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 skills/emdashcodes/claude-code-plugins/docs-to-skillnpx skills add emdashcodes/claude-code-plugins --skill docs-to-skillgit clone --depth 1 https://github.com/emdashcodes/claude-code-pluginsWhat 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 | $0.00044 | $0.03540 |
| Opus 5 | $0.00022 | $0.01770 |
| Sonnet 5 | $0.00009 | $0.00708 |
| Haiku 4.5 | $0.00004 | $0.00354 |
Grade A, and why
docs-to-skill 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.
How it starts
The opening of the file, as written. The whole thing — 428 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docs to Skill
Ingest a documentation site and generate a ready-to-use Claude Code skill. Point this at any docs URL and it will discover pages, fetch content, and produce a skill with a SKILL.md index and references/ directory.
Overview
This skill orchestrates a multi-phase workflow:
- Gather Info — Get the docs URL, skill name, and output location from the user
- Discovery — Find all documentation pages via sitemap, nav crawl, or manual list
- Fetching — Extract clean markdown from each page using subagents
- Skill Generation — Produce the SKILL.md index with reference map
The bundled Playwright MCP server (headless) gives you a real browser for navigating pages, taking screenshots, and extracting content as clean markdown via Turndown.js injection.
Phase 1: Gather Info
Collect three things from the user:
1. Documentation URL(s)
The root URL of the documentation site. Examples:
https://docs.example.comhttps://example.com/docs/getting-started
If the user provides multiple URLs, treat each as a separate docs section to include.
2. Skill Name
Either provided by the user or derived from the site:
- Use the project/product name in hyphen-case
- Examples:
react-docs,stripe-api,shadcn-ui
3. Output Location
Ask the user where to place the generated skill:
- Personal:
~/.claude/skills/<skill-name>/ - Project:
.claude/skills/<skill-name>/ - Plugin: User specifies
<marketplace>/plugins/<plugin-name>/skills/<skill-name>/
Phase 2: Discovery
Find all documentation pages to fetch. Try strategies in order until one succeeds.
Strategy 1: Sitemap
Use WebFetch to retrieve <domain>/sitemap.xml:
WebFetch url="https://docs.example.com/sitemap.xml" prompt="Extract all URLs from this sitemap XML. Return them as a plain list, one URL per line. Only include URLs that appear to be documentation pages (not blog posts, marketing pages, etc.)."
If the sitemap exists, filter URLs to the docs path prefix. For example, if the user gave https://example.com/docs/, only keep URLs starting with that path.
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 · 428 lines · 44 tokens per session scan A f84faa05970f
docs-to-skill is a skill published in the GitHub repository emdashcodes/claude-code-plugins (13 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 3,540 once invoked, about $0.0002 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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
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…