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 edloidas/skills --skill markdown-writinggit clone --depth 1 https://github.com/edloidas/skillsWrote 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/edloidas/skills/markdown-writing)<a href="https://agentmods.dev/skills/edloidas/skills/markdown-writing"><img src="https://agentmods.dev/badge/skills/edloidas/skills/markdown-writing/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/edloidas/skills/markdown-writing"><img src="https://agentmods.dev/badge/skills/edloidas/skills/markdown-writing.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 | $0.00067 | $0.01896 |
| Opus 5.5 | $0.00027 | $0.00758 |
| Sonnet 5.5 | $0.00013 | $0.00379 |
| Haiku 4.5 | $0.00007 | $0.00190 |
Grade A, and why
markdown-writing 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 today.
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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Markdown Writing
Two things decide whether Markdown is good: where it renders (which syntax you may use) and how it reads (whether anyone finishes it). Handle them in that order.
This skill writes and edits Markdown files in the working tree, and nothing else — no commits. Edit an existing document with targeted edits to the passages you are changing; never rewrite the whole file. A whole-file rewrite restyles wrap width, emphasis, and heading case that nobody asked to change, and buries the real edit in the diff.
1. Check the render target first
| Renders where | What you may use |
|---|---|
| GitHub only — issues, PRs, comments, discussions, wiki, repo file views | Everything, including alerts, <details>, task lists, footnotes, mermaid, theme-aware images |
| README that also ships to npm, PyPI, a docs site, or an editor preview | CommonMark + tables + <details>. GitHub extras are degradable, not free: every alert body must read correctly with its [!IMPORTANT] line showing as literal text |
Terminal, --help output, plain-text logs |
No Markdown. Write plain text |
Full syntax and per-host support: references/github-features.md.
2. GitHub alerts
Five types, exact spelling, uppercase, nothing on the label line — the syntax block is in
references/github-features.md.
Picking one:
- NOTE — a true fact that a skimmer would otherwise miss. No stakes.
- TIP — an optional shortcut. Deleting it costs nothing.
- IMPORTANT — they will fail without this. Version floors, required config.
- WARNING — doing it wrong has consequences. Deprecations, data loss, footguns.
- CAUTION — the consequence of an action they are about to take.
Rules that keep them working:
- Rare. Two or three per document. When everything is highlighted, nothing is.
- Not a section. An alert is one to four lines. Longer means it is a section with a heading.
- Not a wrapper for the obvious. If the plain sentence would have been read anyway, leave it plain.
- One at a time. Two alerts in a row read as noise.
What ships with it
3 files 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.
- today Changed · -21 lines c9c0b85bf518
- 1mo ago Changed · +24 lines f14934932df5
- 2mo ago First seen · 169 lines · 67 tokens per session scan A 4117fb59b671
markdown-writing is a skill published in the GitHub repository edloidas/skills (2 stars, last pushed today), licensed MIT. It adds 67 tokens to every session and 1,896 once invoked, about $0.0003 per session on Opus 5.5. 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
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
agent-swarm-pr
Agent skill for swarm-pr - invoke with $agent-swarm-pr.
agent-pr-manager
Agent skill for pr-manager - invoke with $agent-pr-manager.
github-automation
GitHub workflow automation, PR management, issue tracking, and code review coordination. Integrates with GitHub Actions and repository management. Use when: PR creation, code review, issue management, release automation, workflow setup. Skip when: local-only changes, non-GitHub repositories.
babysit
Watch an open PR — fix failing CI, handle the straightforward review comments, and drive it to a mergeable state. Claude Code analog of Cursor's built-in /babysit. Use after opening a PR when the user wants the agent to shepherd it without re-prompting.
make-pr-easy-to-review
Prepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior. Use for "make this easy to review", "tidy this PR", "clean up commits", or "annotate the diff".