Skip to main content
ClaudeWave
Skill155 estrellas del repoactualizado 18d ago

brownfield-drift

Enforces architecture boundaries defined in PLAN.md. Use when a PR crosses module/service boundaries, when the dev asks "are we following the architecture?", or as a scheduled architecture health check. Not for querying what a module does — use brownfield-chat for that.

Instalar en Claude Code
Copiar
git clone --depth 1 https://github.com/wednesday-solutions/ai-agent-skills /tmp/brownfield-drift && cp -r /tmp/brownfield-drift/skills/brownfield-drift ~/.claude/skills/brownfield-drift
Después abre una sesión nueva de Claude Code; el skill carga automáticamente.

SKILL.md

## When to use
- Dev asks "are we following the architecture?" or "is this a valid change?"
- PR touches files near module boundaries or service interfaces
- Weekly architecture health check
- Any cross-service import was just added

## When NOT to use
- "What does module X do?" → use **brownfield-chat**
- "What breaks if I change X?" → use **brownfield-chat**
- Graph coverage is low on a file → use **brownfield-fix (it fills gaps before editing)**
- No PLAN.md exists — drift requires machine-readable boundaries in PLAN.md

## What to do
1. Run `wednesday-skills drift` via Bash tool
2. Report violations with:
   - The specific edge that violates the rule
   - The commit that introduced it (when available)
   - The suggested fix per PLAN.md intent
3. For PR reviews: run `wednesday-skills drift --since <base-commit>` to only report new violations
4. For a single rule: `wednesday-skills drift --rule <rule-name>`

## Adding constraints to PLAN.md
If the project has no constraints block, add one to PLAN.md:

```json
{
  "boundaries": [
    {
      "rule": "frontend-never-imports-db",
      "description": "Frontend components must never import DB layer directly",
      "from": "src/app/**",
      "to": "src/lib/db/**",
      "type": "forbidden"
    },
    {
      "rule": "no-circular-deps",
      "description": "No circular dependencies anywhere",
      "scope": "**",
      "type": "no-cycle"
    }
  ]
}
```

## Violation types
| Type | What it catches |
|------|----------------|
| `forbidden` | Import from A → B that should never exist |
| `ownership` | Logic pattern appearing outside its designated owner |
| `no-direct-import` | Direct import between services that should use API |
| `no-cycle` | Circular dependency between modules |

## Never
- Auto-fix boundary violations — always ask the dev first
- Flag existing violations on a PR that did not introduce them (use `--since`)
- Run on projects without machine-readable PLAN.md constraints
- Report the same violation twice in one review session

## CLI reference
```bash
wednesday-skills drift                              # full check
wednesday-skills drift --rule frontend-never-imports-db  # single rule
wednesday-skills drift --since abc1234              # new drift only (for PR review)
```
module-audit-agentSkill

Use when asked to audit a module, check its health, or assess whether it should be refactored. Runs structural query, risk check, and test generation automatically.

onboard-dev-agentSkill

Use when a dev is new to the project, asks for an overview, or wants to get oriented quickly. Fills graph gaps then runs a guided codebase interview.

pr-review-agentSkill

Full PR review orchestrator. Use when asked to review a PR or check if it is ready to merge. Runs blast radius + drift check on changed files, then hands off to pr-review for comment triage and fixes. Do NOT use pr-review directly for full reviews — use this.

codebase-intelSkill

Unified codebase intelligence. Handles all questions about structure, logic, risk, and dependencies. Combines natural-language Q&A with deterministic lookups and pre-edit blast radius checks.

deploy-checklistSkill

Pre-deploy and post-deploy checklist skill. Ensures env vars, migrations, CI, rollback plan, smoke tests, and monitoring are verified before and after every deployment.

greenfieldSkill

Parallel persona planning for new projects. Research agent runs first to build domain context, then Architect, PM, and Security agents run in parallel. Synthesis agent combines all perspectives into a detailed GSD-style PLAN.md with Tensions section.

pr-reviewSkill

Fix engine for PR review comments. Fetches review comments (Gemini bot or human), categorizes by impact, posts a prioritized fix queue, and applies fixes on dev approval. Called directly for quick fixes, or internally by pr-review-agent as part of full PR review.

standards-kitSkill

Unified development and design standards. Enforces code quality (complexity < 8), strict naming conventions, and the mandatory use of approved UI component libraries.