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-validatenpx skills add raphaelchristi/harness-evolver --skill dev-validategit 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 | $0.00044 | $0.01135 |
| Opus 5 | $0.00022 | $0.00567 |
| Sonnet 5 | $0.00009 | $0.00227 |
| Haiku 4.5 | $0.00004 | $0.00113 |
Grade A, and why
dev:validate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dev:validate
Check plugin integrity: skill/agent frontmatter, cross-references, Python tool syntax, version sync, hook script executability.
Checks
1. Version Sync
PKG_V=$(python3 -c "import json; print(json.load(open('package.json'))['version'])")
PLUGIN_V=$(python3 -c "import json; print(json.load(open('.claude-plugin/plugin.json'))['version'])")
if [ "$PKG_V" = "$PLUGIN_V" ]; then
echo "OK: versions match ($PKG_V)"
else
echo "FAIL: package.json=$PKG_V, plugin.json=$PLUGIN_V"
fi
2. Skill Frontmatter
For each skills/*/SKILL.md:
- Must have
name:in frontmatter - Must have
description:in frontmatter - Must have
allowed-tools:in frontmatter
for f in skills/*/SKILL.md; do
NAME=$(grep -m1 "^name:" "$f" | cut -d: -f2- | xargs)
DESC=$(grep -m1 "^description:" "$f")
TOOLS=$(grep -m1 "^allowed-tools:" "$f")
if [ -z "$NAME" ] || [ -z "$DESC" ] || [ -z "$TOOLS" ]; then
echo "FAIL: $f missing frontmatter fields"
else
echo "OK: $f ($NAME)"
fi
done
3. Agent Frontmatter
For each agents/*.md:
- Must have
name:in frontmatter - Must have
description:in frontmatter - Must have
tools:in frontmatter - Must have
color:in frontmatter
for f in agents/*.md; do
NAME=$(grep -m1 "^name:" "$f" | cut -d: -f2- | xargs)
COLOR=$(grep -m1 "^color:" "$f" | cut -d: -f2- | xargs)
if [ -z "$NAME" ] || [ -z "$COLOR" ]; then
echo "FAIL: $f missing name or color"
else
echo "OK: $f ($NAME, $COLOR)"
fi
done
4. Agent Cross-References
Check that every subagent_type: referenced in skills exists as an agent file:
for AGENT in $(grep -roh 'subagent_type: "[^"]*"' skills/ | sed 's/subagent_type: "//;s/"//' | sort -u); do
if [ ! -f "agents/$AGENT.md" ]; then
echo "FAIL: subagent_type '$AGENT' referenced in skills but agents/$AGENT.md not found"
else
echo "OK: $AGENT agent exists"
fi
done
5. Python Tool Syntax
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 · 138 lines · 44 tokens per session scan A b1d5bf384d62
dev:validate is a skill published in the GitHub repository raphaelchristi/harness-evolver (49 stars, last pushed 4mo ago), licensed MIT. It adds 44 tokens to every session and 1,135 once invoked, about $0.0002 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.