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/raeseoklee/artifacty/agents-mdgit clone --depth 1 https://github.com/raeseoklee/artifactyWrote 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/raeseoklee/artifacty/agents-md)<a href="https://agentmods.dev/instructions/raeseoklee/artifacty/agents-md"><img src="https://agentmods.dev/badge/instructions/raeseoklee/artifacty/agents-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 | $0.00706 | $0.00706 |
| Opus 5 | $0.00353 | $0.00353 |
| Sonnet 5 | $0.00141 | $0.00141 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
artifacty AGENTS.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 5d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
Artifacty shares LLM artifacts over HTTP, CLI, and MCP.
src/server.js: localhost HTTP server, browser routes, and JSON API.src/mcp-server.js: MCP stdio server exposing Artifacty tools.src/cli.js: command-line interface for serving, publishing, importing, listing, and reading artifacts.src/lib/storage.js: SQLite metadata store and immutable version-file handling.src/lib/converters.js: agent artifact conversion rules for Claude, Codex, Gemini, GitHub Copilot, Cursor, and generic payloads.src/lib/installer.js: MCP config installers for Claude, Codex, and Gemini.src/lib/render.js: server-rendered dashboard, viewer, and editor HTML.test/*.test.js: Node test runner suites.docs/integrations.md: setup notes for Claude Code, Codex, Gemini CLI, GitHub Copilot in VS Code, and Cursor.
Build, Test, and Development Commands
npm start: run the HTTP dashboard on127.0.0.1:8787.npm test: run all tests with Node’s built-in test runner.npm run lint: syntax-check source and test files withnode --check.node src/mcp-server.js: run the MCP stdio server.node src/cli.js import --agent claude --file artifact.html: convert and store an external artifact.node src/cli.js install claude --dry-run: preview generated MCP config.node src/cli.js check: verify MCP tool discovery.node src/cli.js index rebuild: rebuild the optional SQLite FTS5 search index.node src/cli.js integrity: verify version files, hashes, and orphaned files.
Coding Style & Naming Conventions
Use modern ESM JavaScript and Node built-ins where practical. Keep modules small and route shared behavior through src/lib/* instead of duplicating logic in CLI, HTTP, and MCP layers. Use two-space indentation, semicolons only where already present, camelCase for functions and variables, and descriptive tool names such as artifacty_create.
Do not add new dependencies unless the operational value clearly outweighs the extra install and security surface.
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.
- 5d ago First seen · 55 lines · 706 tokens per session scan A 202b622b81cb
artifacty AGENTS.md is an instructions file published in the GitHub repository raeseoklee/artifacty (0 stars, last pushed yesterday), licensed MIT. It adds 706 tokens to every session, about $0.0035 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 2026-09-01.
Other instructions, from other repositories
artifacts CLAUDE.md
Claude Code instructions for anvilnine/artifacts, covering artifacts, domains and writing docs (readme, docs/, pr bodies, comments).
codex-a2a-gateway AGENTS.md
AGENTS.md instructions for phamviet86/codex-a2a-gateway, covering repository guidance, mission and scope, architecture ownership, non-negotiable invariants and compatibility policy.
yap AGENTS.md
AGENTS.md instructions for M0Rf30/yap, covering yap agent guidelines, project overview, key packages, architecture and build/test commands.
wire AGENTS.md
AGENTS.md instructions for SlanchaAI/wire, covering agents.md — read this first if you are an ai agent, two modes — pick the one that matches your situation, §0 — talking to other agents (v0.9+), zero-config bootstrap (v0.12) and identity is per session (v0.13+) — not per directory.
agent-2-agent CLAUDE.md
Instructions for CtriXin/agent-2-agent, covering a2a — ai agent 快速上下文, 这是什么, 文件职责, 关键设计决策 and 修改注意事项.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).