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/shirenchuang/agentbro/agents-mdgit clone --depth 1 https://github.com/shirenchuang/agentbroWrote 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/shirenchuang/agentbro/agents-md)<a href="https://agentmods.dev/instructions/shirenchuang/agentbro/agents-md"><img src="https://agentmods.dev/badge/instructions/shirenchuang/agentbro/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 | $0.01558 | $0.01558 |
| Opus 5 | $0.00779 | $0.00779 |
| Sonnet 5 | $0.00312 | $0.00312 |
| Haiku 4.5 | $0.00156 | $0.00156 |
Grade A, and why
agentbro 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 4d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project guidance for AI coding agents (Codex / Cursor / Aider / GitHub Copilot / Gemini CLI / …). Claude Code users should also read
.claude/CLAUDE.mdfor deeper detail.
What this is
AgentBro is a macOS-only Tauri app (Rust backend + React 19 / TypeScript frontend) that surfaces events from AI coding agents (Claude Code, Codex, Gemini CLI, Cursor, Copilot, etc.) into a floating "Dynamic Island" overlay.
Local commands
pnpm install # one-time
pnpm dev # browser UI only at http://localhost:1423
pnpm tauri:dev # full native app
pnpm lint # ESLint
pnpm test:run # vitest (one-shot)
pnpm build # tsc + vite build
cargo check --manifest-path src-tauri/Cargo.toml # Rust quick check
cargo test --manifest-path src-tauri/Cargo.toml # Rust tests
cargo fmt --manifest-path src-tauri/Cargo.toml # Rust format
cargo clippy --manifest-path src-tauri/Cargo.toml -- -D warnings
Before any PR, all of these must be green: pnpm lint, pnpm test:run, pnpm build, cargo check.
Mandatory GitHub delivery workflow
Use this workflow for every task that changes repository files, including bug fixes, features, refactors, tests, documentation, and configuration.
Pure questions, explanations, code review, read-only diagnosis, and research do not require an Issue or PR unless they turn into a repository change.
Before editing
- Confirm GitHub access with
gh auth statusand inspect the current branch and worktree. - Search open Issues for the same scope. Reuse an existing Issue only when it describes the requested work; otherwise create a focused Issue with context, goal, acceptance criteria, and constraints.
- Start from the latest
origin/devon a dedicated branch named<agent>/issue-<number>-<slug>(for example,codex/issue-61-agent-github-workflow). Never implement ondev,main, or an unrelated task branch. - If another task owns the current branch or worktree, preserve it and use a separate git worktree.
- Do not edit files until the Issue exists and its number is known.
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.
- 4d ago First seen · 98 lines · 1,558 tokens per session scan A ecc36593f348
agentbro AGENTS.md is an instructions file published in the GitHub repository shirenchuang/agentbro (211 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,558 tokens to every session, about $0.0078 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
Ocul-PM CLAUDE.md
Claude Code instructions for bunhine0452/Ocul-PM, covering claude.md, what this is, commands, single frontend test and rust (run from src-tauri/).
Ocul-PM AGENTS.md
AGENTS.md instructions for bunhine0452/Ocul-PM, covering ocul-pm 작업 기록 규칙, 0. 시작하기 전 — 과거를 먼저 찾는다, 1. 언제 기록하는가 (5 trigger), 2. 일지 파일 규격 (도구가 없을 때만) and 3. 금지.
caelo CLAUDE.md
Instructions for AuraVixStudio/caelo, covering claude.md, what this is, the single most important structural fact, architecture and commands.
vibe-roast copilot-instructions.md
Copilot instructions for PinkR1ver/vibe-roast: Prioritize actionable correctness, privacy, security, behavioral regressions, and missing tests. Do not block on style-only preferences.
cc-port AGENTS.md
Instructions for Ling-ye/cc-port, covering agents.md, 资源上传流程约束, windows 链接资源约束, claude 指令、记忆与多运行环境约束 and claude plugin 与 skill 约束.
psyche-build AGENTS.md
AGENTS.md instructions for OpenCoven/psyche-build, covering psyche build agent guide, repository role, planning and evidence contract, canonical routing and deterministic entrypoints.