en.md
      skill-guidance-runtime-phase.qa-report.ko.md
      stop-hook-stdin-block-139.qa-report.en.md
      stop-hook-stdin-block-139.qa-report.ko.md
    v2118-sprint-trust-ux-fix.qa-report.md
    v2126-issue-response.qa-report.en.md
    v2126-issue-response.qa-report.ko.md
    v2133-defect-response.qa-report.en.md
    v2133-defect-response.qa-report.ko.md
    v2134-hook-reachability.qa-report.en.md
    v2134-hook-reachability.qa-report.ko.md
  05-research/
    external-dogfooders/
      jbjeong-2026-05-26-displayName-reject.md
  06-guide/
    branch-protection-setup.guide.md
    cc-compatibility.guide.md
    cc-version-monitoring.guide.md
    contract-baseline-rollforward.guide.md
    eval-rebaseline.guide.en.md
    eval-rebaseline.guide.ko.md
    sprint-management.guide.md
    sprint-migration.guide.md
    test-file-tracking-policy.guide.md
    version-policy.guide.md
  adr/
    0003-cc-version-impact-empirical-validation.md
    0004-agent-hook-multi-event-deferral.md
    0005-application-layer-pilot.md
    0006-cc-upgrade-policy.md
    0007-sprint-as-meta-container.md
    0008-sprint-phase-enum.md
    0009-sprint-autorun-trust-scope.md
    0010-effort-aware-invariant.md
    0011-plugin-manifest-schema-compliance.md
    0012-sprint-stop-hook-output-enforcement.md
    0013-context-engineering-factoring.md
    0014-deprecation-registry.en.md
    0014-deprecation-registry.ko.md
    0015-locale-scoped-trigger-deferral.en.md
    0015-locale-scoped-trigger-deferral.ko.md
  ai-agent-security-audit-2026.report.md
  ai-native-role-redistribution.md
  archive/
    2026-05/
      00-pm/
        bkit-v2112-evals-wrapper-hotfix.prd.md
        bkit-v218-bug-fixes.prd.md
        v2113-docs-sync.prd.md
      01-plan/
        features/
          bkit-v2110-compatibility-policy.plan.md
          bkit-v2110-gap-closure-plan-plus.plan.md
          bkit-v2110-integrated-enhancement.plan.md
          bkit-v2110-invocation-contract-addendum.plan.md
          bkit-v2111-integrated-enhancement.plan.md
          bkit-v2112-evals-wrapper-hotfix.plan.md
          bkit-v216-enhancement.plan.md
          bkit-v216-integrated-enhancement.plan.md
          bkit-v217-issue-79-hotfix.plan.md
          bkit-v217-issue-79-hotfix.prd.md
          bkit-v219-docs-sync.plan.md
          cc-v2110-v2112-issue81-response.plan.md
          cc-v2112-v2114-impact-analysis.plan.md
          cc-v2114-v2116-impact-analysis.plan.md
          cc-v2116-v2117-impact-analysis.plan.md
          s1-ux.plan.md
          s1-ux.prd.md
          s2-ux.plan.md
          s2-ux.prd.md
          s3-ux.plan.md
          s3-ux.prd.md
          s4-ux.plan.md
          s4-ux.prd.md
          sprint-management.master-plan.md
          sprint-ux-improvement.master-plan.md
          v2110-docs-sync.plan.md
          v2113-docs-sync.master-plan.md
          v2113-docs-sync.plan.md
          v2113-sprint-1-domain.plan.md
          v2113-sprint-1-domain.prd.md
          v2113-sprint-2-application.plan.md
          v2113-sprint-2-application.prd.md
          v2113-sprint-3-infrastructure.plan.md
          v2113-sprint-3-infrastructure.prd.md
          v2113-sprint-4-presentation.plan.md
          v2113-sprint-4-presentation.prd.md
          v2113-sprint-5-quality-docs.plan.md
          v2113-sprint-5-quality-docs.prd.md
      02-design/
        features/
          bkit-v2110-gap-closure.design.md
          bkit-v2110-integrated-enhancement.design.md
          bkit-v2110-orchestration-integrity.design.md
          bkit-v2111-integrated-enhancement.design.md
          bkit-v2111-sprint-alpha.design.md
          bkit-v2111-sprint-beta.design.md
          bkit-v2111-sprint-delta.design.md
          bkit-v2111-sprint-gamma.design.md
          bkit-v2112-evals-wrapper-hotfix.design.md
... 1478 more

FAQ

What is bkit?: A Claude Code plugin that verifies AI-generated code against its own design specs. Three commands. Anyone — even someone vibe-coding for the first time — can ship robust, production-quality software.
How do I install bkit?: Run these in Claude Code: /plugin marketplace add popup-studio-ai/bkit-claude-code. Then prompt normally.
Does bkit auto-invoke its skills?: Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
Is bkit free?: Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.

bkit

Skills

Agents

Commands

Hooks

README

bkit — AI Native Development OS

Who bkit is for

What you'll achieve with bkit

The 4-step experience

Step 1 — Plan the release in depth

Step 2 — Approve, register, remember

Step 3 — Auto-run each sprint through PDCA

Step 4 — Govern with one dial

How the bkit author actually uses bkit

Step A — Use Claude Code as a thinking amplifier before the master plan

Step B — Hand the rest to Trust Level 4

The three commands

How bkit closes the AI-coding gap — Context Engineering

bkit's three philosophies (from bkit-system/philosophy/core-mission.md)

Quick start

Quality gates — the safety net explained

Architecture at a glance

Documentation

🌟 Real User Hall of Fame

v2.1.19 (2026-05-30 — first entry)

v2.1.20 (2026-05-26 — second entry, first-follower effect validated)

🚀 bkit Early Adopter Program

License

File tree

bkit

Skills

Agents

Commands

Hooks

README

bkit — AI Native Development OS

Who bkit is for

What you'll achieve with bkit

The 4-step experience

Step 1 — Plan the release in depth

Step 2 — Approve, register, remember

Step 3 — Auto-run each sprint through PDCA

Step 4 — Govern with one dial

How the bkit author actually uses bkit

Step A — Use Claude Code as a thinking amplifier before the master plan

Step B — Hand the rest to Trust Level 4

The three commands

How bkit closes the AI-coding gap — Context Engineering

bkit's three philosophies (from bkit-system/philosophy/core-mission.md)

Quick start

Quality gates — the safety net explained

Architecture at a glance

Documentation

🌟 Real User Hall of Fame

v2.1.19 (2026-05-30 — first entry)

v2.1.20 (2026-05-26 — second entry, first-follower effect validated)

🚀 bkit Early Adopter Program

License

File tree

bkit's three philosophies (from `bkit-system/philosophy/core-mission.md`)

bkit's three philosophies (from `bkit-system/philosophy/core-mission.md`)