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-recommendgit 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 | $0.00019 | $0.00311 |
| Opus 5 | $0.00010 | $0.00156 |
| Sonnet 5 | $0.00004 | $0.00062 |
| Haiku 4.5 | $0.00002 | $0.00031 |
Grade A, and why
skill-recommend scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Recommend skills for this project
Run the project-aware recommendation engine:
python "$HOME/.claude/skills/skills-curator/scripts/registry.py" --recommend
If $ARGUMENTS contains "refresh", pass --refresh to force a fresh catalog fetch.
How to present the result
Don't just dump the output. Walk the user through it:
- Lead with the strongest match — highest score, highest trust tier
- Explain why it matched — which project tags triggered it, in plain English ("you're doing scraping, this is for scraping")
- Group by type — Capability skills (new abilities) before Preference skills (better defaults)
- Flag trust — 🏛️ Official, ✅ High, 🟡 Medium
- Offer the next step — "Want me to evaluate this against your project goals?" → triggers
/skill-evaluate
Why this differs from npx skills or skills.sh
The skills.sh leaderboard ranks by install counts. This ranks by fit. A skill with 50k installs is a worse match than a skill with 200 installs if those 200 installs were on projects exactly like yours.
Trust tier + tag overlap is the signal we use. If you want raw popularity, --discover is the catalog browser.
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 · 31 lines · 19 tokens per session scan A 9fc40905d730
skill-recommend is a command published in the GitHub repository captkernel/Skills_Curator (2 stars, last pushed 9d ago), licensed MIT. It adds 19 tokens to every session and 311 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
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.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.