agentmods.dev

zoogent: Instructions file for Claude Code

CLAUDE.md

zoogent CLAUDE.md is an instructions file for Claude Code from bepunk/zoogent. It costs 4,839 tokens per session, scanned A, original, MIT.

Repository instructions for ZooGent, a tool that runs teams of AI agents, routes work between them, records logs, and tracks costs.

In plain words
What is it for?
Use them when modifying ZooGent’s agent runtime, team tools, project structure, or Claude Code integration.
Why use it?
They give a coding agent the project’s architecture, runtime rules, and supported ways to create and manage agents, reducing incorrect changes.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is bepunk/zoogent's own configuration. It tells Claude Code how to work on zoogent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything zoogent configures →

not rated 3repo 6mo ago A scan 4,839 tokens original MIT
View source ↗ bepunk/zoogent
Reuse

Borrowing it

Nothing to install: this file belongs to bepunk/zoogent. 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/bepunk/zoogent/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/bepunk/zoogent

Made for: Claude Code.

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.

agentmods badge for zoogent CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/bepunk/zoogent/claude-md/github.svg)](https://agentmods.dev/instructions/bepunk/zoogent/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/bepunk/zoogent/claude-md"><img src="https://agentmods.dev/badge/instructions/bepunk/zoogent/claude-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.

agentmods 80×15 button for zoogent CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/bepunk/zoogent/claude-md"><img src="https://agentmods.dev/badge/instructions/bepunk/zoogent/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,839 This file is loaded in full into every session.
When invoked 4,839 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.04839 $0.04839
Opus 5.5 $0.01936 $0.01936
Sonnet 5.5 $0.00968 $0.00968
Haiku 4.5 $0.00484 $0.00484

Measured 2mo ago against content hash 964002fe8779, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

zoogent CLAUDE.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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- **Sandbox (always on)**: TypeScript agents spawn with `--permission --allow-fs-read=* --allow-fs-write={sharedDir} --max-old-space-size=512`. No child_process, no native addons. Write only to `ZOOGENT_SHARED_DIR`.
CLAUDE.md · 321 lines

How it starts

The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - ZooGent v0.4.4

What is ZooGent

Lightweight AI agent orchestrator with built-in Architect AI. Multi-team support. Process manager for agent teams — spawns agents, routes tasks, tracks costs, captures logs. Single container, SQLite, npm package zoogent.

Two UX paths:

  1. Chat UI (main) — Architect AI at /teams/:slug/chat designs teams, writes code, manages agents
  2. MCP (dev path) — ~35 tools for Claude Code, team-scoped, supports local and remote servers. Agent code flows through MCP: create_agent with source (bundled atomically) or separate write_agent_code for iteration. Team code library tools: list_team_library, write_team_library_file, get_team_library_file, delete_team_library_file.

Agent Runtime Model (v0.4)

Two runtimes:

  • typescript (default, 95% of agents): Source lives in agents.source column. On upload, zoogent bundles with esbuild (blessed deps list in src/lib/agent-bundler.ts) and stores source + bundle + bundleHash. Process manager materializes {dataDir}/teams/{teamId}/agents/{id}.mjs on spawn (skipped if hash matches marker file) and runs node {path} with NODE_PATH set to zoogent's node_modules (so blessed externalized deps resolve).
  • exec (escape hatch): Provides command + args + cwd. Used for wrapping binaries / Python / Go / shell. Code is NOT managed through MCP. CRUD via command PATCH fields applies only here.

Code is never written to the local filesystem of the MCP client. All write_agent_code / create_agent({ source }) calls upload through HTTP to the zoogent server and are persisted in SQLite. This means the same MCP flow works against local and remote zoogent servers identically.

Invariants (enforced at route + architect level):

  • runtime='typescript' → source required for run; command/args/cwd null.
  • runtime='exec' → command required; source/bundle null.
  • runtime cannot be changed after creation.
  • source cannot be updated via PATCH (use PUT /code or MCP write_agent_code).

Read the full file on GitHub · 321 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.

  1. 2mo ago First seen · 321 lines · 4,839 tokens per session scan A 964002fe8779

Subscribe to this mod's changes

zoogent CLAUDE.md is an instructions file published in the GitHub repository bepunk/zoogent (3 stars, last pushed 6mo ago), licensed MIT. It adds 4,839 tokens to every session, about $0.0194 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents
Related

zoogent CLAUDE.md compared with instructions from other repositories

zoogent CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
zoogent CLAUDE.mdbepunk/zoogentInstructions file36mo agoMITA4,839Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot