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/zircote-plugins/documentation-review/diataxisnpx skills add zircote-plugins/documentation-review --skill diataxisgit clone --depth 1 https://github.com/zircote-plugins/documentation-reviewWrote 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/zircote-plugins/documentation-review/diataxis)<a href="https://agentmods.dev/skills/zircote-plugins/documentation-review/diataxis"><img src="https://agentmods.dev/badge/skills/zircote-plugins/documentation-review/diataxis.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 | $0.00212 | $0.03994 |
| Opus 5 | $0.00106 | $0.01997 |
| Sonnet 5 | $0.00042 | $0.00799 |
| Haiku 4.5 | $0.00021 | $0.00399 |
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 3d 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 — 478 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diátaxis Documentation Framework
Most documentation problems stem from mixing different types of content in ways that serve nobody well. A tutorial that drifts into reference material loses beginners; a reference page with step-by-step instructions frustrates experts looking up specifics. Diátaxis solves this by identifying four distinct documentation modes, each serving a different user need at a different moment. Keeping these modes separate and well-executed is the foundation of documentation that actually works.
The Diátaxis Compass
Two fundamental axes classify all documentation:
| Acquisition (study/learning) | Application (work/doing) | |
|---|---|---|
| Action | Tutorial | How-to Guide |
| Cognition | Explanation | Reference |
Diagnostic questions:
- Does this content involve practical steps (action) or theoretical knowledge (cognition)?
- Is the user learning something new (acquisition) or applying existing skill (application)?
The answers place content in exactly one quadrant.
The Four Documentation Modes
1. Tutorials (Learning-oriented)
Purpose: Guide a learner through a series of steps to acquire skills and understanding.
Defining characteristics:
- The teacher takes full responsibility for the learner's success
- Learning happens through doing, not through explanation
- The learner follows a carefully designed path to a meaningful result
Effective tutorials: (A learner in acquisition mode needs confidence and momentum — these principles protect that.)
- Show the destination upfront — what the learner will accomplish
- Deliver visible results at every step — each action produces comprehensible output
- Maintain narrative expectations — "You will notice that...", "The output should look like..."
- Point out observable details — direct the learner's attention to important cues
- Target the "feeling of doing" — help learners discover rhythm and satisfaction
- Encourage repetition — design steps that reward being repeated
- Aspire to perfect reliability — learners must get the promised results every time
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.
- 3d ago First seen · 478 lines · 212 tokens per session scan A c676498903bd
diataxis is a skill published in the GitHub repository zircote-plugins/documentation-review (5 stars, last pushed 2mo ago), licensed MIT. It adds 212 tokens to every session and 3,994 once invoked, about $0.0011 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
documentation-writer
Write clear, scannable documentation using a research-first, phase-separated workflow. Covers READMEs, doc sites, API references, migration guides, and technical markdown. Uses web search for up-to-date facts and delegates broad repo reads to an explore subagent before drafting. Use when the user asks for…
technical-documentation
AI-powered technical documentation creation, maintenance, and auditing across README, ADR, API docs, runbooks, onboarding guides, changelogs, knowledge bases, and AI agent context files (AGENTS.md/CLAUDE.md). Primary keywords: technical documentation writing automation, ADR architecture decision record, API docs…
API Documentation Generator
AI-powered API documentation generation tool that auto-generates comprehensive API docs from source code, including OpenAPI/Swagger specs, Postman collections, and markdown documentation with examples and authentication details.
documentation-standards
Use when writing README files, API documentation, user guides, or technical documentation following industry standards from Google, Microsoft, and GitLab style guides.
decided-capture
Capture a NEW decision or requirement from a conversation (an interview) into ONE valid RAC (requirements-as-code) artifact — you interview and propose, the human ratifies, decided validate closes, and promotion into the trusted corpus is by pull request reviewed by someone other than the author. Use when a user wants…
decided-import
Reformat ONE existing document (a decision, requirement, design, roadmap, or prompt) into ONE valid RAC (requirements-as-code) artifact, with a mandatory human-review step before any file is written and decided validate as the deterministic close. Use when a user wants to add or import a single existing decision or…