What is bobbit AGENTS.md?

Repository instructions for Bobbit, covering its commands, architecture, editing workflow, and test levels. They explain where the server, user interface, agent runtime, and MCP tools live.

Use them when building or running Bobbit, changing its interface or server, restarting services, and running layout, unit, browser, end-to-end, or manual tests.

They help contributors find the right code and choose the appropriate checks after making changes.

How G-Research/bobbit configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to G-Research/bobbit. 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/G-Research/bobbit/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/G-Research/bobbit

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/g-research/bobbit/agents-md/github.svg)](https://agentmods.dev/instructions/g-research/bobbit/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/g-research/bobbit/agents-md"><img src="https://agentmods.dev/badge/instructions/g-research/bobbit/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/g-research/bobbit/agents-md"><img src="https://agentmods.dev/badge/instructions/g-research/bobbit/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,613 This file is loaded in full into every session.

When invoked 1,613 The same file — it is already loaded in full.

Security scan A 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.

Model	Per session	Once invoked
Fable 5.1	$0.01613	$0.01613
Opus 5.5	$0.00645	$0.00645
Sonnet 5.5	$0.00323	$0.00323
Haiku 4.5	$0.00161	$0.00161

Measured 2mo ago against content hash 1f1786906e31, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

bobbit AGENTS.md scanned grade A 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**Driving the gateway from an agent**: prefer the `bobbit_read`/`bobbit_orchestrate`/`bobbit_admin` tools over hand-rolled `curl` where their tool-groups are enabled. See [docs/bobbit-gateway-tool.md](docs/bobbit-gateway

AGENTS.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bobbit — Agent Guide

Commands

npm run build          # Build server + UI
npm run dev:harness    # Gateway + vite dev
npm run restart-server # Rebuild & restart after server changes
npm run check          # Layout + type checks
npm run test:layout    # Validate test conventions
npm run test:new -- <semantic> <name> # Scaffold canonical test
npm run test:unit      # Vitest tier-1, fixed 3-worker cap
npm run test:browser   # Playwright browser-v2
npm run test:e2e       # E2E v2: git/worktree/Docker/MCP/restart
npm run test:manual    # Real agents/LLM + Docker (~5 min); ONLY gate-exempt path

UI changes (src/ui/, src/app/) hot-reload under npm run dev:harness. Server changes (src/server/) require npm run restart-server. Run npm run check first. Sessions survive restarts via .bobbit/state/sessions.json.

Architecture map

Orient here, then rg for the symbol.

Server REST/WS: src/server/ — REST in server.ts::handleApiRoute(), WS in src/server/ws/.
Agent runtime: src/server/agent/ — sessions, manager, status, steer, respawn, store, project context. See docs/bg-process-persistence.md for bash_bg.
MCP / tools: src/server/mcp/, defaults/tools/<group>/ (project overrides under .bobbit/config/tools/<group>/). Descriptions budget-pinned by tests/unit/core/tool-description-budget.unit.test.ts.
Skills: .claude/skills/<name>/SKILL.md.
Roles/tools/skills resolution: unified PackResolver over one ordered pack list in src/server/agent/pack-*.ts; built-in packs in market-packs/. See docs/marketplace.md.
UI shell: src/app/ — state, render, message-reducer, dialogs, follow-tail.
UI components: src/ui/ — components, tools/renderers/, lazy/.
Tests: canonical directory plus semantic suffix determines runner ownership. See docs/testing-strategy.md.
Docs: docs/ (reference + design notes), docs/design/ (per-feature design docs), docs/debugging.md (full diagnostic checklists), docs/internals.md (config cascade, sandbox, search, MCP).

Read the full file on GitHub · 79 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.

2mo ago Changed · +1 lines · +62 tokens per session 1f1786906e31
2mo ago First seen · 78 lines · 1,551 tokens per session scan A cdb3885bc3bc

Subscribe to this mod's changes

bobbit AGENTS.md is an instructions file published in the GitHub repository G-Research/bobbit (18 stars, last pushed 1mo ago), licensed MIT. It adds 1,613 tokens to every session, about $0.0065 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

bobbit AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
bobbit AGENTS.mdG-Research/bobbit	Instructions file	18	1mo ago	MIT	A	1,613	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	today	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

bobbit: Instructions file for Codex