meta_harnesslisted
Install: claude install-skill zedarvates/botte-secrete
# meta_harness — orchestration multi-agent
Un meta-harness qui orchestre les skills Botte (audit, fix, counter-audit, optimize, test)
dans un pipeline gouverné. Chaque étape tourne dans son propre sandbox
(subprocess, workdir isolé). Governance = approval gates + budgets + rollback.
## Concept
```
USER: "audit + fix mon projet"
│
▼
Meta-Harness
├── Orchestrator → Plan: [audit] → [review] → [fix] → [test]
│
├── Sandbox 1: Porthos audit (skills/directives_audit)
├── Sandbox 2: Rochefort counter-audit (skills/cardinal)
├── Sandbox 3: d'Artagnan fix (skills/fix)
└── Sandbox 4: run tests
│
├── Governance → approval gate avant apply
│
└── Report → synthèse multi-agent
```
## Agents disponibles
| Agent | Skill Botte | Rôle |
|-------|-------------|------|
| `porthos` | directives_audit | Audit initial |
| `rochefort` | cardinal | Contre-audit (red team) |
| `d'artagnan` | fix | Correction automatique |
| `aramis` | optimize | Optimisation token |
| `conductor` | conductor | Planification |
| `security` | security_scanner | Scan sécurité |
| `fast_context` | fast_context | Exploration repo |
## Usage
```bash
# Pipeline complet: audit → counter-audit → fix → test
python -m skills.meta_harness.cli run . audit counter-audit fix test
# Voir les pipelines disponibles
python -m skills.meta_harness.cli plans
# Lancement avec approval gate
python -m skills.meta_harness.cli run . audit fix --approval
# Voir l'état d'un pipeline
python