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 skills add po4yka/llm-wiki-skills --skill llm-wiki-skill-doctorgit clone --depth 1 https://github.com/po4yka/llm-wiki-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/po4yka/llm-wiki-skills/llm-wiki-skill-doctor)<a href="https://agentmods.dev/skills/po4yka/llm-wiki-skills/llm-wiki-skill-doctor"><img src="https://agentmods.dev/badge/skills/po4yka/llm-wiki-skills/llm-wiki-skill-doctor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/po4yka/llm-wiki-skills/llm-wiki-skill-doctor"><img src="https://agentmods.dev/badge/skills/po4yka/llm-wiki-skills/llm-wiki-skill-doctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00057 | $0.00859 |
| Opus 5.5 | $0.00023 | $0.00344 |
| Sonnet 5.5 | $0.00011 | $0.00172 |
| Haiku 4.5 | $0.00006 | $0.00086 |
Grade A, and why
llm-wiki-skill-doctor 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 1mo 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM-Wiki Skill Doctor
Goal
Improve the quality, safety and discoverability of Agent Skills before they are installed or distributed.
When to use
- Before publishing a new or edited
SKILL.mdinskills/to catch frontmatter, trigger-clarity, or smell issues early. - When a skill's description looks vague, overloaded, or likely to collide with another skill's triggers.
- Before granting a skill broader permissions (shell, remote scripts, secrets) to check for supply-chain risk.
- When preparing a batch of skills for distribution and
skills.sh.jsongroupings need a release-readiness check. - When a skill body may contain stale or unverifiable claims that need re-verification against current sources before shipping.
Inputs
- One or more
skills/*/SKILL.mdfiles. - Optional
skills.sh.json. - Agent targets: Claude Code, Codex, Cursor, OpenCode, etc.
- Desired mode: report-only or patch.
Procedure
1. Run deterministic validation
node scripts/audit-skills.mjs <project-root-or-skills-dir>
The bundled script is read-only and accepts a project root, a skills/ directory or a single skill directory. Do not re-derive its checks by hand; re-run it instead. It reports:
- structure: frontmatter validity,
namematching the directory, name pattern, description presence and length bounds; - metadata conventions: license, compatibility, author, version,
install_scope, deprecation contract; - skill smells: overlong body, missing recommended sections, volatile current-state claims without browse instruction, destructive writes without dry-run language;
- trigger collisions: pairwise description-overlap ratios;
- self-containment: repository-root references,
npm runcommands and missing localscripts/,references/orassets/files inself-containedskills; - package metadata: every skill listed in
skills.sh.json, no grouping references a missing skill.
Use --strict to fail on warnings in CI.
2. Judge what the script cannot
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 105 lines · 57 tokens per session scan A 5a96c66ad275
llm-wiki-skill-doctor is a skill published in the GitHub repository po4yka/llm-wiki-skills (4 stars, last pushed 2d ago), licensed MIT. It adds 57 tokens to every session and 859 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
steel-quench
All-angle verification meta-skill for near-complete artifacts. Turns vague design anxiety into structured challenger waves using fh-commons:quench-challenger, then drives defense and convergence until root weaknesses, residual risks, and added complexity are explicit. Covers standard attack/defense rounds, optional…
architecture-review
Surfaces architectural friction in real code — shallow modules, tight coupling, untested seams — and proposes deepening refactors using Ousterhout's deep-module principle (small interface hiding a large implementation). Use when the founder says 'architecture review', 'find shallow modules', 'architectural friction'…
harness-pr-reviewer
Checks a submitted PR against the environment's baseline assets (CLAUDE.md, memory, naming, asset classification) and attaches a review comment with a merge recommendation. 5 steps — diff read, 8-area consistency check, self-catch, comment, merge recommendation.
apex-review
Reviews a technical proposal from the perspective of organizational decision-makers (CTO, technical lead, QA lead, conference reviewers, etc.) and generates an HTML presentation deck. Outputs approval gate results per persona and connects to sim-conductor for improvement suggestions.
mstar-pr-loop
Opt-in skill loaded when the user explicitly asks for a review → fix loop on an existing ready PR, or when iteration Phase 1 selects it as that iteration's prmergepolicy: reviewed-auto review path. It never activates for routine review requests or on its own initiative.
mstar-coding-behavior
Use for non-trivial implementation, debugging, refactoring or code review in any project: requirement drift, speculative complexity, agent-facing interfaces. Not workflow or role selection.