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 OKHP3/skillz --skill markdown-docsgit clone --depth 1 https://github.com/OKHP3/skillzWrote 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/okhp3/skillz/markdown-docs)<a href="https://agentmods.dev/skills/okhp3/skillz/markdown-docs"><img src="https://agentmods.dev/badge/skills/okhp3/skillz/markdown-docs/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/okhp3/skillz/markdown-docs"><img src="https://agentmods.dev/badge/skills/okhp3/skillz/markdown-docs.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 | $0.00089 | $0.01246 |
| Opus 5 | $0.00044 | $0.00623 |
| Sonnet 5 | $0.00018 | $0.00249 |
| Haiku 4.5 | $0.00009 | $0.00125 |
Grade A, and why
markdown-docs 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 6d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Markdown docs
Documentation is read by someone mid-task who is slightly annoyed. They do not read from the top; they scan for the part that matches their situation, take it, and leave. Every structural decision follows from that.
The most common failure is not absence — it is documentation organised around the system's structure instead of the reader's task. A page-per-module reference is easy to generate and answers almost no real question.
1. Identify the reader and their moment
Different moments need different documents, and merging them serves none:
| Moment | They need | Document |
|---|---|---|
| "What is this, should I use it?" | Purpose, fit, constraints | README top section |
| "Get me running" | The shortest working path | Quickstart |
| "Teach me the concepts" | Mental model, why it works this way | Guide |
| "What are the options for X?" | Complete, scannable facts | Reference |
| "It's 3am and it's broken" | Symptom → action, no prose | Runbook |
| "Why is it built this way?" | Context, alternatives, trade-offs | Decision record |
Write one of these at a time. A quickstart that pauses to explain architecture loses the reader who wanted to be running in two minutes.
Done when: you know which document you are writing and who opens it.
2. Front-load ruthlessly
Readers scan the first screen and decide whether to stay.
- First sentence: what it is and what it is for. Not history, not motivation. "A CLI that syncs Postgres tables to BigQuery on a schedule."
- Then: whether it fits them. Requirements, constraints, what it does not do. Saving someone twenty minutes by telling them early that it will not work for them is a service.
- Then: the first working thing. Copy-pasteable, complete, no placeholders they must resolve first.
Done when: the first screen answers "what is it" and "does it apply to me".
3. Make every command actually runnable
The fastest way to lose trust is a command that fails. For each 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.
- 6d ago First seen · 110 lines · 89 tokens per session scan A e0a21dbb1f5e
markdown-docs is a skill published in the GitHub repository OKHP3/skillz (3 stars, last pushed yesterday), licensed MIT. It adds 89 tokens to every session and 1,246 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
vastai-sdk
Vast.ai Python SDK — high-level API for GPU instances, volumes, serverless endpoints, and billing.
pm-aarrr
A post-launch product-growth workflow based on AARRR: acquiring users, activating them, retaining them, earning revenue, and gaining referrals.
pm-docs
A workflow for producing product documents such as PRDs, BRDs, and MRDs. These are structured documents describing what a product needs, its business case, and its market.
product-marketing-copywriter
A marketing-copy tool that analyzes audience problems and product benefits, then creates promotional headlines and body text. Marketing copy is writing intended to explain and promote a product.
pm-position
A guided process for defining a product’s market position, value, audience, competitive difference, business model, pricing, and revenue plan. The instructions are written mainly in Chinese.
pm-retro
A retrospective workflow for reviewing a finished agile iteration, recording what happened, and choosing improvements for the next cycle.