brooks-health
Run a Brooks-Lint codebase health dashboard across all four dimensions
A command is the one you type. It runs exactly when you ask it to, and never before.
1,549 commands across 626 plugins.
Run a Brooks-Lint codebase health dashboard across all four dimensions
Plan-then-execute against SPEC.md. Native Claude Code loop, no sub-agents.
Drift detector. Diff SPEC.md against code. Read-only, zero writes.
Spare-budget design pass. Make one shallow module deep — smaller interface, behavior held, tests green before & after.
Analyzes your project's dependencies and checks architecture health.
Analyzes application performance from a user experience perspective and quantifies experience improvements from optimizations. Calculates UX scores based on…
Verifies if a statement is true by checking your project's code and documentation.
Interrogate a spec with Loki's Devil's-Advocate grill before building, and summarize the hardest questions it surfaces.
Check whether the spec has drifted from its lock using Loki's living-spec drift detection, and summarize the report.
Run Loki's deterministic PR verification on the current change and summarize the evidence verdict.
**参数说明**:`$ARGUMENTS` 由 Claude Code 自动传递,对应用户输入的参数部分(如 `/cache-patch status` 中的 `status`)。
Cleans up all git branches marked as [gone] (branches that have been deleted on the remote but still exist locally), including removing associated worktrees.
Discover installed and available Salesforce capabilities, drill into a domain or skill, or explicitly add one catalog-authorized project skill.
Authenticate to a new Salesforce org via the browser (sf org login web). Optionally set the org as the project's default target.
Sign out of one or all Salesforce orgs (sf org logout). Confirms before destructive action.
전문 에이전트 자동 라우팅. 법률, 재무, 특허, SEO, 마케팅, 기획, BM 설계(BMC/Lean/JTBD/Wardley/Blue Ocean/Lightning Sprint), 코드리뷰, 아키텍처, 견적, CRM, HR/인사, 노무(노동법/해고/산재/취업규칙), 리서치, 데이터…
Add todo item to TO-DOS.md with context from conversation
Comprehensive security audit with intelligent multi-phase orchestration and automatic agent selection
Load testing and performance benchmarking with intelligent scenario generation
触发 product-lead 派 apple-release-engineer 把合并后的 main 代码构建成签名分发包(TestFlight / 公证 DMG / 内部包)并冒烟自检;通过后交接 apple-qa-engineer 跑 E2E/UAT
生成/实时刷新 AGF 开发看板(task 卡片三列 kanban + 成员栏 + 工序 chips 的自包含 HTML,浏览器 open 即用)。数据全来自现成落盘态(~/.claude/tasks + ~/.claude/teams config + docs 报告 frontmatter),零新状态。
Deeply Understand (codemap) 入口 — 代码图谱 / 变更影响分析 / 理解地图(ADR-021,替换 agf-understand)。在 tools/codemap/ 跑 codemap CLI
Address code review feedback — corroborate, validate, and implement changes from a review's final.md.
Deep code and data analysis with batch processing capabilities.
Assess your Claude Code level (0-10) and get a personalized roadmap to the next one
**Navigation**: [← Main Workflow](../workflow-steps.md) | [Step 2: Triage →](2-triage.md)
**Navigation**: [← Step 1: Analyze](1-analyze.md) | [Main Workflow](../workflow-steps.md) | [Step 3: Plan →](3-plan.md)
**Navigation**: [← Step 2: Triage](2-triage.md) | [Main Workflow](../workflow-steps.md) | [Step 4: Fix →](4-fix.md)
run in the background using bash background <example> // replace it with your 1. the BE @REPOS/xxx-be (by default XXXX PORT, use `bun run start:dev` because…
Interview Boss about the project, then reason from first principles to design the ideal ATLAS operating identity/system-prompt for it — free to drop…
Commit what is already staged — runs the commit subagent in the background, following the ATLAS commit convention.
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic