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 instructions/coda0hq/open-artifacts/claude-mdgit clone --depth 1 https://github.com/coda0HQ/open-artifactsWrote 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/coda0hq/open-artifacts/claude-md)<a href="https://agentmods.dev/instructions/coda0hq/open-artifacts/claude-md"><img src="https://agentmods.dev/badge/instructions/coda0hq/open-artifacts/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 | $0.00711 | $0.00711 |
| Opus 5 | $0.00356 | $0.00356 |
| Sonnet 5 | $0.00142 | $0.00142 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
open-artifacts 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 6d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
Open Artifacts is a Cloudflare Worker engine plus the published
skills/using-open-artifacts/ agent skill. Worker code is in src/: routing
and composition live in app.ts, api.ts, and index.ts; persistence is in
store.ts; viewer wrapping is in wrap.ts; optional live and handoff features
live in live-* and handoff/. The installable skill owns SKILL.md, its
zero-dependency CLI scripts, reference contracts, and Recipe examples.
Keep formal behavior specifications in tests/features/. Worker integration
tests live in tests/worker/; Node CLI tests live in tests/cli/; the optional
real-browser live workflow is tests/e2e/live-e2e.mjs. Static assets are in
public/; do not hand-edit src/generated/, public/vendor/mediapipe/, or
worker-configuration.d.ts.
Build, Test, and Development Commands
pnpm dev
pnpm test # Worker tests via workerd
pnpm test:cli # CLI/skill tests in Node
pnpm test -- tests/worker/api.test.ts
pnpm test:cli -- tests/cli/artifact-cli.test.ts
pnpm typecheck # Worker and CLI targets
pnpm check # Biome format and lint check
node tests/e2e/live-e2e.mjs # Requires agent-browser; uses port 8788
Run pnpm test, pnpm test:cli, pnpm typecheck, and pnpm check for
cross-cutting changes. pnpm run deploy deploys directly to production; use it
only when explicitly requested. @fradser/pi-kit is absent; do not add an
unverified replacement.
Coding Style & Naming Conventions
Use TypeScript strict mode for Worker code and Node ESM for skill scripts.
Biome enforces two-space indentation, double quotes, and semicolons. Name tests
*.test.ts; name BDD files *.feature. Add dependencies with pnpm add or
pnpm remove, never by editing package.json.
Artifacts are sandboxed under strict CSP and opaque origin: no runtime fetch,
external resources, or storage. Preserve the Recipe/token contract, both
:root themes, and viewer-owned --oa-* tokens. Canvas runtime behavior belongs
in references/canvas.md, not per-artifact patches.
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.
- 6d ago First seen · 64 lines · 711 tokens per session scan A af5c88674f74
open-artifacts CLAUDE.md is an instructions file published in the GitHub repository coda0HQ/open-artifacts (51 stars, last pushed 9d ago), licensed MIT. It adds 711 tokens to every session, about $0.0036 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
awsmux AGENTS.md
Instructions for 0hardik1/awsmux, covering agents.md, what awsmux is, build, test, verify, layout and the safety model — invariants you must not weaken.
plan-forge naming.instructions.md
Azure naming conventions — Microsoft CAF abbreviations, constraints, uniqueness, tagging.
agent-skills fortrabbit.instructions.md
Instructions for fortrabbit/agent-skills, covering fortrabbit — github copilot instructions, what fortrabbit is, configuration lookup, available operations and mcp server (optional).
cron-mcp CLAUDE.md
Claude Code instructions for Shreyas-Profile/cron-mcp, covering deploying cron-mcp to hetzner + regiq.in, server (shared with the rest of the globalion mcp fleet), deploy a new version, first-time subdomain wiring (cron.regiq.in) and env vars.
Railway-mcp CLAUDE.md
Claude Code instructions for Travis-Gilbert/Railway-mcp, covering railway mcp server, quick reference, file map, architecture and key patterns.
equinix-fabric-mcp CLAUDE.md
Claude Code instructions for sliuuu/equinix-fabric-mcp, covering claude.md — equinix-fabric-mcp, canonical files, auth, add equinixclientid and equinixclientsecret and running.