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/dev-releasenpx skills add raphaelchristi/harness-evolver --skill dev-releasegit 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 | $0.00058 | $0.01234 |
| Opus 5 | $0.00029 | $0.00617 |
| Sonnet 5 | $0.00012 | $0.00247 |
| Haiku 4.5 | $0.00006 | $0.00123 |
Grade A, and why
dev:release scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dev:release
Interactive release workflow for harness-evolver. Handles everything: validation, changelog, version bump, git tag, GitHub release, npm publish.
Step 1: Determine Version Bump
Parse the argument if provided (patch, minor, major). If not provided, ask:
{
"questions": [
{
"question": "Version bump type?",
"header": "Bump",
"multiSelect": false,
"options": [
{"label": "patch", "description": "Bug fixes, small changes (e.g., 4.0.2 → 4.0.3)"},
{"label": "minor", "description": "New features, backwards compatible (e.g., 4.0.2 → 4.1.0)"},
{"label": "major", "description": "Breaking changes (e.g., 4.0.2 → 5.0.0)"}
]
}
]
}
Step 2: Read Current State
# Current version
CURRENT=$(python3 -c "import json; print(json.load(open('package.json'))['version'])")
echo "Current version: $CURRENT"
# Commits since last tag
LAST_TAG=$(git describe --tags --abbrev=0 2>/dev/null || echo "")
if [ -n "$LAST_TAG" ]; then
echo "Commits since $LAST_TAG:"
git log --oneline "$LAST_TAG"..HEAD
else
echo "No previous tags found"
git log --oneline -10
fi
Step 3: Compute New Version
Based on the bump type and current version, compute the new version. For example:
patch: 4.0.2 → 4.0.3minor: 4.0.2 → 4.1.0major: 4.0.2 → 5.0.0
python3 -c "
v = '$CURRENT'.split('.')
bump = '$BUMP_TYPE'
if bump == 'major':
v = [str(int(v[0])+1), '0', '0']
elif bump == 'minor':
v = [v[0], str(int(v[1])+1), '0']
else:
v = [v[0], v[1], str(int(v[2])+1)]
print('.'.join(v))
"
Step 4: Generate Changelog Entry
Read the commits since the last tag. Categorize them:
feat:→ Addedfix:→ Fixedrefactor:→ Changeddocs:→ (skip unless significant)chore:→ (skip unless version bump)
Write a new ## [NEW_VERSION] - YYYY-MM-DD section at the top of CHANGELOG.md (after the header, before the previous version entry). Follow Keep a Changelog format. Use the commit messages as a starting point but rewrite them to be user-facing — explain what changed for the user, not what files were touched.
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 · 153 lines · 58 tokens per session scan A ac1a1621027c
dev:release is a skill published in the GitHub repository raphaelchristi/harness-evolver (48 stars, last pushed 4mo ago), licensed MIT. It adds 58 tokens to every session and 1,234 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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.