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/open-resource-discovery/a2a-editor/claude-mdgit clone --depth 1 https://github.com/open-resource-discovery/a2a-editorWrote 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/open-resource-discovery/a2a-editor/claude-md)<a href="https://agentmods.dev/instructions/open-resource-discovery/a2a-editor/claude-md"><img src="https://agentmods.dev/badge/instructions/open-resource-discovery/a2a-editor/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 | $0.01342 | $0.01342 |
| Opus 5 | $0.00671 | $0.00671 |
| Sonnet 5 | $0.00268 | $0.00268 |
| Haiku 4.5 | $0.00134 | $0.00134 |
Grade A, and why
a2a-editor 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 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
React component library for analyzing, validating, and interacting with A2A (Agent-to-Agent) protocol agent cards. Provides a multi-mode playground (full, lite, viewer, editor, card-view) distributed as both an npm library and a standalone CDN bundle.
Commands
# Development
npm run dev # Vite dev server at localhost:5173
npm run website:start # Docusaurus docs site at localhost:3000
# Building
npm run build # Full build: lib + standalone
npm run build:lib # ES module library only (dist/)
npm run build:standalone # IIFE CDN bundle only (dist-standalone/)
npm run build:demo # Demo SPA for GitHub Pages
# Testing
npm test # Vitest unit tests (run once)
npm run test:watch # Vitest in watch mode
npm run test:e2e # Playwright e2e (requires servers on :5173 and :3000)
# Code quality
npm run lint # ESLint check
npm run format # Prettier + ESLint auto-fix
npm run format:check # Check formatting without fixing
Running a single unit test
npx vitest run src/lib/utils/__tests__/a2a-compliance.test.ts
Running a single e2e test
npx playwright test e2e/tests/chat.spec.ts --project=vite
Architecture
Build modes
The project produces four distinct build artifacts:
| Command | Output | Format | Use case |
|---|---|---|---|
build:lib |
dist/ |
ES modules, multiple entry points | npm consumers |
build:standalone |
dist-standalone/ |
IIFE, React bundled | CDN / script tag |
build:demo |
dist-demo/ |
SPA | GitHub Pages demo |
website:build |
website/build/ |
Static | Docusaurus docs |
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 · 129 lines · 1,342 tokens per session scan A fed1e1771151
a2a-editor CLAUDE.md is an instructions file published in the GitHub repository open-resource-discovery/a2a-editor (21 stars, last pushed today), licensed Apache-2.0. It adds 1,342 tokens to every session, about $0.0067 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
trpc-agent-go AGENTS.md
AGENTS.md instructions for trpc-group/trpc-agent-go, covering agents.md, project overview, engineering principles, go design conventions and implementation workflow.
Agentlas-OS CLAUDE.md
Claude Code instructions for agentlas-ai/Agentlas-OS, covering claude code adapter, public release boundary, route, use when and verification.
Agentlas-OS AGENTS.md
AGENTS.md instructions for agentlas-ai/Agentlas-OS, covering agentlas core engine meta-agent team, repository constitution: local main only, public release allowlist (hard rule), source of truth and third-party plugin boundary.
Agentlas-OS GEMINI.md
Gemini CLI instructions for agentlas-ai/Agentlas-OS, covering gemini cli adapter, public release boundary, startup, default behavior and global command.
innovation-lab-examples typescript.instructions.md
Instructions for fetchai/innovation-lab-examples, a project described as: 80+ production-ready AI agent examples in Python — build autonomous agents, multi-agent systems and agentic AI with uAgents, ASI:One, MCP, A2A, LangChain, CrewAI, Gemini, Claude and OpenAI.
agent-skills-standard CLAUDE.md
Claude Code instructions for HoangNguyen0403/agent-skills-standard, covering agent protocol and self-learning protocol.