documenter
AgentWrites or surgically updates one ./diagrams doc (infrastructure, architecture, or a simplified overview) from the code.…
11,388 agents. Claude Code subagents shipped in plugins found in public marketplaces and GitHub repositories. Each works in Claude Code and Cursor.
Writes or surgically updates one ./diagrams doc (infrastructure, architecture, or a simplified overview) from the code.…
Turns ./diagrams docs into D2 sources and renders them to themed, GitHub-safe SVGs. Dispatched by the d2:diagram skill with the…
Adversarially checks ./diagrams docs and renders against the code and against each other, and returns findings without fixing…
Researches a single decision area and produces a structured comparison table. Spawned by discuss-phase for gray-area decisions.
Analyzes Claude Code session logs for PBR workflow compliance, hook firing, state file hygiene, and user experience quality.…
Explores existing codebases and writes structured analysis documents. Four focus areas: tech, arch, quality, concerns.
Use for hard problems only — cross-cutting design, gnarly multi-file debugging, race conditions and concurrency, performance…
Use for standard implementation work — features, bug fixes, writing tests, refactors scoped to roughly 5 files or fewer, API…
Use proactively for mechanical, low-risk edits — renames, typo fixes, comment and docstring updates, formatting, simple config…
Java system architect — designs project structure, module layout, class hierarchies, and applies architecture patterns for Java…
Java build error resolver — diagnoses and fixes Maven, Gradle, and javac compilation errors with minimal code changes
Java performance reviewer — identifies N+1 queries, memory leaks, thread safety issues, and inefficient code patterns in Java 8+…
Use when asked to analyze BigQuery SQL files across a project for cost optimization opportunities, estimate total query costs, or…
Use when asked to review all SQL files in a project or directory for BigQuery anti-patterns, scan a codebase for SQL performance…
Use when asked to analyze table schemas across a project, recommend partitioning and clustering strategies for existing tables,…
Use this agent when you need to validate design implementations in real browsers for Drupal or WordPress projects. This agent…
Use when reviewing Litestar PRs/code for stack-aware DTOs, guards, DI, data services, pagination, settings, async I/O, plugins,…
Meta-agent that adopts external personalities and adapts them to LETS modes. Loads identity from personality text provided in…
System design expert for architecture reviews, pattern analysis, SOLID principles evaluation, and coupling/abstraction…
Backend development expert for API design review, business logic analysis, error handling assessment, and performance evaluation.…
Async fan-out orchestrator. Given an approved backlog of GitHub issues, it follows the delegate-backlog skill — the configured…
Product-owner orchestrator. Given an idea, brief, or document (in any form), it reads the source, learns the team's tracker…
Orchestrator for the issue-to-PR workflow. Given a user story ID (e.g. PROJ-1234, ENG-42, #123), it fetches the ticket and any…
Curator for the external evidence over self-description lane in Gauntlet Loop Brain. Use when maintaining source coverage,…
Grounded secretary for Gauntlet Loop Brain. Use for source-cited questions about designing, running, evaluating, and governing…
Curator for the honest stopping and acceptance lane in Gauntlet Loop Brain. Use when maintaining source coverage, questions,…
Autonomously author NEW verifiable stateful code from a feature description — draft a contract, author a SAM v2 strict-profile…
Autonomously prepare an invariant-elicitation session — harvest candidate invariants from the contract vocabulary, traces, and…
Autonomously check whether a state-machine version change is safe against the live fleet — classify it into compatibility lanes,…
Use this agent when designing APIs, building server-side logic, implementing databases, or architecting scalable backend systems.…
Use this agent when setting up CI/CD pipelines, configuring cloud infrastructure, implementing monitoring systems, or automating…
Use this agent when building user interfaces, implementing React/Vue/Angular components, handling state management, or optimizing…
Requirements analyst. MUST BE USED for ambiguous requests, requirements gathering, scope assessment, feasibility checks, and…
Technical architect. MUST BE USED for system design, API design, implementation planning, multi-file refactoring, and agent…
Analyzes tasks and decomposes them into a sequence of agent steps for execution.
Business operations specialist covering market analysis, pricing strategy, go-to-market planning, and competitive intelligence.…
Content strategist specializing in messaging, copywriting, tutorials, documentation, and launch communications. Use proactively…
Product designer specializing in UI/UX, user flows, HTML mockups, and design systems. Use proactively when creating user…
Impl-blind test/oracle author — writes conformance tests from a spec-only brief. Tool-restricted by definition (no…
Implementer — writes production code, tests, and migrations. The "generic engineer" fallback when no narrower specialist exists.…
Log and metrics analyst — reads .cladding/audit.log.jsonl, perf/baseline.json, and drift reports; surfaces patterns the human can…
Use this agent for managing DDEV-based Drupal 11 projects — installing/updating modules, running Drush commands, managing…
Use this agent after creating or modifying a CLAUDE.md file. Reviews quality including instruction specificity, token efficiency,…
Use this agent after creating or modifying a hook. Reviews quality including exit code contract, performance, file filtering,…
Reviews a single refactor phase diff before commit. Called by applying-refactors at each phase checkpoint. Enforces 400 LOC cap,…
Use proactively in the background after creating or modifying multiple vault notes, or when asked about vault link health. Lowest…
Use proactively in the background after completing significant work blocks, after git commits (triggered automatically by…
Use proactively when researching what the vault knows about a topic, before creating new notes, or when exploring existing…
Agent body content should meet minimum length requirements
Agent disallowedTools must be an array of tool names
Action-specific Auto-Harness Evaluator subagent for contract review. Use only when the current legal action is evaluator_review.
Action-specific Auto-Harness Evaluator subagent for parallel contract review. Use only when the current legal action is…
Action-specific Auto-Harness Evaluator subagent for final report synthesis. Use only when the current legal action is…
Converts test scenarios into executable Playwright, Cypress, or Gherkin test code
Validates test scenarios against a running application using Chrome MCP — navigates, interacts, and verifies in a real browser
Use this agent when qa-output/functional-review.md or qa-output/browser-validation.md reports any gap, failed scenario, or…
Image generation and editing agent. Creates photos, illustrations, icons, website visuals, placeholders, banners, thumbnails, and…
Dumb passthrough relay between Claude Code phone app and a Codex/Gemini pane. Forwards messages verbatim, displays output…
ControlFlow Planner — saves a durable, risk-reviewed plan before non-trivial implementation and hands execution back to native…
Financial and fiscal controller for Frihet ERP. Delegate to this agent to audit pending receivables, reconcile monthly revenue…
Loaded when the user invokes `/learn-this`, says "learn this" / "remember this", or accepts your auto-detect offer to capture a…
Loaded when the user invokes `/new-rule` or says "new rule" to add a rule from scratch (not tied to a correction).
You are the morph-deck composer. Given a brief + design tokens + primitive library, emit a complete `stages.ts` and `data.ts` for…
Acceptance auditor for the dotnet-qa pipeline - verifies a story implementation against its spec, one verdict per acceptance…
Enumeration worker for the dotnet-refactor pipeline - builds the complete branch/consumer/sibling map for a target area before…
Post-design audit worker for the dotnet-refactor pipeline - checks every change already in the branch against the approved design…
Orchestrator agent for software development. Analyzes user requests, creates implementation plans, delegates tasks to specialist…
Backend development agent. Implements server-side code, APIs, business logic, and authentication. Invoke for REST/GraphQL APIs,…
Database development agent for data layer implementation. Designs schemas, writes migrations, optimizes queries, and manages data…
Adds, edits or retires a check in an existing skill of this repository and propagates the change to every file that states a…
Audits this repository's credit-and-cite rule — finds checks, thresholds, formulas, quotes, parameter names and adapted work that…
Finds semantic drift across this repository's 29 skills and root docs that verify-docs.sh cannot detect — the same metric given…
WCAG 2.1 compliance, screen readers, keyboard navigation, color contrast
REST and GraphQL API design, OpenAPI specs, versioning strategies
Backend architecture and API design expert for scalable systems
Use this agent ONLY when a human has just run /memory-seed and the new L1 atoms need folding into scenes and persona. Automatic…
Navigation subagent over tandem's shared Chrome. Use it ONLY for HEAVY read/extraction (large snapshots, scraping, walking many…
This agent is no longer used. All orchestration logic lives in `commands/haunt-test.md` so that output renders at the command…
You are a sub-agent that tests one specific page as a given persona. You are spawned in parallel with other page-tester agents.
This agent is no longer used. Report generation is inlined into `commands/haunt-test.md` so there is no sub-agent bubble. The…
한국어로 Claude Code 사용법을 묻는 사용자를 돕는 서브에이전트. 커맨드 실행, 워크플로우 안내, CLAUDE.md 작성을 한국어로 지원합니다.
Synthesize multiple research notes into comprehensive, well-structured reports with cross-references and insights
Research a specific subtopic using web search, gathering authoritative sources, statistics, and expert insights
Executes semantic index management operations (index, incremental-reindex, status). Creates, updates, and inspects semantic…
Use when migrating from Kubernetes, Docker Compose, or Helm to Control Plane. Picks the right converter, runs it, analyzes what…
Use when a Control Plane workload is unhealthy, crashing, not starting, or behaving unexpectedly. Diagnoses image pull errors,…
The `xhigh` rung of `cad-assumptions-analyzer` (codebase assumption gathering); `bin/route.mjs` picks it, not the user.
The `high` rung of `cad-assumptions-analyzer` (codebase assumption gathering); `bin/route.mjs` picks it, not the user.
The `low` rung of `cad-assumptions-analyzer` (codebase assumption gathering); `bin/route.mjs` picks it, not the user.
Designs software architecture from a confirmed PRD. Produces ARCHITECTURE.md and optional ADRs. Applies scale-adaptive depth…
Decomposes a confirmed ARCHITECTURE.md into a structural implementation roadmap of isolated, dependency-ordered chunks. Applies…
Use this agent for rigorous quality assessment of work produced by other agents, particularly producer-agent. Invoke after any…
Builds and operationalizes AI safety — turning safety assessments into shipped safeguards: safety evals in CI/CD, guardrail…
Senior AI safety reviewer for an end-to-end SAFETY assessment of a model or feature — harm modeling, safety evaluation,…
Coordinates defensive operations end to end — detection engineering, incident response, threat hunting, and threat intelligence —…
Account-Abstraction (ERC-4337) specialist. EntryPoint, Bundler, Paymaster, smart-wallet (SimpleAccount, Safe-AA, Kernel,…
AMM-specific audit specialist. Uniswap V2/V3/V4, Curve, Balancer, Berachain BEX, custom AMMs. Use when the target is an AMM,…
Specialist for inline assembly / Yul. Reviews memory layout, return-data handling, dirty-bits, opcode usage. Use whenever…
Use after changing the ultrapowers engine, embedded prompts, manifests, README, or benchmark docs — reviews the diff…
© 2026 Flowy
Built for Claude Code · Not affiliated with Anthropic
Logos are trademarks of their owners.