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/nulab/bee/agents-mdgit clone --depth 1 https://github.com/nulab/beeWhat 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 | $0.05721 | $0.05721 |
| Opus 5 | $0.02861 | $0.02861 |
| Sonnet 5 | $0.01144 | $0.01144 |
| Haiku 4.5 | $0.00572 | $0.00572 |
Grade A, and why
bee 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 yesterday.
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 — 462 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to AI coding agents when working with code in this repository.
Overview
bee (bee) — a CLI for the Backlog project management service. pnpm workspace monorepo with ESM-only packages.
Commands
# Install
pnpm install
# Lint (oxlint, NOT ESLint)
pnpm run lint
pnpm run lint:fix
# Type check (tsc --noEmit per package via turbo)
pnpm run typecheck
# Format (oxfmt)
pnpm run format
pnpm run format:check
# Test
pnpm run test # all tests
pnpm --filter @repo/backlog-utils exec vitest run src/client.test.ts # single file
# Build
pnpm --filter @nulab/bee build
# Dev (CLI)
pnpm --filter @nulab/bee dev
Module Resolution: bundler
TypeScript is configured with module: "preserve" / moduleResolution: "bundler". This means:
- Relative imports omit the file extension:
// Correct import { foo } from "./foo"; // Wrong import { foo } from "./foo.js"; import { foo } from "./foo.ts"; - Inline
typekeyword — useimport { type Foo, bar }instead of separateimport type { Foo }(enforced by oxlint)
Architecture
apps/cli — CLI entry point (commander.js, consola logging)
apps/docs — Astro Starlight documentation site
packages/backlog-utils — Backlog API client wrapper (backlog-js, OAuth auto-refresh, rate-limit handling)
packages/cli-utils — Shared CLI utilities (output formatting, table, splitArg, prompts)
packages/config — CLI configuration management (~/.config/bee RC file, space/auth resolution)
packages/test-utils — Shared test helpers (mock client, mock consola, process.exit spy, vi.clearAllMocks setup)
packages/tsconfigs — Shared TypeScript base config
Documentation site (apps/docs)
Command reference pages are auto-generated from CLI source code — do NOT create .md files under apps/docs/src/content/docs/commands/. The dynamic route apps/docs/src/pages/commands/[...slug].astro uses loadCommands() (in apps/docs/src/lib/commands.ts) to import each command's BeeCommand metadata at build time and render documentation pages automatically.
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.
- yesterday First seen · 462 lines · 5,721 tokens per session scan A 762b9712f78b
bee AGENTS.md is an instructions file published in the GitHub repository nulab/bee (72 stars, last pushed 2d ago), licensed MIT. It adds 5,721 tokens to every session, about $0.0286 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 2026-08-31.
Other instructions, from other repositories
DevoxxGenieIDEAPlugin GEMINI.md
Instructions for devoxx/DevoxxGenieIDEAPlugin, a project described as: DevoxxGenie is an agentic plugin for IntelliJ IDEA that uses local LLM's (Ollama, LMStudio, GPT4All, Jan and Llama.cpp) and Cloud based LLMs to help review, test, explain your project code. Latest version now also supports Spec Driven Development…
squarebox CLAUDE.md
Instructions for SquareWaveSystems/squarebox, covering claude.md, agent skills, issue tracker, triage labels and domain docs.
mcpelevator CLAUDE.md
Instructions for pacnpal/mcpelevator, covering commands, architecture, conventions, agent skills and issue tracker.
clawchat-plugin-connect AGENTS.md
Instructions for XMethues/clawchat-plugin-connect, covering agent skills, issue tracker, triage labels and domain docs.
autonomous-dev CLAUDE.md
Claude Code instructions for akaszubski/autonomous-dev, covering autonomous-dev, critical rules, maintainer escape hatches, architecture and code navigation.
icloud-reminders-mcp CLAUDE.md
Claude Code instructions for Lingnik/icloud-reminders-mcp, covering icloud-reminders-mcp — project conventions, backlog: github issues, always, secrets, architecture and testing.