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/raysonmeng/agent-bridge/claude-mdgit clone --depth 1 https://github.com/raysonmeng/agent-bridgeWhat 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 | $0.02848 | $0.02848 |
| Opus 5 | $0.01424 | $0.01424 |
| Sonnet 5 | $0.00570 | $0.00570 |
| Haiku 4.5 | $0.00285 | $0.00285 |
Grade A, and why
agent-bridge 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 3d 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 — 169 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.
语言 / Language
- 🔴 铁律：面向用户的叙述只可以用中文，禁止用英文。（用户多次强调，2026-06-11 再次明确"禁止说英文！！只可以说中文！"）。聊天回复、状态汇报、表格标题、列表、解释、报告里的叙述文字——一律中文。唯一例外：代码、命令、文件路径、标识符、API 名、配置键、PR/commit 里既有的英文约定段落可保留原文（因为它们就是字面量）。除此之外任何句子都不许用英文。每次回复前自检：有没有冒出英文叙述句？有就改成中文。
- 强制使用中文回复（用户明确要求 / 强制项目级规则）。所有面向用户的输出（解释、报告、问答、plan、commit message 中的中文部分、issue / report）使用中文。
- 代码内的注释、变量名、提交信息中的英文部分、日志保持英文（与项目既有约定一致）。
- 涉及给用户读的内容（README、用户文档、终端说明）必须中文优先。
- 若用户用英文提问，仍用中文回复（除非他明确要求英文）。
Commands
Runtime is Bun — do not change the local Bun version.
| Task | Command |
|---|---|
| Install deps | bun install |
| Type check | bun run typecheck (= tsc --noEmit) |
| Run all tests | bun test src |
| Run a single test file | bun test src/unit-test/<name>.test.ts |
| Run a single test by name | bun test src -t "<test name pattern>" |
| Full pre-commit check | bun run check (typecheck + tests + plugin sync + plugin versions) |
| Build CLI binary | bun run build:cli → dist/cli.js |
| Build plugin bundle | bun run build:plugin → plugins/agentbridge/server/{bridge-server,daemon}.js |
| Verify plugin sync | bun run verify:plugin-sync |
| Validate plugin manifest | bun run validate:plugin (requires claude CLI) |
| Local dev link | bun link then agentbridge dev (registers local marketplace + installs plugin; repo checkout only) |
| Update global CLI + plugin | bun run install:global (one command: rebuild, replace global install, sync plugin; --skip-plugin to opt out) |
| Start session | agentbridge claude (one terminal) + agentbridge codex (another) |
| Show quota snapshot | agentbridge budget [--json] (both agents' 5h/weekly usage, drift, pause state) |
| Stop everything | agentbridge kill |
Before committing: run bun run typecheck && bun test src.
After modifying src/: run bun run build:plugin before end-to-end testing. The installed plugin loads the bundled JS under plugins/agentbridge/server/, not the raw TS — forgetting to rebuild means you are testing the old code.
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.
- 3d ago First seen · 169 lines · 2,848 tokens per session scan A 4b3e247fb1f9
agent-bridge CLAUDE.md is an instructions file published in the GitHub repository raysonmeng/agent-bridge (315 stars, last pushed 4d ago), licensed MIT. It adds 2,848 tokens to every session, about $0.0142 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
siyuan AGENTS.md
AGENTS.md instructions for siyuan-note/siyuan, covering agents.md, 1. non-negotiable constraints, do not hand-edit, verification and prohibited operations and 2. project-specific rules.
veritas-kanban AGENTS.md
Instructions for BradGroux/veritas-kanban, covering agents.md — canonical agent instructions for veritas kanban, runtime requirements, repository layout, essential commands and install.
ima2-gen AGENTS.md
Instructions for lidge-jun/ima2-gen, covering ima2-gen — ai context, what this project does, tech stack, project structure and agent skills (packaged).
gini-agent AGENTS.md
AGENTS.md instructions for Open-Curiosity/gini-agent, covering gini agent instructions, shape, adrs, boundaries and branches.
paxm AGENTS.md
Instructions for pax-beehive/paxm, covering paxm 开发要求, git 与协作, 架构边界, 代码与验证 and 文档与发布.
barkeep AGENTS.md
Instructions for iannuttall/barkeep, covering agent notes, product rules, repo map, commands and app structure.