baudbot: Instructions file for Codex

AGENTS.md

baudbot AGENTS.md is an instructions file for Codex, OpenCode from modem-dev/baudbot. It costs 1,461 tokens per session, scanned B, original, MIT.

An AGENTS.md instruction file for Baudbot, a system that receives coding requests from Slack and runs AI coding workers on a server. It describes the control agent, temporary isolated workspaces, incident monitoring, pull requests, and continuous-integration feedback.

In plain words
What is it for?
Use it when developing or troubleshooting Baudbot, its Slack gateway, control agent, development workers, incident agent, or deployment setup.
Why use it?
It explains how work moves from a Slack request to code changes, tests, pull requests, and status updates, helping agents follow the system's operating boundaries.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is modem-dev/baudbot's own configuration. It tells Codex and OpenCode how to work on baudbot itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything baudbot configures →

Reuse

Borrowing it

Nothing to install: this file belongs to modem-dev/baudbot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/modem-dev/baudbot/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/modem-dev/baudbot

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for baudbot AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/modem-dev/baudbot/agents-md/github.svg)](https://agentmods.dev/instructions/modem-dev/baudbot/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/modem-dev/baudbot/agents-md"><img src="https://agentmods.dev/badge/instructions/modem-dev/baudbot/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.

agentmods 80×15 button for baudbot AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/modem-dev/baudbot/agents-md"><img src="https://agentmods.dev/badge/instructions/modem-dev/baudbot/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,461 This file is loaded in full into every session.
When invoked 1,461 The same file — it is already loaded in full.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01461 $0.01461
Opus 5.5 $0.00584 $0.00584
Sonnet 5.5 $0.00292 $0.00292
Haiku 4.5 $0.00146 $0.00146

Measured 2mo ago against content hash 2be57f9c652b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

baudbot AGENTS.md scanned grade B with 1 finding 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo baudbot update
AGENTS.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Baudbot — Agent Guidelines

Baudbot is hardened infrastructure for running always-on AI agents.

Use this file for repo-wide guidance. For directory-specific rules, use the nearest nested AGENTS.md:

How Baudbot works

Baudbot is a persistent, team-facing coding agent system. It connects to Slack, receives work requests from developers, and autonomously executes coding tasks (branch, code, test, PR, CI) on a Linux server.

Runtime model: A long-running control agent stays connected to Slack, triages incoming requests, and delegates work to ephemeral dev agents that each run in isolated git worktrees. A sentry agent handles on-demand incident triage. All agents run as an unprivileged baudbot_agent Unix user.

Slack
   ↓
Gateway bridge (gateway-bridge dir; broker pull-mode or legacy Socket Mode)
   ↓
control-agent (always-on, manages todo/routing/Slack threads)
   ├── dev-agent(s) — ephemeral coding workers in isolated worktrees
   └── sentry-agent — incident triage (Sentry alerts)
         ↓
git commits → PRs → CI feedback → thread updates back to Slack

Deployment model: Admin-managed source (this repo) is deployed as immutable, git-free release snapshots under /opt/baudbot. The agent runtime (/home/baudbot_agent) receives deployed extensions, skills, and bridge code. Updates and rollbacks are atomic symlink switches. See docs/architecture.md for full details.

Startup boundary: start.sh vs agent

There are two startup phases with distinct ownership:

Phase Owner Scope
OS boot (start.sh) Admin Env validation, permissions, secrets, socket cleanup, launch pi
Agent boot (startup-pi.sh) Agent Gateway bridge, sentry-agent, dev-agents, session wiring

Rule: start.sh must never spawn tmux sessions or background processes that need pi runtime state (session UUIDs, socket paths, etc.). Those only exist after pi starts. All tmux sessions (bridge, sentry-agent, dev-agents) are owned and managed by the agent via startup-pi.sh or extensions. start.sh may only kill stale processes as pre-cleanup.

Read the full file on GitHub · 112 lines

Changes

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.

  1. 2mo ago First seen · 112 lines · 1,461 tokens per session scan B 2be57f9c652b

Subscribe to this mod's changes

baudbot AGENTS.md is an instructions file published in the GitHub repository modem-dev/baudbot (218 stars, last pushed 5mo ago), licensed MIT. It adds 1,461 tokens to every session, about $0.0058 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

baudbot AGENTS.md compared with instructions from other repositories

baudbot AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
baudbot AGENTS.mdmodem-dev/baudbotInstructions file2185mo agoMITB1,461Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode