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 FrancyJGLisboa/cliskill --skill cliskillgit clone --depth 1 https://github.com/FrancyJGLisboa/cliskillWrote 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/francyjglisboa/cliskill/cliskill)<a href="https://agentmods.dev/skills/francyjglisboa/cliskill/cliskill"><img src="https://agentmods.dev/badge/skills/francyjglisboa/cliskill/cliskill/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/francyjglisboa/cliskill/cliskill"><img src="https://agentmods.dev/badge/skills/francyjglisboa/cliskill/cliskill.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 | $0.00183 | $0.14591 |
| Opus 5 | $0.00092 | $0.07295 |
| Sonnet 5 | $0.00037 | $0.02918 |
| Haiku 4.5 | $0.00018 | $0.01459 |
Grade A, and why
cliskill 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 10d 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 — 1,329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cliskill — AI-Agent-Friendly CLI Skill Framework
Point at any reference material. Get a self-installing CLI tool that agents know how to wield.
cliskill is a closed-loop pipeline that transforms any reference material — API docs, repositories, PDFs, course materials, pasted text — into self-bootstrapping CLI skills that work on any OS and any agent tool. The produced skills are git repos: users clone and run, agents read the SKILL.md and wield. It delegates specification to /clarity, implementation to /agent-skill-creator, and adds what neither has: an automated evaluation-fix-rebuild loop and self-bootstrapping packaging.
The human provides references and reviews twice. Everything else is autonomous.
Trigger
/cliskill <reference-1> [<reference-2> ...]
/cliskill resume
/cliskill update <existing-skill-path> <new-reference-1> [<new-reference-2> ...]
/cliskill discover <capability-ref-1> [<capability-ref-2> ...] -- <knowledge-ref-1> [<knowledge-ref-2> ...]
/cliskill research <capability-ref-1> [<capability-ref-2> ...] -- <knowledge-ref-1> [<knowledge-ref-2> ...]
/cliskill self-improve
References can be: API documentation, repository URLs, file paths, PDFs, URLs, or free-text descriptions — anything /clarity can ingest.
Examples:
/cliskill https://api.example.com/docs https://github.com/example/weather-api
/cliskill ./specs/finnhub-api-reference.pdf
/cliskill resume
/cliskill update ./weather-api-skill https://api.example.com/docs/v2
/cliskill discover https://github.com/john/portfolio-repo -- ./course-materials/quantitative-finance.pdf
/cliskill discover ./my-data-pipeline -- ./analytics-textbook.pdf "focus on risk analytics"
/cliskill research ./my-ml-pipeline -- ./methodology-paper.pdf "optimize RMSE for yield prediction"
Natural language works too. Users don't need to know the subcommands. cliskill infers the right mode from intent:
/cliskill ./my-repo ./finance-textbook.pdf "what analytics can I build?" → detects DISCOVER
/cliskill ./my-pipeline ./methods-paper.pdf "make predictions better" → detects RESEARCH
/cliskill https://api.stripe.com/docs "wrap this API" → detects STANDARD
See "Phase Detection — Step 2: Intent Inference" for classification rules. When the mode is ambiguous, cliskill confirms before proceeding.
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.
- 10d ago First seen · 1,329 lines · 183 tokens per session scan A 44745685cb12
cliskill is a skill published in the GitHub repository FrancyJGLisboa/cliskill (5 stars, last pushed 4mo ago), licensed MIT. It adds 183 tokens to every session and 14,591 once invoked, about $0.0009 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 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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…