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/monkey1wizard/golem-agents-legion/markdown-formattingnpx skills add monkey1wizard/Golem-Agents-Legion --skill markdown-formattinggit clone --depth 1 https://github.com/monkey1wizard/Golem-Agents-LegionWrote 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/monkey1wizard/golem-agents-legion/markdown-formatting)<a href="https://agentmods.dev/skills/monkey1wizard/golem-agents-legion/markdown-formatting"><img src="https://agentmods.dev/badge/skills/monkey1wizard/golem-agents-legion/markdown-formatting.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 | $0.00029 | $0.00491 |
| Opus 5 | $0.00015 | $0.00246 |
| Sonnet 5 | $0.00006 | $0.00098 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
markdown-formatting 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 yesterday.
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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Markdown Formatting Skill
Write clean, consistent Markdown.
Headings
- Increase heading levels one step at a time
- Use ATX headings:
# Heading - Surround headings with blank lines
- Do not repeat the same heading text in the same document
Lists
- Use
-for unordered lists - Indent nested lists with 2 spaces
- Use a single space after the list marker
- Surround lists with blank lines when they are separate blocks
Code Blocks
- Use fenced code blocks, not indented blocks
- Always specify the language when possible
- Surround code blocks with blank lines
Lines
- No trailing spaces
- No hard tabs
- No multiple consecutive blank lines
- End files with a single newline
Line Wrapping
- One paragraph is one physical line. Never hard-wrap prose inside a paragraph, list item, or table cell
- Long lines are correct;
MD013stays disabled for this reason - Why this rule exists (do not "fix" it back): agent edits are fragment replacements that cannot re-flow a wrapped paragraph, so hard-wrapped prose degrades into ragged widths after a few edits. And an intra-paragraph line break renders as a space, which corrupts CJK prose with visible gaps between characters
- Exceptions: fenced code blocks, text diagrams, frontmatter, and HTML comment blocks keep their own line structure — there the newlines are content
Links and Tables
- Do not use bare URLs in prose; prefer
[text](url) - Use standard table dividers like
| --- |
Punctuation
- In general prose and documentation, do not use CJK fullwidth semicolon punctuation
- Do not pad semicolons with surrounding spaces
- The semicolon rule above does not override Conventional Commit bullets, where semicolons are allowed inside bullet lines
Recommended .markdownlint.json
{
"MD013": false,
"MD033": false,
"MD041": false
}
Output Requirements
When editing Markdown:
- Preserve structure
- Normalize formatting to these rules
- Do not introduce style churn unrelated to the requested change
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.
- yesterday First seen · 72 lines · 29 tokens per session scan A f55517b6e43e
markdown-formatting is a skill published in the GitHub repository monkey1wizard/Golem-Agents-Legion (15 stars, last pushed 4d ago), licensed MIT. It adds 29 tokens to every session and 491 once invoked, about $0.0001 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…