leonidas CLAUDE.md

leonidas CLAUDE.md is an instructions file for coding agents from JeremyDev87/leonidas. It costs 944 tokens per session, scanned A, original, MIT.

Instructions for Leonidas, a GitHub Action that turns labeled GitHub issues into proposed plans and, after approval, pull requests.

In plain words
What is it for?
Use it to automate issue analysis, plan comments, approved implementation, commits, pull requests, sub-issue linking, and workflow recovery.
Why use it?
It separates planning from execution so a developer can review Claude Code’s proposed work before changes are committed and submitted.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/jeremydev87/leonidas/claude-md
Clone the repo
git clone --depth 1 https://github.com/JeremyDev87/leonidas

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 leonidas CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jeremydev87/leonidas/claude-md.svg)](https://agentmods.dev/instructions/jeremydev87/leonidas/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jeremydev87/leonidas/claude-md"><img src="https://agentmods.dev/badge/instructions/jeremydev87/leonidas/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 944 This file is loaded in full into every session.
When invoked 944 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 $0.00944 $0.00944
Opus 5 $0.00472 $0.00472
Sonnet 5 $0.00189 $0.00189
Haiku 4.5 $0.00094 $0.00094

Measured 3d ago against content hash fd1e99282dbb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

leonidas 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 3d 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 · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What is Leonidas

Leonidas is a GitHub Action that automates issue-to-PR workflows using Claude Code. It operates in two phases:

  1. Plan (triggered by labeling an issue with leonidas) — Claude analyzes the issue and posts an implementation plan as a comment
  2. Execute (triggered by /approve comment) — Claude follows the approved plan, makes commits, and creates a PR

The action has two entry points: src/main.ts (prompt preparation for Claude Code) and src/post_process_cli.ts (post-workflow tasks like linking sub-issues, posting comments, rescuing partial progress).

Commands

npm test                # Run all tests (vitest, single run)
npm run test:watch      # Watch mode
npm run test:coverage   # Coverage report (90% threshold for all metrics)
npm run lint            # ESLint + Prettier check
npm run lint:fix        # Auto-fix lint and formatting
npm run typecheck       # tsc --noEmit
npm run build           # ncc bundle → dist/index.js + dist/post_process_cli/

Run a single test file:

npx vitest run src/config.test.ts

Before committing, all four must pass: npm run lint && npm run typecheck && npm test && npm run build

Architecture

src/
├── main.ts                 # Entry point: reads inputs, loads config, builds prompts, sets GH Action outputs
├── config.ts               # Loads leonidas.config.yml, merges with action inputs, loads rule files
├── github.ts               # GitHub API wrapper (createGitHubClient factory returning method object)
├── types.ts                # Shared TypeScript interfaces (LeonidasConfig, ActionInputs, GitHubContext, etc.)
├── i18n.ts                 # 8-language translation map (en, ko, ja, zh, es, de, fr, pt)
├── comment_builder.ts      # Pure functions for building GitHub comment strings
├── post_process_cli.ts     # Separate CLI entry: link-subissues, post-completion, post-failure, rescue, post-process-pr, trigger-ci
├── utils/
│   └── sanitize.ts         # Prompt injection defense (wrapUserContent, escapeForShellArg)
├── prompts/
│   ├── system.ts           # Builds system prompt from prompts/system.md + .github/leonidas.md + rules
│   ├── plan.ts             # Plan-mode prompt with 5-phase methodology and restricted tools
│   └── execute.ts          # Execute-mode prompt with branch/PR instructions
├── templates/
│   └── plan_comment.ts     # Plan comment formatting
└── test-helpers/
    └── main.helpers.ts     # Shared test utilities

Read the full file on GitHub · 78 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. 3d ago First seen · 78 lines · 944 tokens per session scan A fd1e99282dbb

Subscribe to this mod's changes

leonidas CLAUDE.md is an instructions file published in the GitHub repository JeremyDev87/leonidas (2 stars, last pushed 6mo ago), licensed MIT. It adds 944 tokens to every session, about $0.0047 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

task-orchestrator CLAUDE.md

Instructions for jpicklyk/task-orchestrator, covering project: mcp task orchestrator, build commands, docker (most common), architecture and modes of operation.

jpicklyk/task-orchestrator · 4,722 tokens

shinobi CLAUDE.md

Claude Code instructions for numbererikson/shinobi, covering claude.md, what this is, dogfooding — use shinobi to build shinobi, dev commands and layout.

numbererikson/shinobi · 1,118 tokens

high-quality-projects-skill copilot-instructions.md

Copilot instructions for RandyNorthrup/high-quality-projects-skill: This repository provides two vendor-neutral workflows for holding a codebase to production standards.

RandyNorthrup/high-quality-projects-skill · 205 tokens

Claude-Code-Kanban-Automator CLAUDE.md

Instructions for cruzyjapan/Claude-Code-Kanban-Automator, covering claude.md, project overview, key development commands, database operations and development servers.

cruzyjapan/Claude-Code-Kanban-Automator · 1,570 tokens

ESAA-Core AGENTS.md

Instructions for elzobrito/ESAA-Core, covering agents.md — contrato operacional codex/esaa, 1. autoridade e termos, 2. cli e runner, ou configure o runner uma vez por sessão and 3. concorrência.

elzobrito/ESAA-Core · 2,154 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