open-artifacts CLAUDE.md

open-artifacts CLAUDE.md is an instructions file for Claude Code from coda0HQ/open-artifacts. It costs 711 tokens per session, scanned A, original, MIT.

Repository instructions for Open Artifacts, a Cloudflare Worker project and its installable agent skill. They explain the project layout, commands, coding conventions, and testing rules.

In plain words
What is it for?
Developing the Worker, maintaining the agent skill and command-line scripts, running targeted tests, and avoiding changes to generated or vendor files.
Why use it?
They help an agent understand where code belongs and how to build, test, and type-check the Worker and command-line tools.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

Install

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.

agentmods
npx agentmods add instructions/coda0hq/open-artifacts/claude-md
Clone the repo
git clone --depth 1 https://github.com/coda0HQ/open-artifacts

Made for: Claude Code.

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.

agentmods badge for open-artifacts CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/coda0hq/open-artifacts/claude-md.svg)](https://agentmods.dev/instructions/coda0hq/open-artifacts/claude-md)
Your own site
<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>
Per session 711 This file is loaded in full into every session.
When invoked 711 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 6d ago against content hash af5c88674f74, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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.

CLAUDE.md · 64 lines

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.

Read the full file on GitHub · 64 lines

Changes

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.

  1. 6d ago First seen · 64 lines · 711 tokens per session scan A af5c88674f74

Subscribe to this mod's changes

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.