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 hanyuancheung/llm-skill --skill guidegit clone --depth 1 https://github.com/hanyuancheung/llm-skillWrote 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/hanyuancheung/llm-skill/guide)<a href="https://agentmods.dev/skills/hanyuancheung/llm-skill/guide"><img src="https://agentmods.dev/badge/skills/hanyuancheung/llm-skill/guide.svg" alt="Measured on agentmods" 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 | $0.00001 | $0.00893 |
| Opus 5 | $0.00000 | $0.00447 |
| Sonnet 5 | $0.00000 | $0.00179 |
| Haiku 4.5 | $0.00000 | $0.00089 |
Grade A, and why
guide 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 7d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
guide — Guidance Meta-Skill
What
Maintain the single Schema file AGENT.md so that execute always routes to the right skill with the minimum information possible.
Guide does not create domain knowledge; it organizes and routes.
When to use
- ✅
distillhas just done Create / Merge / Deprecate. - ✅ User asks to "tidy up skills / find merge candidates".
- ✅ Periodic review (e.g. every N completed tasks).
When NOT to use
- ❌ Domain questions themselves (those belong to
execute). - ❌ Internal edits to a single
SKILL.md(those belong todistill).
How (SOP)
1. Scan the skill set
ls skills/*/SKILL.md
Parse only the front-matter of each file (skip the body). Collect:
name, status, triggers, dependencies, updated.
2. Consistency checks (Schema guard)
| Check | Action |
|---|---|
| Missing front-matter field | Mark as malformed, notify distill to fix |
name differs from directory name |
Error, require fix |
triggers fully overlap another skill |
Suggest Merge |
status: experimental for > 2 reuse cycles with no promotion |
Suggest promote or deprecate |
status: deprecated kept for > 1 cycle |
Suggest deletion |
dependencies point to a non-existent skill |
Error |
3. Update AGENT.md
May edit only:
- §2.1 / §2.2 registry (add/remove/modify rows).
- §7 changelog (append a line).
All other sections (loop definition, contract, anti-patterns) are stable; changes require explicit user confirmation.
4. Produce a diff summary
After each guide run, report to user:
Added: skills/xxx (from distill, experimental)
Promoted: skills/yyy experimental → active
Deprecated: skills/zzz (90 days cold)
5. Reverse-notify
If a skill has weak triggers (never matches), reverse-suggest distill to rewrite them.
Examples
After distill creates debug-cuda-oom
- Scan finds a new directory
skills/debug-cuda-oom. - Front-matter is valid.
- Append to
AGENT.md§2.2:| debug-cuda-oom | skills/debug-cuda-oom/SKILL.md | CUDA, OOM, VRAM | experimental | - Append to
AGENT.md§7:- 2026-05-02 — registered debug-cuda-oom (experimental) - Report to user.
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.
- 7d ago First seen · 101 lines · 1 tokens per session scan A ab2e5c3f1c68
guide is a skill published in the GitHub repository hanyuancheung/llm-skill (22 stars, last pushed 4mo ago), licensed MIT. It adds 1 tokens to every session and 893 once invoked, about $0.0000 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…