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 joaquimscosta/arkhe-claude-plugins --skill diataxisgit clone --depth 1 https://github.com/joaquimscosta/arkhe-claude-pluginsWrote 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/joaquimscosta/arkhe-claude-plugins/diataxis)<a href="https://agentmods.dev/skills/joaquimscosta/arkhe-claude-plugins/diataxis"><img src="https://agentmods.dev/badge/skills/joaquimscosta/arkhe-claude-plugins/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/joaquimscosta/arkhe-claude-plugins/diataxis"><img src="https://agentmods.dev/badge/skills/joaquimscosta/arkhe-claude-plugins/diataxis.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 | $0.00083 | $0.00958 |
| Opus 5.5 | $0.00033 | $0.00383 |
| Sonnet 5.5 | $0.00017 | $0.00192 |
| Haiku 4.5 | $0.00008 | $0.00096 |
Grade B, and why
diataxis scanned grade B with 2 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 yesterday.
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.
Downloads and executes remote codemediumSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
| `uv` not found | `curl -LsSf https://astral.sh/uv/install.sh \| sh` or run with `python3 scripts/diataxis_classify.py` | Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| `uv` not found | `curl -LsSf https://astral.sh/uv/install.sh \| sh` or run with `python3 scripts/diataxis_classify.py` | How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diataxis Documentation Framework
Audit, classify, validate, and scaffold documentation using the Diataxis framework.
Quick Start
# Classify individual files
uv run scripts/diataxis_classify.py docs/*.md
# Audit a docs directory for coverage
uv run scripts/diataxis_audit.py --dir docs
# Validate quadrant purity
uv run scripts/diataxis_validate.py --dir docs
# Scaffold a new Diataxis structure
uv run scripts/diataxis_scaffold.py --dry-run
uv run scripts/diataxis_scaffold.py
Capabilities
| Script | Purpose | Key Flags |
|---|---|---|
diataxis_classify.py |
Classify files into quadrants | --json, --verbose, --no-content |
diataxis_audit.py |
Coverage report with quality score | --dir, --json, --min-coverage |
diataxis_validate.py |
Lint for quadrant purity (DX001-DX010) | --dir, --file, --strict, --json |
diataxis_scaffold.py |
Generate folder structure | --layout folders|flat, --init-config, --dry-run |
The Four Quadrants
| Quadrant | Orientation | User State | Folder |
|---|---|---|---|
| Tutorial | Learning | Study + Action | tutorials/ |
| How-to | Task | Work + Action | how-to/ |
| Reference | Information | Work + Cognition | reference/ |
| Explanation | Understanding | Study + Cognition | explanation/ |
Classification Algorithm
Multi-signal weighted scoring (title 30%, headings 25%, content 25%, structure 20%). Documents scoring highly for 2+ quadrants are flagged as "collapsed" with split suggestions.
Validation Rules
| ID | Rule | Severity |
|---|---|---|
| DX001 | Tutorial contains reference tables | warning |
| DX002 | How-to has long conceptual preamble | warning |
| DX003 | Reference contains step-by-step instructions | warning |
| DX004 | Explanation contains execution commands | warning |
| DX005 | No clear quadrant signal | info |
| DX006 | Collapsed document (mixed quadrants) | warning |
| DX007 | Tutorial missing prerequisites | info |
| DX008 | Tutorial missing learning objectives | info |
| DX009 | How-to missing problem statement | info |
| DX010 | Reference missing tables | info |
What ships with it
8 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.
- yesterday First seen · 101 lines · 83 tokens per session scan B 1128ebdda2d0
diataxis is a skill published in the GitHub repository joaquimscosta/arkhe-claude-plugins (21 stars, last pushed yesterday), licensed MIT. It adds 83 tokens to every session and 958 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-16.
Other skills, from other repositories
explain
Explain something in depth on request. Use when the user writes "???" - alone, or placed directly after a reference, statement, or term - which means "explain that in more detail, with a concrete example AND consequences". Also invoked by the /credo:explain command. Treat the pointed-at subject as the thing to…
recipe-schema-explore
Discover and introspect any Google Workspace API before using it — explore methods, parameters, and types.
recipe-create-classroom-course
Create a Google Classroom course and invite students.
developer-growth-analysis
Analyzes your recent Claude Code chat history to identify coding patterns, development gaps, and areas for improvement, curates relevant learning resources from HackerNews, and automatically sends a personalized growth report to your Slack DMs.
onboarding-pm
Utiliser à chaque arrivée d'un nouveau Product Manager dans l'équipe pour produire un parcours d'onboarding sur mesure. Produit les questions clés à poser à la base, les décisions structurantes récentes, les zones de tension, les rencontres prioritaires et un projet introductif.
web-basics
HTML, CSS, and how browsers work. Activated when Claude creates or edits .html or .css files. Provides teaching context for CodeSensei to explain web fundamentals.