메뉴
Meta-Harness orchestre les skills Botte comme des agents interchangeables dans un pipeline gouverné. Planifie → exécute en sandbox → review croisé → applique avec garde-fous. Inspiré d'Omnigent mais 100% Botte-native.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | meta_harness |
| description | Meta-Harness orchestre les skills Botte comme des agents interchangeables dans un pipeline gouverné. Planifie → exécute en sandbox → review croisé → applique avec garde-fous. Inspiré d'Omnigent mais 100% Botte-native. |
| tags | ["orchestration","pipeline","governance","sandbox","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.
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
| 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 |
# 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 -m skills.meta_harness.cli status <session_id>
# Rollback
python -m skills.meta_harness.cli rollback <session_id>
from skills.meta_harness import MetaHarness, PipelinePlan, Step, Sandbox
# Créer un harness
h = MetaHarness(workdir="/path/to/project")
# Planifier un pipeline
plan = h.plan(["audit", "counter-audit", "fix", "test"])
# Exécuter
session = h.execute(plan, approval=False)
# Voir le rapport
print(session.report())
meta_harness/
├── orchestrator.py — Planification pipeline + dispatch
├── runner.py — Sandbox subprocess + workdir isolé
├── governance.py — Garde-fous, budgets, rollback
├── session.py — Persistance + historique
├── cli.py — argparse CLI
└── test_meta_harness.py
Memory as a learnable skill — store, recall, compress, and consolidate agent memories. Inspired by Stanford AutoMem.
Auto-decide whether a task runs on a LOCAL model or a CLOUD model (DeepSeek, GLM, Nemotron, Grok, Gemma, …) from an automatic effort estimate, and run multi-model fusion (cascade, draft→refine, vote). Use when the user wants automatic local-vs-cloud routing, to add cloud LLM providers, to make local and cloud models collaborate, or mentions effort-based routing, model fusion/ensemble, OpenRouter, DeepSeek, GLM, Nemotron, or Grok.
Fenêtres de contexte pour boucles rétroactives — charge seulement les deltas.
Optimisations DAG/RAG — waves, pruning, memoization, routing.
Generate one self-contained, timestamped HTML dashboard of the system's cost picture — routing savings (control loop), metric trends, current metrics, and the cost of outstanding fixes. Also renders as a live ANSI terminal view (--tui, --watch) and serves a live HTTP API (api.py). Use when the user wants a single visual view of cost/savings/health over time, or a live terminal view they don't have to open a browser for.
Append-only JSONL decision log (.botte/events.jsonl) that every filter in the belt writes to — routing, cache hits, escalations, micro-NN outputs. The single source of truth demo mode, the live dashboard, and session replay all read from. Use when you want to see or emit a live feed of routing/cache/escalation decisions, or when building a tool that needs to watch the belt work in real time.