Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/instructions/uinerd16/aicanvas/claude-md)<a href="https://agentmods.dev/instructions/uinerd16/aicanvas/claude-md"><img src="https://agentmods.dev/badge/instructions/uinerd16/aicanvas/claude-md.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 | $0.01947 | $0.01947 |
| Opus 5 | $0.00974 | $0.00974 |
| Sonnet 5 | $0.00389 | $0.00389 |
| Haiku 4.5 | $0.00195 | $0.00195 |
Grade A, and why
aicanvas CLAUDE.md 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.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@AGENTS.md
AI Canvas — Global Rules
What this project is
AI Canvas (aicanvas.me) is an open component marketplace where every component ships with:
- Its full source code
- One expert-crafted, comprehensive AI remix prompt (platform-agnostic; works in any AI coding tool)
How work is organized
Three tiers; every task routes to exactly one:
| Tier | Folder | Design rules | Details |
|---|---|---|---|
| Standalone components | components-workspace/<slug>/ |
Creative freedom (except container chrome) | components-workspace/CLAUDE.md |
| Design systems | design-systems/<system>/ |
Strict, each system's own tokens.ts |
design-systems/CLAUDE.md |
| Site chrome | app/, app/components/ |
sand/olive/Manrope | supervisor/skills/site-design-tokens.md |
The component pipeline (create + modify, gates, registry rules) lives in supervisor/CLAUDE.md. Every built or modified component gets an independent review pass against the checklist in reviewer/CLAUDE.md before the user sees it. Integration steps live in integration/CLAUDE.md. Known recurring mistakes: supervisor/mistakes.md. The component inventory is app/lib/component-registry.tsx — the registry IS the status ledger; do not maintain a separate one.
Secrets & credentials — this is an OPEN-SOURCE repo
This repository is public. A leaked secret is exposed the moment it is committed. Treat every key as radioactive:
- Never commit a secret. Real values live only in
.env.local(already gitignored). Confirm.env.localand any*service_role*/*secret*files are covered by.gitignorebefore touching keys. Never paste a live key into a tracked file, a doc, a commit message, or chat output. NEXT_PUBLIC_ships to the browser. Only the Supabase anon/publishable key may carry that prefix. Theservice_role/SUPABASE_SECRET_KEYmust NEVER beNEXT_PUBLIC_and must only be read in server code.- Prefer the Supabase CLI over keys on disk.
supabase loginstores the token in the OS keychain, not the repo — nothing to accidentally commit. Use aservice_rolekey in.env.localonly as a last resort, never beyond it. - Supabase access is read-only by default. Run writes/migrations only when the user explicitly asks, one at a time, showing the SQL first. It is the production project — no destructive or schema changes without sign-off.
- If a secret is ever found in tracked history, treat it as compromised: rotate it in the provider, don't just delete the line.
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 Changed · +8 lines · +463 tokens per session 0c8af26c602d
- 6d ago First seen · 80 lines · 1,484 tokens per session scan A 3c85120d61ca
aicanvas CLAUDE.md is an instructions file published in the GitHub repository uiNerd16/aicanvas (51 stars, last pushed 2d ago), licensed MIT. It adds 1,947 tokens to every session, about $0.0097 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 2026-08-30.
Other instructions, from other repositories
www-sacred AGENTS.md
Instructions for internet-development/www-sacred, covering agents.md, what this repo is, repo map, conventions and the fonts menu previews.
starwind-ui AGENTS.md
AGENTS.md instructions for starwind-ui/starwind-ui, covering agents.md, project shape, useful commands and contribution conventions.
animal-island-ui AGENTS.md
AGENTS.md instructions for guokaigdg/animal-island-ui, covering agents.md — working in this repository, read first, by task, verification, content that must be kept in sync and ground rules.
ns-ui AGENTS.md
AGENTS.md instructions for nikolas-sapa/ns-ui, covering agents.md — working inside this repo, structure, autoplay — how a card demonstrates itself, descriptor schema and driver constraints (don't regress these).
animal-island-ui CLAUDE.md
Claude Code instructions for guokaigdg/animal-island-ui, a project described as: Kawaii React UI component library 可爱风格 React 组件库.
kernel-ui AGENTS.md
AGENTS.md instructions for kemiljk/kernel-ui, covering working in this repo, release checklist for pull requests, the one rule that matters most: build every component twice, repo layout and conventions to match, not reinvent.