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/cratis/ai/write-documentationnpx skills add Cratis/AI --skill write-documentationgit clone --depth 1 https://github.com/Cratis/AIWhat 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 | $0.00069 | $0.01472 |
| Opus 5 | $0.00034 | $0.00736 |
| Sonnet 5 | $0.00014 | $0.00294 |
| Haiku 4.5 | $0.00007 | $0.00147 |
Grade A, and why
write-documentation 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 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.
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:
- write-documentation — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diátaxis Documentation Expert
You are an expert technical writer producing documentation for Cratis projects. The site is built with Astro Starlight; you author product .md/.mdx that a converter syncs into it (see the documentation-structure-and-formatting rule for the mechanical conventions). Every page you write is guided by the Diátaxis framework — a systematic approach that classifies documentation into four distinct types, each serving a different user need.
Guiding Principles
- Clarity — Write in simple, clear, unambiguous language.
- Accuracy — Every code example must be complete, correct, and runnable. No pseudo-code.
- User-centricity — Every page helps a specific reader achieve a specific goal. Lead with why, then how.
- Consistency — Match the project's existing tone, terminology, and style. If it's "event source" in one place, it's "event source" everywhere.
The Four Document Types
Before writing, determine which Diátaxis quadrant the page belongs to:
| Type | Orientation | Analogy | When to use |
|---|---|---|---|
| Tutorial | Learning | A lesson | Guide a newcomer step-by-step to a successful first outcome |
| How-to Guide | Problem-solving | A recipe | Show an experienced user how to accomplish a specific task |
| Reference | Information | A dictionary | Describe the technical machinery — APIs, attributes, configuration |
| Explanation | Understanding | A discussion | Clarify why something works the way it does, trade-offs, architecture |
Rules per type
- Tutorial — Never explain why; focus on do this, then this. Each step must produce a visible, verifiable result. The reader should succeed even if they don't fully understand the concepts yet.
- How-to Guide — Assume competence. State the goal, list prerequisites, give the steps, done. No teaching.
- Reference — Be exhaustive and terse. Tables, type signatures, attribute lists. No narrative.
- Explanation — No steps. Discuss concepts, trade-offs, and architecture decisions. Use Mermaid diagrams freely.
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 · 123 lines · 69 tokens per session scan A 29986538efff
write-documentation is a skill published in the GitHub repository Cratis/AI (2 stars, last pushed 4d ago), licensed MIT. It adds 69 tokens to every session and 1,472 once invoked, about $0.0003 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
add-cratis-docs-page
Use this skill when creating a NEW Cratis documentation page under Documentation/ (tutorial, how-to, explanation, reference, or recipe). Handles where the file goes (which product repo), sidebar wiring (toc.yml + Diátaxis bucket), and verifying it renders. Trigger on add/create/write a new docs page, document a new…
write-documentation
Diátaxis classification and authoring guidance for Cratis docs — decide whether a page is a Tutorial, How-to, Reference, or Explanation and draft its content in that style. For WHERE a new page goes + sidebar wiring use add-cratis-docs-page; to change an existing page use edit-cratis-docs.
ship-changes
Ship staged or unstaged local changes: create a branch, make logical commits, push to origin, open a PR with the correct description and label, merge it, close the issues it resolves, and delete the branch locally and on origin. Use whenever the user asks to commit, push, create a PR, ship, or land changes.
add-concept
Use this skill when asked to create a strongly-typed domain identifier or value (such as ProjectId, AuthorName, InvoiceNumber) in a Cratis-based project. Produces a ConceptAs record with the correct conversions and sentinel values.
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
cratis-command
Step-by-step guidance for creating a Cratis Arc command — [Command] record, Handle() method, CommandValidator, proxy generation, and React .use() hook with CommandDialog. Use when adding or creating a command, wiring up a form or button to the backend, working with IEventLog, CommandResult, CommandValidator…