Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/raphaelchristi/harness-evolver/deploynpx skills add raphaelchristi/harness-evolver --skill deploygit clone --depth 1 https://github.com/raphaelchristi/harness-evolverWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00030 | $0.00805 |
| Opus 5 | $0.00015 | $0.00402 |
| Sonnet 5 | $0.00006 | $0.00161 |
| Haiku 4.5 | $0.00003 | $0.00081 |
Grade A, and why
harness:deploy scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
86% identical to phone — 146 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/harness:deploy
Finalize the evolution results. In v3, the best code is already in the main branch (auto-merged during evolve). Deploy is about cleanup, tagging, and pushing.
What To Do
TOOLS="${EVOLVER_TOOLS:-$([ -d ".evolver/tools" ] && echo ".evolver/tools" || echo "$HOME/.evolver/tools")}"
EVOLVER_PY="${EVOLVER_PY:-$([ -f "$HOME/.evolver/venv/bin/python" ] && echo "$HOME/.evolver/venv/bin/python" || echo "python3")}"
1. Show Results
python3 -c "
import json
c = json.load(open('.evolver.json'))
baseline = c['history'][0]['score'] if c['history'] else 0
best = c['best_score']
improvement = best - baseline
print(f'Baseline: {baseline:.3f}')
print(f'Best: {best:.3f} (+{improvement:.3f}, {improvement/max(baseline,0.001)*100:.0f}% improvement)')
print(f'Iterations: {c[\"iterations\"]}')
print(f'Experiment: {c[\"best_experiment\"]}')
"
Show git diff from before evolution started:
git log --oneline --since="$(python3 -c "import json; print(json.load(open('.evolver.json'))['created_at'][:10])")" | head -20
2. Ask What To Do (interactive)
{
"questions": [{
"question": "Evolution complete. What would you like to do?",
"header": "Deploy",
"multiSelect": false,
"options": [
{"label": "Tag and push", "description": "Create a git tag with the score and push to remote"},
{"label": "Just review", "description": "Show the full diff of all changes made during evolution"},
{"label": "Clean up only", "description": "Remove temporary files (trace_insights.json, etc.) but don't push"},
{"label": "Promote learnings", "description": "Add proven evolution insights to CLAUDE.md (permanent knowledge)"}
]
}]
}
3. Execute
If "Tag and push":
VERSION=$(python3 -c "import json; c=json.load(open('.evolver.json')); print(f'evolver-v{c[\"iterations\"]}')")
SCORE=$(python3 -c "import json; print(f'{json.load(open(\".evolver.json\"))[\"best_score\"]:.3f}')")
git tag -a "$VERSION" -m "Evolver: score $SCORE"
git push origin main --tags
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 89 lines · 30 tokens per session scan A 48da90a0bd29
harness:deploy is a skill published in the GitHub repository raphaelchristi/harness-evolver (49 stars, last pushed 4mo ago), licensed MIT. It adds 30 tokens to every session and 805 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to phone, differing in 146 lines, and is treated as a copy.
Other skills, from other repositories
nature-statistics
Audit, revise, or draft manuscript statistical reporting for Nature / high-impact journal submissions. Use when the user asks to check statistical analysis sections, p values, confidence intervals, sample size, biological versus technical replicates, randomization, blinding, multiple-comparison correction, model…
baoyu-youtube-transcript
Downloads YouTube video transcripts/subtitles and cover images by URL or video ID. Supports multiple languages, translation, chapters, and speaker identification. Caches raw data for fast re-formatting. Use when user asks to "get YouTube transcript", "download subtitles", "get captions", "YouTube字幕", "YouTube封面"…
comet-verify
Comet Phase 4: Verify and Close. Invoke with /comet-verify. Verify implementation matches design, handle development branch.
comet-design
Comet Classic 阶段 2 —— 为 change 产出深度技术 Design Doc。.
comet-hotfix
Comet preset path: Bug fix / hotfix. Skip brainstorming, directly open → build → verify → archive. Applicable for behavior fixes, scenarios not involving new capability design.
generate-harness-dsl
Generate, revise, or review complete Harness as Code .harness files when a coding-agent workflow, agent role, skill, tool contract, MCP connection, runtime, or deployment must be compiler-valid and resolvable with @qoder-ai/harness.