bb is an agentic IDE that lets users control, customize, and automate a software-development environment through a desktop app, web app, command-line interface, or HTTP API. Developers use it to run work in observable threads that can be steered or handed off to other agents. Its catalogue add-ons provide skills and instructions for working with bb.
Borrowing it
Nothing to install: this file belongs to get-bb/bb. 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/get-bb/bb/main/AGENTS.mdgit clone --depth 1 https://github.com/get-bb/bbWrote 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/get-bb/bb/agents-md)<a href="https://agentmods.dev/instructions/get-bb/bb/agents-md"><img src="https://agentmods.dev/badge/instructions/get-bb/bb/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/get-bb/bb/agents-md"><img src="https://agentmods.dev/badge/instructions/get-bb/bb/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 | $0.01614 | $0.01614 |
| Opus 5.5 | $0.00646 | $0.00646 |
| Sonnet 5.5 | $0.00323 | $0.00323 |
| Haiku 4.5 | $0.00161 | $0.00161 |
Grade A, and why
bb 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 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Guidelines
Task Completion
- Carry the requested change through implementation, relevant verification, and fixes for failures it causes. Continue authorized, reversible local work without asking for approval at each step; ask when a missing user decision blocks progress.
- Match verification to the change. Once relevant checks pass, broaden or repeat them only for new changes, failures, or unresolved concerns.
- Read the linked guidance when its topic applies to the task.
Code And Contracts
- Code comments are forbidden, except for semantic tool directives and Plugin SDK declaration comments.
- When renaming a domain concept, search project-wide for stale names in variables, files, query keys, constants, tests, and docs; TypeScript only catches type references.
- Parse and validate data at system boundaries, then pass typed values internally. Restrict
unknownandas Xcasts to genuinely unknowable boundaries and narrow immediately. - Keep one-off types local; share types only for real cross-package contracts.
- Optional or nullable fields must represent meaningful absence. Fill defaults once at the server boundary and pass explicit values through internal routes, commands, and persisted events.
- Delete accepted-but-ignored route or command fields, or implement them end to end. Document route and command behavior when it is non-obvious.
Server And Daemon
- The server owns product policy: defaults, instructions, manager behavior, tool lists, and thread behavior. The host daemon owns host-local primitives, provider translation, runtime/session management, and workspace execution.
- Return raw host-local data from the daemon; assemble product behavior on the server. Move responsibility across this boundary only when the change requires it.
- Increment
HOST_DAEMON_PROTOCOL_VERSIONfor changes to server/daemon wire fields, including their types, requiredness, defaults, or meaning, unless compatibility with the previously shipped daemon is deliberately preserved and tested. This covers session payloads, WebSocket messages, and host RPC commands/results. Shared TypeScript builds do not verify compatibility with enrolled machines; the version bump triggers their update.
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 Changed · +1 lines · +63 tokens per session 4c3759184490
- 12d ago Changed · +31 tokens per session 4d8cb6ba7852
- 19d ago Changed · +1 lines · +90 tokens per session fff23b779a47
- 1mo ago Changed · +1 lines · +90 tokens per session 936c62fe6e0b
- 1mo ago Changed · +1 tokens per session 4d2250777336
- 1mo ago Changed · -24 lines · -807 tokens per session 3e4c8b27ae60
- 1mo ago Changed · -23 tokens per session 983535c8c253
- 1mo ago First seen · 82 lines · 2,169 tokens per session scan A a4c316fd3689
bb AGENTS.md is an instructions file published in the GitHub repository get-bb/bb (4,625 stars, last pushed today), licensed MIT. It adds 1,614 tokens to every session, about $0.0065 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 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.