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/beadhive/beadhive/claude-mdgit clone --depth 1 https://github.com/beadhive/beadhiveWrote 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/beadhive/beadhive/claude-md)<a href="https://agentmods.dev/instructions/beadhive/beadhive/claude-md"><img src="https://agentmods.dev/badge/instructions/beadhive/beadhive/claude-md.svg" alt="Measured on agentmods" 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 | $0.00592 | $0.00592 |
| Opus 5 | $0.00296 | $0.00296 |
| Sonnet 5 | $0.00118 | $0.00118 |
| Haiku 4.5 | $0.00059 | $0.00059 |
Grade A, and why
beadhive CLAUDE.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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Instructions for AI Agents
Agentic Git Flow (AGF)
This repo authors bh (Beadhive), the integration-plane driver for AGF, and is driven by
it. AGF is the abstract, tracker-independent process; Beadflow is that process implemented
on beads — what this repo's tool (bh) drives. Don't improvise raw git / gh pr for the
lifecycle — drive beads through bh work and load the role skill for your seat (coordinator
/ developer / merger / work).
See docs/AGF.md for the tenets, the one-terminal loop, and which skill to load when.
Bead history is an archive — never squash it
Do not run bd compact or bd flatten on any hive. Not with a retention window, not
"just the old commits", not to reclaim disk. If you believe a hive needs either, stop and ask
the operator.
Bead version history is the only record of when each lifecycle stage happened — claim,
close, reopen — reconstructable by diffing consecutive versions from bd history <id> --json.
Both commands destroy that permanently: compact squashes everything past its retention
window, and flatten squashes all of it, prunes remote-tracking refs, and runs Dolt GC, so
the next push replaces the remote's copy too. There is no archive tier to fall back on yet.
This is not hypothetical. bh-art was created 2026-06-29 and its reachable history begins
2026-07-25 — about a month is already gone, and nothing surfaced that loss at the time.
A two-tier design (permanent archive on the remote + a compacted working copy for the open
frontier) is filed as bh-3vs6c. Until it lands, both commands are one-way.
AGF — Agentic Git Flow
This repo is onboarded as a bh hive and develops via AGF: work is tracked in beads
and driven through bh, not raw git / bd / gh.
- Is this repo set up for AGF? → run
bh hive ready(add-vfor the line-item breakdown). - Lifecycle, roles, conventions: see
docs/AGF.mdand the bh plugin's role skills. - Drive beads with
bh work; load the role skill for your seat (coordinator / developer / merger).
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 First seen · 42 lines · 592 tokens per session scan A 89b5cdb27ee0
beadhive CLAUDE.md is an instructions file published in the GitHub repository beadhive/beadhive (10 stars, last pushed yesterday), licensed MIT. It adds 592 tokens to every session, about $0.0030 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
codex-autoresearch AGENTS.md
Instructions for TheGreenCedar/codex-autoresearch, covering agents.md, purpose and scope, canonical sources, stable product boundaries and source and package boundaries.
OwnPilot AGENTS.md
Instructions for ownpilot/OwnPilot, covering ownpilot, architecture, key patterns, commands and tech stack.
pydantic-ai-todo CLAUDE.md
Instructions for vstorm-co/pydantic-ai-todo, covering claude.md, what this project is, commands, structure and core pattern.
nightshift AGENTS.md
AGENTS.md instructions for orwa-mahmoud/nightshift: AI-assisted contributions are welcome. The same correctness, security, licensing, testing, and quality standards apply regardless of which tools are used.
SeekMoney-ai CLAUDE.md
Claude Code instructions for zykooooooooo/SeekMoney-ai, covering claude.md, project overview, development commands, development and production.
Agent-Worlds CLAUDE.md
Instructions for hjl2004-10/Agent-Worlds, covering ai夸父 开发规范文档 (v2.0 - skill化重构), 架构总览：概念坐标系（先看这张图）, 横向：子系统（业界术语 ↔ 本项目目录）, 纵向：作用域分层（每个子系统内部都按此三层） and 正交二维（横×纵 = 网格，不是树）.