Skip to content

Destynova2/cli-code-skills / cli-forge-chef

cli-forge-chef

Verified

Generate a multi-agent orchestrator for any project using the Brigade de Cuisine pattern: Chef (plans, decides), Sous-Chef (validates, merges), Commis (execute). Clients order via a Menu (PERT), the kitchen delivers Plats (merged features). Creates tmuxinator config, prompts, shared-state memory, quality gates, and permissions. Uses Claude Code Agent Teams (TeamCreate + SendMessage) with visible tmux panes. Use when the user wants to parallelize work across multiple Claude Code agents, orchestrate a multi-agent sprint, or says 'boss', 'multi-agent', 'orchestrate', 'parallelize agents', 'team of claudes', 'sprint multi-agent', 'brigade', 'chef'. Also triggers on 'swarm', 'agent team', 'parallel workers', 'PERT multi-agent'.

references/quality-gates.md

View on GitHub
# Quality Gates — CLI skills for merge gates

## Available gates

| Skill | When | Blocks if | Token cost |
|-------|------|-----------|------------|
| `/cli-audit-tangle` | Pre-cycle (Phase 0) | God functions, cycles | High |
| `/cli-audit-drift` | Per merge | Misses (code ≠ CONTRACTS.md contract) | Medium |
| `/cli-audit-code` | Per merge | CQI drops by > 0.2 | Medium |
| `/cli-audit-test` | Per merge | Test pyramid unbalanced | Medium |
| `/cli-audit-sync` | Post-merge (if docs) | Docs out of sync | Medium |
| `/cli-cycle` | End of cycle | Global regression | High |

## When to use what

### Minimum viable (any project)

```
Phase 0: /cli-audit-tangle -> assign modules
Per merge: /cli-audit-code -> minimum quality
End of cycle: /cli-cycle -> scorecard
```

### Standard (project with contracts/docs)

```
Phase 0: /cli-audit-tangle
Per merge: /cli-audit-code + /cli-audit-drift
Post-merge docs: /cli-audit-sync
End of cycle: /cli-cycle
```

### Full (enterprise/regulated project)

```
Phase 0: /cli-audit-tangle
Per merge: /cli-audit-code + /cli-audit-drift + /cli-audit-test
Post-merge docs: /cli-audit-sync
End of cycle: /cli-cycle
```

## Integration in the Chef prompt

```markdown
## Quality Gates

### Protocol

1. Commis sends "Task complete" via SendMessage
2. Sous-Chef runs the gates in the gate window:
   /cli-audit-code {scope}
   /cli-audit-drift {scope}
3. If a gate fails:
   SendMessage { to: "{worker}", summary: "gate failed", message: "GATE FAILED: {detail}. Fix and recommit." }
4. Wait for the fix, re-run the gate
5. If the gate passes: merge
```

## Protocol when a gate fails

1. Read the audit report
2. Identify the files/functions at fault
3. Send the worker a precise message:
   - Which gate failed
   - Which file/function is at fault
   - What the contract/rule expected
   - What the code does instead
4. Wait for the worker's fix
5. Re-run the gate
6. If 3 consecutive failures: escalate to the user
```
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 469kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 321kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 321kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 321kUpdated Claude CodeCodexVerifiedInstall