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 commands/captkernel/skills_curator/skill-auditgit clone --depth 1 https://github.com/captkernel/Skills_CuratorWhat 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 | $0.00025 | $0.00316 |
| Opus 5 | $0.00013 | $0.00158 |
| Sonnet 5 | $0.00005 | $0.00063 |
| Haiku 4.5 | $0.00003 | $0.00032 |
Grade A, and why
skill-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Audit my skill stack
Run the four-part stack review:
python "$HOME/.claude/skills/skills-curator/scripts/registry.py" --audit
python "$HOME/.claude/skills/skills-curator/scripts/registry.py" --health
python "$HOME/.claude/skills/skills-curator/scripts/registry.py" --stale
The three together give the complete picture: what's broken, what's risky, what's outdated.
How to present the result
Don't dump three reports back-to-back. Synthesise:
- Triage — what should the user fix first? Lead with critical findings:
- Preference conflicts (Claude getting contradictory instructions)
- Security-unreviewed community skills
- Stale versions of skills with known security history
- Group the rest — duplicates, low health scores, unevaluated skills — as a punch list with the exact command to fix each
- End with one ask — "Want me to evaluate the unreviewed ones now?"
Why this matters
A skill stack rots. New skills overlap with old ones. Community skills go un-reviewed. Versions drift. Most users never look. This command makes the rot visible in 10 seconds.
Run /skill-audit after you install anything new, or weekly if you can remember.
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 · 34 lines · 25 tokens per session scan A 9d5a28227da3
skill-audit is a command published in the GitHub repository captkernel/Skills_Curator (2 stars, last pushed 9d ago), licensed MIT. It adds 25 tokens to every session and 316 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.