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 rlespinasse/agent-skills --skill diataxisgit clone --depth 1 https://github.com/rlespinasse/agent-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/rlespinasse/agent-skills/diataxis)<a href="https://agentmods.dev/skills/rlespinasse/agent-skills/diataxis"><img src="https://agentmods.dev/badge/skills/rlespinasse/agent-skills/diataxis/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/rlespinasse/agent-skills/diataxis"><img src="https://agentmods.dev/badge/skills/rlespinasse/agent-skills/diataxis.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 | $0.00075 | $0.03292 |
| Opus 5 | $0.00037 | $0.01646 |
| Sonnet 5 | $0.00015 | $0.00658 |
| Haiku 4.5 | $0.00007 | $0.00329 |
Grade A, and why
diataxis 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 11d 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 — 384 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintain Documentation with the Diataxis Method
You are helping the user organize and maintain their project documentation following the Diataxis framework.
What is Diataxis?
Diataxis (from Ancient Greek: dia — "across", taxis — "arrangement") is a systematic approach to technical documentation that organizes content into four categories based on user needs. See diataxis.fr for the full framework.
| Category | Orientation | Purpose | Form |
|---|---|---|---|
| Tutorials | Learning-oriented | Guide a beginner through learning | A lesson |
| How-to guides | Task-oriented | Help accomplish a specific goal | A series of steps |
| Explanation | Understanding-oriented | Deepen understanding through discussion | A discursive essay |
| Reference | Information-oriented | Provide precise technical descriptions | Dry, accurate facts |
The Compass — Two Axes for Classification
Use two questions to classify any content (see references/compass.md):
| Acquisition (study) | Application (work) | |
|---|---|---|
| Action (practical) | Tutorial | How-to guide |
| Cognition (theoretical) | Explanation | Reference |
- "Is this about action or cognition?" — Does the reader do something or understand something?
- "Is this about acquisition or application?" — Is the reader studying or working?
Key Distinctions
- Tutorials vs How-to guides: Tutorials teach ("follow me") for learners; how-to guides direct ("do this") for practitioners. Tutorials are complete end-to-end; how-to guides start and end at reasonable points the reader joins to their own work.
- Explanation vs Reference: Explanation discusses why (discursive, admits opinion); reference states what (austere, authoritative, no ambiguity).
- Action vs Cognition: Tutorials and how-to guides are practical (doing). Explanation and reference are theoretical (knowing).
- Acquisition vs Application: Tutorials and explanation serve learning/studying. How-to guides and reference serve working/coding.
What ships with it
7 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.
- 11d ago First seen · 384 lines · 75 tokens per session scan A 4fcd56afd752
diataxis is a skill published in the GitHub repository rlespinasse/agent-skills (10 stars, last pushed 4d ago), licensed MIT. It adds 75 tokens to every session and 3,292 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 2026-08-31.
Other skills, from other repositories
fastapi_stripe
A Stripe Checkout implementation takes four steps.
standalone-python-scripts
Skill "standalone-python-scripts" from iloveitaly/llm-ide-rules, covering standalone python scripts, /// script, requires-python = ">=3.13", dependencies = [] and ///.
secrets
Here's how environment variables are managed in this application.
fix-tests
Focus on all unit + command tests (pytest --exclude tests/integration). Make sure they pass and fix errors. If you run into anything very odd: stop, and let me know. Mutate test code first and let me know if you think you should update application code.
plan-only
As this point, I only want to talk about the plan. How would you do this? What would you refactor to make this design clean? You are an expert software engineer and I want you to think hard about how to plan this project out.
dev-in-browser
Use your browser to view https://verso.localhost which is tied to livereload dev server which is already running. You can inspect that page (including taking screenshots!) to validate that your changes fixed the issue.