doc-diataxis

doc-diataxis is a command for coding agents from zircote-plugins/documentation-review. It costs 22 tokens per session (1,060 once invoked), scanned A, original, MIT.

A documentation review command based on Diátaxis, a framework that separates docs into tutorials, how-to guides, reference, and explanations.

In plain words
What is it for?
It can classify docs, review them against Diátaxis criteria, find gaps by feature or component, or run all three checks as one audit.
Why use it?
It helps find documents in the wrong category, quality problems, and missing documentation. This gives teams a consistent way to check whether their docs support learning and day-to-day work.

Command

Part of the documentation-review plugin — 4 skills, 6 commands, 2 agents shipped together

Install

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.

agentmods
npx agentmods add commands/zircote-plugins/documentation-review/doc-diataxis
Clone the repo
git clone --depth 1 https://github.com/zircote-plugins/documentation-review

Or install documentation-review, the plugin that ships this one along with the rest of its 4 skills, 6 commands, 2 agents.

Wrote 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.

agentmods badge for doc-diataxis

README.md
[![agentmods](https://agentmods.dev/badge/commands/zircote-plugins/documentation-review/doc-diataxis.svg)](https://agentmods.dev/commands/zircote-plugins/documentation-review/doc-diataxis)
Your own site
<a href="https://agentmods.dev/commands/zircote-plugins/documentation-review/doc-diataxis"><img src="https://agentmods.dev/badge/commands/zircote-plugins/documentation-review/doc-diataxis.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,060 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00022 $0.01060
Opus 5 $0.00011 $0.00530
Sonnet 5 $0.00004 $0.00212
Haiku 4.5 $0.00002 $0.00106

Measured 3d ago against content hash ad7aa054031f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

doc-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.

commands/doc-diataxis.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analyze documentation against the Diátaxis framework.

Operation Mode

$IF($1, Mode: $1 $IF($2, Scope: @$2, Scope: all configured documentation paths), Ask the user which operation to perform:

  • classify — Classify documents into Diátaxis quadrants (tutorial, how-to, reference, explanation)
  • review — Review documents for Diátaxis quality criteria and mode purity
  • gaps — Identify missing documentation across Diátaxis quadrants per feature/component
  • audit — Full audit: classify + review + gaps in one pass )

Configuration Check

Use Glob tool to check if .claude/documentation-review.local.md exists.

If configuration exists, read it with Read tool and check for diataxis: section. Use the following defaults if not configured:

  • strictness: standard
  • require_frontmatter: true
  • doc_paths: from top-level plugin config, or require user to specify

Operations

Classify

For each documentation file in scope:

  1. Read the file content
  2. Check for diataxis_type in frontmatter
  3. If no frontmatter, apply the Diátaxis compass:
    • Is the content action-oriented or cognition-oriented?
    • Is it acquisition (learning) or application (working)?
  4. Assign the quadrant with confidence level (High/Medium/Low)
  5. Detect mode mixing — sections where the document shifts quadrant
  6. Report classification with recommendations

Review

For each documentation file in scope:

  1. Classify the document (if not already classified)
  2. Apply the quadrant-specific quality criteria from the diataxis skill:
    • Tutorial: mode purity, learning path, reliability, tone, cross-references
    • How-to: mode purity, goal clarity, practical focus, sequencing, cross-references
    • Reference: mode purity, accuracy/completeness, structure, tone, cross-references
    • Explanation: mode purity, depth/context, connections, scope discipline, cross-references
  3. Score each criterion using the weighted rubric
  4. Calculate aggregate Diátaxis score
  5. Flag mode mixing issues with specific locations

Read the full file on GitHub · 131 lines

Changes

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.

  1. 3d ago First seen · 131 lines · 22 tokens per session scan A ad7aa054031f

Subscribe to this mod's changes

doc-diataxis is a command published in the GitHub repository zircote-plugins/documentation-review (5 stars, last pushed 2mo ago), licensed MIT. It adds 22 tokens to every session and 1,060 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 2026-08-31.

Related

Other commands, from other repositories

capture-answer

Ingests an expert's answers to an L2 questionnaire in the abapwiki knowledge base: transforms the answers (filled in the interviews/ file or given verbally) into a canonical citable expert-answer (slices/ /inputs/expert-answers/), moves gaps to 'answered' and closes the questions. Use this skill when the owner/expert…

Gixsy95/abap_wiki · 85 tokens

ingest-l1

L1 analysis loop for the abapwiki knowledge base: for each batch it launches the abap-analyzer sub-agent in parallel, then the adversarial judge abap-deepcheck (separate session), applies only the analyses that pass the fail-closed gate, and commits. Resumes exactly after an interruption. Use this skill to document…

Gixsy95/abap_wiki · 86 tokens

research-l2

Executes Phases 1-3 of the L2 process of the abapwiki knowledge base on a slice: launches the abap-functional-researcher sub-agent (gap discovery + multi-source auto-research: wiki -> raw/docs -> MCP abap-fs on the system read-only -> standard knowledge), ingests gaps and evidence, and generates questionnaires for…

Gixsy95/abap_wiki · 111 tokens

slice-init

Creates an L2 slice in the abapwiki knowledge base: a business process on which to build functional documentation. Writes the manifest (curated anchors + mandatory real owner) and derives the membership from the dependency graph (BFS hop<=2). Use this skill to start the L2 process on a custom domain. Does not promote…

Gixsy95/abap_wiki · 83 tokens

ingest-l0

L0 bootstrap of the abapwiki knowledge base: creates stubs for all custom objects from the TADIR. Use this skill to initialize the repo from scratch or to ingest a new TADIR export. Deterministic operations (no LLM sub-agent), idempotent.

Gixsy95/abap_wiki · 59 tokens

lint-audit

Checks the integrity of the abapwiki knowledge base: parseable YAML frontmatter, no broken wikilinks, resolvable [VERIFIED: path:N-M] citations, non-nested confidence tags, drift between wiki and DB, synchronization between canonical agent contracts and the .claude/agents/ copies. Use this skill periodically or after…

Gixsy95/abap_wiki · 74 tokens