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/qa-cratis-docsnpx skills add Cratis/AI --skill qa-cratis-docsgit 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 | $0.00096 | $0.00871 |
| Opus 5 | $0.00048 | $0.00436 |
| Sonnet 5 | $0.00019 | $0.00174 |
| Haiku 4.5 | $0.00010 | $0.00087 |
Grade A, and why
qa-cratis-docs 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 2d 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:
- qa-cratis-docs — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual & layout QA for the docs site
Scope this skill to visual checks for product or contributing docs whose source lives under
Documentation/**. Site-level pages inDocumentation/webare owned by the Documentation repo.
shot-scraper/Playwright aren't dependencies, but Chrome is. Use the committed Documentation/web/scripts/screenshot.mjs (drives system Chrome over CDP) — it captures light or dark, full-page, with client-side rendering settled.
Capture
cd Documentation/web && npm run dev # serve at http://localhost:4321 (keep it running)
node scripts/screenshot.mjs http://localhost:4321/chronicle/concepts/event-source/ /tmp/es-dark.png dark
node scripts/screenshot.mjs http://localhost:4321/chronicle/concepts/event-source/ /tmp/es-light.png light
Then Read the PNG to evaluate it. Crop/zoom with the sharp already in node_modules (PIL/ImageMagick aren't installed):
node -e "require('sharp')('/tmp/es-dark.png').extract({left:300,top:600,width:900,height:500}).resize({width:1400}).toFile('/tmp/crop.png')"
Build the page list from web/src/generated/topics.json + the site-level slugs. The bar is aspire.dev — study its frontend site.css/mermaid.css for the depth cues (gradient glows, framed diagrams, lifted cards) that cratis.css is built from.
What to check on each page
- Diagrams themed and correctly sized in both themes (pre-rendered SVG — should be present immediately, no pop).
- Tables render as real tables (not raw
|pipes — that's the GFM/MDX bug). - Code blocks not over-indented (no spurious leading whitespace in the source snippet) and lifted off the page.
- Hero / cards have depth (glow, lift), inline code is a brand-tinted chip.
- Light AND dark both read cleanly.
Diagnosing a flicker / twitch / layout-shift
The cause is almost always one of: font swap (fixed — font-display: optional + preload in Head.astro), client-side rendering settling, or Mermaid (fixed — build-time pre-render). To measure:
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.
- 2d ago First seen · 52 lines · 96 tokens per session scan A d88d3aecb2a2
qa-cratis-docs is a skill published in the GitHub repository Cratis/AI (2 stars, last pushed 4d ago), licensed MIT. It adds 96 tokens to every session and 871 once invoked, about $0.0005 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
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.
auth-and-identity
Use this skill for authentication, authorization, or identity in a Cratis Arc project — backend, frontend, or both. Covers identity providers (IProvideIdentityDetails), protecting commands/queries with authorization attributes, Microsoft Identity Platform, connecting backend identity to React, multi-tenant identity…
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…
cratis-readmodel
Step-by-step guidance for creating a Cratis Chronicle read model from scratch — defining events, choosing between projection and reducer, [ReadModel] record with static query methods, and the generated TypeScript proxy in React. Use when creating a read model, working with [EventType], [ReadModel], IProjectionFor…