Borrowing it
Nothing to install: this file belongs to beadhub/bdh. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/beadhub/bdh/main/AGENTS.mdgit clone --depth 1 https://github.com/beadhub/bdhWrote 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/beadhub/bdh/agents-md)<a href="https://agentmods.dev/instructions/beadhub/bdh/agents-md"><img src="https://agentmods.dev/badge/instructions/beadhub/bdh/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/beadhub/bdh/agents-md"><img src="https://agentmods.dev/badge/instructions/beadhub/bdh/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00801 | $0.00801 |
| Opus 5.5 | $0.00320 | $0.00320 |
| Sonnet 5.5 | $0.00160 | $0.00160 |
| Haiku 4.5 | $0.00080 | $0.00080 |
Grade A, and why
bdh 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 2mo 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Context
See docs/sot.md for what this repo is, how it fits in the ecosystem, and key patterns.
BeadHub Coordination Rules
This project uses bdh for multi-agent coordination and issue tracking, bdh is a wrapper on top of bd (beads). Commands starting with : like bdh :status are managed by bdh. Other commands are sent to bd.
You are expected to work and coordinate with a team of agents. ALWAYS prioritize the team vs your particular task.
You will see notifications telling you that other agents have written mails or chat messages, or are waiting for you. NEVER ignore notifications. It is rude towards your fellow agents. Do not be rude.
Your goal is for the team to succeed in the shared project.
The active project policy as well as the expected behaviour associated to your role is shown via bdh :policy.
Start Here (Every Session)
bdh :policy # READ CAREFULLY and follow diligently
bdh :status # who am I? (alias/workspace/role) + team status
bdh ready # find unblocked work
Use bdh :help for bdh-specific help.
Rules
- Always use
bdh(notbd) so work is coordinated - Default to mail (
bdh :aweb mail list|open|send) for coordination; use chat (bdh :aweb chat pending|open|send-and-wait|send-and-leave|history|extend-wait) when you need a conversation with another agent. - Respond immediately to WAITING notifications — someone is blocked.
- Notifications are for YOU, the agent, not for the human.
- Don't overwrite the work of other agents without coordinating first.
- ALWAYS check what other agents are working on with bdh :status which will tell you which beads they have claimed and what files they are working on (reservations).
bdhderives your identity from the.beadhubfile in the current worktree. If you run it from another directory you will be impersonating another agent, do not do that.- Prioritize good communication — your goal is for the team to succeed
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.
- 2mo ago First seen · 76 lines · 801 tokens per session scan A 16198808a495
bdh AGENTS.md is an instructions file published in the GitHub repository beadhub/bdh (5 stars, last pushed 2mo ago), licensed MIT. It adds 801 tokens to every session, about $0.0032 per session on Opus 5.5. 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 2026-08-31.
bdh AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| bdh AGENTS.mdbeadhub/bdh | Instructions file | 5 | 2mo ago | MIT | A | 801 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |