harness-evolve — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited harness-evolve (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Surfaces the upstream metaharness-darwin evolve CLI as a ruflo skill. The write layer that pairs with ADR-150's read layer (score / genome / mcp-scan / threat-model / oia-audit). Use when you have a harness whose readiness scores are flat and you want to discover which surface mutation moves them — without retraining the foundation model.
harness-score result is below target and you don't know which policysurface is responsible.
starting configuration empirically rather than hand-tuning.
(treat darwin's champion as the strawman).
Wire it into CI for one-shot exploration, not for autonomous self-modification.
— the CI gate verifies graceful degradation, not convergence.
Implementation: scripts/evolve.mjs.
--repo exists, caps on --generations ≤ 50, --children≤ 20, --concurrency ≤ 8, sandbox/selection/mutator are known values).
--confirm: print plan + exit 0 (mirrors harness-mint safetyconvention; defense in depth over the upstream safety.ts checks).
--confirm: shell to npx -y @metaharness/darwin@~0.3.1 metaharness-darwin evolve <repo> ...via the shared _darwin.mjs async helper. Per-generation progress is forwarded to stderr; final champion JSON is captured from stdout.
generations × children × per-variant (per-variant≈ 60s real, ≈ 2s mock). Caller may override with --timeout-ms.
remap. This is a designed-in tripwire (a variant tripped inspectVariant for secrets / shell-out / network / dynamic-eval). See ADR-153 §"Safety model".
--alert-on-no-improvement: exit 1 when champion ≤ parent.| Surface | What it owns |
|---|---|
planner | task decomposition / step ordering |
contextBuilder | what gets fed into the prompt |
reviewer | self-critique / output verification |
retryPolicy | when + how to retry on failure |
toolPolicy | which tools the agent may use, under which conditions |
memoryPolicy | what to persist, recall, forget |
scorePolicy | how the agent grades its own output |
One mutation per variant. Multi-surface mutations are not allowed (causal attribution stays clean).
Reports land under <repo>/.metaharness/:
.metaharness/
archive.json # full lineage tree (sampling next gen draws from this)
lineage.json # parent→child edges only
variants/<id>/ # per-variant code (kept for audit)
runs/<id>/ # per-variant sandbox test output
reports/winner.json # final champion + score delta vs parentSkill stdout = JSON {success, data: {champion, plan, durationMs, improved}}.
| Code | Meaning |
|---|---|
| 0 | Evolved OK, or dry-run, or degraded (Darwin absent) |
| 1 | --alert-on-no-improvement and champion did not beat parent |
| 2 | Config error or evolution infrastructure failure |
| 99 | Upstream "safety-disqualified" (PROPAGATED, not remapped) |
When @metaharness/darwin is not installed, the script emits {degraded: true, reason: 'metaharness-darwin-not-available', hint: ...} and exits 0. ruflo continues to function. CI's no-metaharness-smoke.yml-style job asserts this path.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.