agent-loop-ext
Crash-resilient external agent loop with state persistence and CI/CD integration
Generate traceability report from @-mentions
$ npx -y skills add jmagly/aiwg --skill mention-report --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/mention-reportContext preview
The summary Claude sees to decide when to auto-load this skill.
Generate traceability report from @-mentions
namespace: aiwg name: mention-report platforms: [all] description: Generate traceability report from @-mentions
<!-- AIWG-SKILL-CALLOUT --> > **Skill access pattern (post-kernel-pivot, 2026.5+)** > > Skill names referenced in this document are AIWG skills, **not slash commands**. Most are not kernel-listed and cannot be invoked as `/skill-name` by the platform. Reach them via: > > ```bash > aiwg discover "<capability>" > aiwg show skill <name> > ``` > > Only kernel-listed skills (`aiwg-doctor`, `aiwg-refresh`, `aiwg-status`, `aiwg-help`, `use`, `steward`) are directly invokable as slash commands. See [skill-discovery rule](../../../addons/aiwg-utils/rules/skill-discovery.md).
Generate traceability report showing relationships between artifacts.
/mention-report # Markdown report to stdout /mention-report --format json # JSON format /mention-report --format csv # CSV for spreadsheets /mention-report --output .aiwg/reports/traceability.md
| Option | Default | Description | |--------|---------|-------------| | --target | . | Directory to analyze | | --format | md | Output format: md, json, csv | | --output | stdout | Write to file |
## Requirements Coverage | Requirement | Implemented | Tested | Documented | |-------------|-------------|--------|------------| | UC-001 | ✓ src/auth/ | ✓ test/auth/ | ✓ docs/ | | UC-002 | ✓ src/api/ | ✗ | ✗ | | UC-003 | ✗ | ✗ | ✗ | Coverage: 67% implemented, 33% tested, 33% documented
## Architecture Traceability | ADR | Referenced By | Implementation | |-----|---------------|----------------| | ADR-001 | 3 files | src/db/ | | ADR-002 | 5 files | src/auth/, src/api/ | | ADR-003 | 1 file | src/cache/ |
## Security Control Coverage | Control | Implementation | Verification | |---------|----------------|--------------| | AUTHN-001 | src/auth/middleware.ts | test/security/ | | AUTHZ-001 | src/auth/permissions.ts | ✗ |
## Dependency Graph UC-001 (User Authentication) ├── ADR-005-jwt-strategy.md ├── src/services/auth/ │ ├── login.ts │ ├── logout.ts │ └── refresh.ts ├── test/integration/auth/ └── docs/api/auth.md
{
"generated": "2025-01-15T10:30:00Z",
"summary": {
"total_mentions": 142,
"requirements": { "total": 15, "covered": 12 },
"adrs": { "total": 8, "referenced": 6 }
},
"traceability": [
{
"artifact": ".aiwg/requirements/UC-001.md",
"type": "requirement",
"referenced_by": ["src/auth/login.ts", "test/auth/login.test.ts"],
"coverage": { "implemented": true, "tested": true, "documented": true }
}
]
}aiwg mention-report [--format md|json|csv] [--output <file>]
Generate report for: $ARGUMENTS
Reusable project context and specialist workflows for the AI tools you already use. Plan software, coordinate specialist reviews, prepare campaigns, investigate incidents, organize research, curate media, and maintain operational knowledge.
Repo: jmagly/aiwg
Crash-resilient external agent loop with state persistence and CI/CD integration
Detect requests for iterative autonomous agent loops and route to the appropriate loop executor
Automatically execute tests when code-generating agents modify source files, enforcing the execute-before-return pattern
Enable agent loops to learn from similar past tasks and share patterns across loops
Query and manage the executable feedback debug memory
Execute tests on generated code and iterate until passing