leo: Instructions file for Claude Code

CLAUDE.md

leo CLAUDE.md is an instructions file for Claude Code from blackpaw-studio/leo. It costs 1,779 tokens per session, scanned A, original, MIT.

Repository instructions for Leo, a Go command-line tool that supervises Claude Code agents and schedules their tasks.

In plain words
What is it for?
Use them when changing Leo’s commands or service, running one test, checking coverage, or working with local and remote agents.
Why use it?
They explain how the daemon, agents, scheduled tasks, messaging plugins, builds, and tests fit together, reducing the chance of unsafe or incorrect changes.

Instructions file for Claude Code

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

This is blackpaw-studio/leo's own configuration. It tells Claude Code how to work on leo 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 leo configures →

Reuse

Borrowing it

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

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 leo CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/blackpaw-studio/leo/claude-md.svg)](https://agentmods.dev/instructions/blackpaw-studio/leo/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/blackpaw-studio/leo/claude-md"><img src="https://agentmods.dev/badge/instructions/blackpaw-studio/leo/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,779 This file is loaded in full into every session.
When invoked 1,779 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01779 $0.01779
Opus 5 $0.00890 $0.00890
Sonnet 5 $0.00356 $0.00356
Haiku 4.5 $0.00178 $0.00178

Measured 6d ago against content hash 715254ac9a68, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

leo 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 6d 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.

CLAUDE.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository agent guidance

This file provides shared guidance to coding agents working in this repository. AGENTS.md is a symlink to this file so Claude Code and Codex use one source of truth.

What is Leo

Leo is a Go CLI that supervises Claude Code agents and schedules tasks. leo service runs the daemon — web UI, cron, agent supervision, and the IPC socket — which keeps ephemeral agents alive, each in its own tmux session. Channels (Telegram, Slack, webhook, etc.) are Claude Code plugins the user installs separately; Leo only knows them as opaque plugin IDs.

Two core primitives:

  • Agents (leo agent): spawn/list/attach/stop/suspend/resume/reset/logs for on-demand agents created from templates, supervised by the daemon with restart-on-crash. Dual-purpose — runs locally against the daemon, or acts as a thin SSH client against a remote leo host when client.hosts is configured. Agents can idle-suspend after inactivity and auto-resume on the next message.
  • Tasks (leo run <task>, cron-scheduled): default runtime: oneshot invokes a fresh claude -p per firing; the agent handles outbound messaging via whatever channel plugin(s) are configured. runtime: persistent instead injects the prompt into a supervised agent — template: <name> targets that template's agent explicitly (shareable across tasks), or an implicit agent named after the task is spawned/resumed on demand ("ensure-exists") when no template: is set. See docs/configuration/persistent-tasks.md.

Build & Test Commands

make build          # Build binary to bin/leo
make install        # go install
make test           # go test -race -cover ./...
make lint           # go vet + staticcheck
make snapshot       # goreleaser snapshot

# Run a single test
go test -race -run TestFunctionName ./internal/config/

# Coverage report
go test -race -coverprofile=coverage.out ./... && go tool cover -html=coverage.out

Version is injected via ldflags: -X github.com/blackpaw-studio/leo/internal/cli.Version=$(VERSION)

Read the full file on GitHub · 90 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. 6d ago First seen · 90 lines · 1,779 tokens per session scan A 715254ac9a68

Subscribe to this mod's changes

leo CLAUDE.md is an instructions file published in the GitHub repository blackpaw-studio/leo (5 stars, last pushed yesterday), licensed MIT. It adds 1,779 tokens to every session, about $0.0089 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens