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/battysh/batty/claude-mdgit clone --depth 1 https://github.com/battysh/battyWrote 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/battysh/batty/claude-md)<a href="https://agentmods.dev/instructions/battysh/batty/claude-md"><img src="https://agentmods.dev/badge/instructions/battysh/batty/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 | $0.01511 | $0.01511 |
| Opus 5 | $0.00756 | $0.00756 |
| Sonnet 5 | $0.00302 | $0.00302 |
| Haiku 4.5 | $0.00151 | $0.00151 |
Grade A, and why
batty 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 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Batty — Agent Instructions
What Is This Project
Batty is a hierarchical agent command system for software development. It runs a small team of agents inside tmux, routes messages between roles, tracks work on a shared Markdown board, and keeps the whole run visible in the terminal.
See planning/architecture.md for the system design and planning/dev-philosophy.md for development principles.
Tech Stack
- Language: Rust
- CLI framework: clap
- Terminal runtime: tmux (pane layout, display-only surfaces when shim mode is active, session persistence)
- Agent shim: PTY-owning subprocess per agent, screen classification, structured socketpair protocol (
src/shim/) - PTY support: portable-pty (used by shim runtime for agent PTY management)
- Async runtime: tokio
- Config format: YAML (
.batty/team_config/team.yaml) - Board format: Markdown tasks with YAML frontmatter
- Execution logs: JSON lines
Project Structure
src/ # Rust source
shim/ # Agent shim runtime (PTY, state classifier, protocol, chat)
docs/ # User and reference documentation
assets/ # Static assets (images, demos)
scripts/ # Utility scripts
planning/ # Architecture, roadmap, philosophy docs
.agents/ # Codex agent rules/skills
.claude/ # Claude agent rules/skills
.batty/
team_config/
team.yaml # Team topology, routing, layout, timing
*.md # Role prompts used to launch architect/manager/engineer agents
board/ # Shared task board and task files
events.jsonl # Team event log
Development Principles
- Compose, don't monolith. Use existing CLI tools where possible.
- Markdown as backend. Keep state human-readable and git-versioned.
- Minimal code. Build the smallest thing that works.
- No premature abstraction. Prefer obvious code over clever indirection.
- Test what matters. Focus on tmux supervision, message routing, board state, and prompt handling.
- Extensive unit tests. Every module gets
#[cfg(test)]coverage for happy paths, edge cases, and failures. Runcargo testbefore committing. If a task adds code, it adds tests.
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 · 137 lines · 1,511 tokens per session scan A a3b18b255bc0
batty CLAUDE.md is an instructions file published in the GitHub repository battysh/batty (53 stars, last pushed 15d ago), licensed MIT. It adds 1,511 tokens to every session, about $0.0076 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
turso AGENTS.md
Instructions for tursodatabase/turso, covering turso agent guidelines, quick reference, testing, running tests and test organization.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
azure-sdk-for-rust resourcemanager.instructions.md
Instructions for Azure/azure-sdk-for-rust, a project described as: This repository is for the active development of the Azure SDK for Rust. For consumers of the SDK we recommend visiting Docs.rs and looking up the docs for any of libraries in the SDK.
Browser4 CLAUDE.md
Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
bifrost AGENTS.md
Instructions for bifrost-proxy/bifrost, covering bifrost 项目开发规则, 执行心法, 执行模式与完成定义, 任务模式判定 and 变更类型与验证路由(先判定,后执行).
nanocodex AGENTS.md
Instructions for gakonst/nanocodex, covering nanocodex development, commands, product boundary, account, connect, and walletconnect and workflow.