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 klh/speedy-claude --skill md-formatgit clone --depth 1 https://github.com/klh/speedy-claudeWrote 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/klh/speedy-claude/md-format)<a href="https://agentmods.dev/skills/klh/speedy-claude/md-format"><img src="https://agentmods.dev/badge/skills/klh/speedy-claude/md-format/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/klh/speedy-claude/md-format"><img src="https://agentmods.dev/badge/skills/klh/speedy-claude/md-format.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00596 |
| Opus 5 | $0.00028 | $0.00298 |
| Sonnet 5 | $0.00011 | $0.00119 |
| Haiku 4.5 | $0.00006 | $0.00060 |
Grade A, and why
md-format 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 8d 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 — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Markdown Style (GFM-first)
Mechanical formatting is handled automatically: every Write/Edit to a .md file triggers hooks/md-format.sh → prettier --write --prose-wrap preserve. That aligns table pipes, normalizes list markers (- for bullets, 1. ordered), code-fence style, and spacing. You write; the hook tidies.
Manual format (unformatted files, bulk):
prettier --write --prose-wrap preserve "docs/**/*.md"
Judgment calls (prettier can't decide these)
- GFM is the default target: tables, task lists, strikethrough, autolinks, fenced code with language tags. Write for GitHub rendering.
- Tables: only when the data is genuinely tabular (2+ columns, comparable rows). One-liner pairs → a list. Wide tables (5+ cols) often read better as definition lists or headed sections — GitHub doesn't wrap table cells.
- Column width: keep header cells short; long cells in a column mean the table fights the formatter's alignment.
- Code fences: always tag the language in the fence info string (
bash,ts). Untagged blocks lose highlighting. - Headings: one H1 per file, no level skips (H1→H3 is broken anchoring). Headings are the anchor API —
#-Patternlinks depend on exact casing. - Lists:
-bullets; parallel capitalization; no trailing.on fragments,.on full sentences — pick one per list. - Emphasis:
*italic*,**bold**; underscores read as code in some renderers around words. - Line breaks: single newline within a paragraph (GFM renders it as a space — don't rely on hard-wraps); blank line between blocks. Two trailing spaces for intentional
<br>— rare. - Flavor exceptions: Obsidian-targeted notes may use wikilinks/callouts; plain CommonMark when a renderer is unknown. Match the repo's existing flavor before defaulting to GFM.
- Links: reference-style for repeated URLs or >3 links in a paragraph; inline otherwise. Naked URLs fine (GFM autolinks).
Verification
After bulk-formatting or flavor migrations: prettier --check for strays, and render-check tables (column count consistent per row — the formatter will not fix a table with mismatched cells, it will happily align a broken one).
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.
- 8d ago First seen · 32 lines · 57 tokens per session scan A dd2f034df7ea
md-format is a skill published in the GitHub repository klh/speedy-claude (11 stars, last pushed 2d ago), licensed MIT. It adds 57 tokens to every session and 596 once invoked, about $0.0003 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 2026-09-04.
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…