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/longzhi/clawhive/agents-mdgit clone --depth 1 https://github.com/longzhi/clawhiveWrote 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/longzhi/clawhive/agents-md)<a href="https://agentmods.dev/instructions/longzhi/clawhive/agents-md"><img src="https://agentmods.dev/badge/instructions/longzhi/clawhive/agents-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 | $0.03168 | $0.03168 |
| Opus 5 | $0.01584 | $0.01584 |
| Sonnet 5 | $0.00634 | $0.00634 |
| Haiku 4.5 | $0.00317 | $0.00317 |
Grade A, and why
clawhive 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 4d 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 — 313 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.
Project Overview
Clawhive is a Rust-native single-binary (~14MB) multi-agent AI platform for deploying agents across messaging channels (Telegram, Discord, Slack, WhatsApp, iMessage). 13-crate workspace, edition 2021, Rust 1.92.0+, version 0.1.0-alpha.*.
Build / Test / Lint
# One-time setup (git hooks: fmt+clippy on commit, full check on push)
just install-hooks
# Full CI-equivalent quality gate (run before every PR)
just check
# Equivalent to:
# 1. cargo fmt --all -- --check
# 2. cargo clippy --workspace --all-targets -- -D warnings
# 3. cargo test --workspace
# Individual commands
just fmt # cargo fmt --all (auto-format)
just fmt-check # cargo fmt --all -- --check
just clippy # cargo clippy --workspace --all-targets -- -D warnings
just test # cargo test --workspace
cargo build --release # release binary
# Run a single test (by name substring)
cargo test -p clawhive-core -- policy::tests::check_exec -v
# Run all tests in one crate
cargo test -p clawhive-core
# Run tests matching a pattern
cargo test -p clawhive-scheduler -- integration
# Frontend (in web/ directory, use bun not npm)
cd web && bun install && bun run build
cd web && bun run dev # dev server with proxy to localhost:3001
# Deploy to Mac Studio (pushes dev, builds remotely, restarts daemon)
./deploy.sh
# Version release (tags on main, not dev)
just release patch # or minor/major
CI runs 4 parallel jobs on ubuntu-latest: check, test, clippy, fmt. RUSTFLAGS=-Dwarnings is set globally in CI — all warnings are errors.
Workspace Structure
crates/
├── clawhive-cli/ # CLI binary (clap) — the only bin crate
├── clawhive-core/ # Orchestrator, tools, policy, skills, config — most logic lives here
├── clawhive-memory/ # Memory system (file store, JSONL sessions, SQLite index, embedding)
├── clawhive-gateway/ # Gateway, agent routing, rate limiting, scheduled task listener
├── clawhive-bus/ # In-process event bus (pub/sub)
├── clawhive-provider/ # LLM provider trait + multi-provider adapters
├── clawhive-channels/ # Channel adapters (Telegram, Discord, Slack, WhatsApp, iMessage)
├── clawhive-auth/ # OAuth and API key auth
├── clawhive-scheduler/ # Cron-based task scheduling
├── clawhive-server/ # HTTP API server (axum) + embedded SPA
├── clawhive-schema/ # Shared DTOs (InboundMessage, OutboundMessage, BusMessage)
├── clawhive-runtime/ # Task executor abstraction
└── clawhive-tui/ # Terminal dashboard (ratatui)
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.
- 4d ago First seen · 313 lines · 3,168 tokens per session scan A a5549b8b601a
clawhive AGENTS.md is an instructions file published in the GitHub repository longzhi/clawhive (57 stars, last pushed 3mo ago), licensed MIT. It adds 3,168 tokens to every session, about $0.0158 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 2026-08-30.
Other instructions, from other repositories
agentscope copilot-instructions.md
Copilot instructions for agentscope-ai/agentscope, covering agentscope code review guide, 1. code quality, 2. [must] code security, 3. [must] testing & dependencies and 4. code standards.
chat-gun-react-agent AGENTS.md
AGENTS.md instructions for HsienW/chat-gun-react-agent, covering chat gun react agent:全域 ai 編程規則, 1. 適用範圍, openspec workflow router 感知, agent 角色寫入前硬檢查 and 2. 指令與規格優先順序.
chat-gun-react-agent CLAUDE.md
Claude Code instructions for HsienW/chat-gun-react-agent, covering chat gun react agent:claude 協調與規格管理規則, 1. 文件定位, 1.1 openspec workflow router 感知, 2. claude 的角色 and 2.1 寫入前角色硬檢查.
pragma AGENTS.md
AGENTS.md instructions for pqpo/pragma, covering agents.md, 项目定位, 技术基线, 目录结构 and package 命名.
zhin zhin-plugin.instructions.md
Instructions for zhinjs/zhin, covering zhin plugin runtime authoring, package contract, convention directories, imports and native typescript and command routes.
lobu AGENTS.md
Instructions for lobu-ai/lobu, covering repo map, unrecoverable — never do these, facts you cannot derive, ship a change and how to work.