Pre-action boundary checking — validates agent tool calls against declared capabilities and task contracts
中文简介正在准备中。当前显示原文说明。
Audit agent dependencies and references
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Audit agent dependencies to ensure all skill and guide references are valid and symlinks are working.
--all, -a Audit all agents
--verbose, -v Show detailed results
--fix Auto-fix issues (delegates to /fix-refs)
1. Load agent configuration
└── Read agent .md file
2. Check skills
├── Skill exists in .claude/skills/
└── Skill path is valid
3. Check guides
├── Guide exists in templates/guides/
└── Guide path is valid
4. Report results
[mgr-supplier:audit lang-golang-expert]
Auditing: lang-golang-expert
Skills:
✓ go-best-practices
Path: .claude/skills/go-best-practices/
Status: Valid
Guides:
✓ golang
Path: templates/guides/golang/
Status: Valid
Summary:
Skills: 1/1 valid
Guides: 1/1 valid
Status: HEALTHY
[mgr-supplier:audit --all]
Auditing all agents...
sw-engineer:
✓ lang-golang-expert (2/2 deps valid)
✓ lang-python-expert (2/2 deps valid)
✓ lang-rust-expert (2/2 deps valid)
✗ lang-kotlin-expert (1/2 deps valid)
└─ Missing: kotlin guide symlink
sw-engineer/backend:
✓ be-fastapi-expert (2/2 deps valid)
✓ be-springboot-expert (2/2 deps valid)
✓ be-go-backend-expert (2/2 deps valid)
infra-engineer:
✓ infra-docker-expert (2/2 deps valid)
✓ infra-aws-expert (2/2 deps valid)
Summary:
Total agents: 15
Healthy: 14
Issues: 1
Run "mgr-supplier:fix lang-kotlin-expert" to fix issues.
[mgr-supplier:audit lang-golang-expert --verbose]
Auditing: lang-golang-expert
Configuration:
Path: .claude/agents/lang-golang-expert.md
Type: sw-engineer
Source: internal
Declared Skills:
[1] go-best-practices
Path: .claude/skills/go-best-practices/
Exists: ✓
Declared Guides:
[1] golang
Path: templates/guides/golang/
Exists: ✓
Cross-references:
✓ go-best-practices.used_by includes lang-golang-expert
✓ golang.used_by includes lang-golang-expert
Status: HEALTHY (all checks passed)
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Pre-action boundary checking — validates agent tool calls against declared capabilities and task contracts
中文简介正在准备中。当前显示原文说明。
Auto-detect project context and optimize harness — deactivate unused agents/skills, suggest missing experts, generate project profile
中文简介正在准备中。当前显示原文说明。
Adversarial code review using attacker mindset — trust boundary, attack surface, business logic, and defense evaluation
中文简介正在准备中。当前显示原文说明。
Apache Airflow best practices for DAG authoring, testing, and production deployment
中文简介正在准备中。当前显示原文说明。
Alembic migration patterns for naming conventions, safety checks, expand-contract, env.py configuration, and CI integration
中文简介正在准备中。当前显示原文说明。
Pre-routing ambiguity analysis — scores request clarity and asks clarifying questions when needed (inspired by ouroboros)
中文简介正在准备中。当前显示原文说明。