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 Kastalien-Research/thoughtbox --skill diataxisgit clone --depth 1 https://github.com/Kastalien-Research/thoughtboxWrote 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/kastalien-research/thoughtbox/diataxis)<a href="https://agentmods.dev/skills/kastalien-research/thoughtbox/diataxis"><img src="https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/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 5.1 | $0.00078 | $0.01331 |
| Opus 5 | $0.00039 | $0.00665 |
| Sonnet 5 | $0.00016 | $0.00266 |
| Haiku 4.5 | $0.00008 | $0.00133 |
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 4d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- diataxis — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diátaxis Documentation Framework
Apply the Diátaxis systematic framework to structure and write documentation.
The Four Documentation Types
Diátaxis identifies exactly four types, defined by two axes:
| Acquisition (study) | Application (work) | |
|---|---|---|
| Action (doing) | Tutorial | How-to guide |
| Cognition (thinking) | Explanation | Reference |
1. Tutorials — learning-oriented
Write tutorials as lessons. Take the learner by the hand through a practical experience where they acquire skills by doing.
- Use first-person plural ("We will...")
- Show where they're going up front
- Deliver visible results early and often
- Ruthlessly minimize explanation — link to it instead
- Focus on the concrete, ignore options and alternatives
- Aspire to perfect reliability
Load references/tutorials.md for full guidance.
2. How-to guides — goal-oriented
Write how-to guides as practical directions for an already-competent user to achieve a specific real-world goal.
- Name clearly: "How to [achieve X]"
- Use conditional imperatives ("If you want x, do y")
- Assume competence — don't teach
- Omit the unnecessary; practical usability > completeness
- Allow flexibility with alternatives
Load references/how-to-guides.md for full guidance.
3. Reference — information-oriented
Write reference as technical description of the machinery. Keep it austere, authoritative, consulted not read.
- Describe and only describe — neutral tone
- Adopt standard, consistent patterns
- Mirror the structure of the product
- Provide examples to illustrate, not explain
Load references/reference.md for full guidance.
4. Explanation — understanding-oriented
Write explanation as discursive treatment that deepens understanding. Answer "Can you tell me about...?"
- Make connections to related topics
- Provide context: why things are so
- Talk about the subject (title: "About X")
- Admit opinion and perspective
- Keep closely bounded — don't absorb other types
What ships with it
18 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.
- README.md 752 B
- references/application.md 1.6 KB
- references/colophon.md 1.6 KB
- references/compass.md 2.2 KB
- references/complex-hierarchies.md 3.4 KB
- references/explanation.md 6.8 KB
- references/foundations.md 3.8 KB
- references/how-to-guides.md 3.2 KB
- references/how-to-use-diataxis.md 2.4 KB
- references/index.md 1.9 KB
- references/map.md 2.4 KB
- references/quality.md 9.0 KB
- references/reference-explanation.md 3.4 KB
- references/reference.md 5.2 KB
- references/start-here.md 2.0 KB
- references/theory.md 1.4 KB
- references/tutorials-how-to.md 1.7 KB
- references/tutorials.md 13 KB
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.
- 4d ago First seen · 134 lines · 78 tokens per session scan A 153627195eda
diataxis is a skill published in the GitHub repository Kastalien-Research/thoughtbox (64 stars, last pushed 1mo ago), licensed MIT. It adds 78 tokens to every session and 1,331 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
local-rag-search
Efficiently perform web searches using the mcp-local-rag server with semantic similarity ranking. Use this skill when you need to search the web for current information, research topics across multiple sources, or gather context from the internet without using external APIs. This skill teaches effective use of…
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis with two-column tables. Left column preserves the chapter content; right column maps every idea to the reader's actual life using brain context. Output is a single brain page at media/books/ -personalized plus an optional PDF via brain-pdf.
courses
GetCourse management - users, deals, student creation.
octave-literacy
LLM-native structured communication format. Teaches OCTAVE syntax rules, canonical forms, and warning prevention for zero-error .oct.md authoring.
understand-anything
Deeply explain any code, concept, system, or error in a way that builds genuine understanding. Use when user wants to understand something rather than just fix it.
技能创建助手
A guide for creating Claude skills, which are reusable instruction packages that add specialized knowledge, workflows, tools, or reference files. It includes a process for testing and improving those skills.