leonidas: Instructions file for Claude Code

CLAUDE.md

leonidas CLAUDE.md is an instructions file for Claude Code 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 for Claude Code

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

This is JeremyDev87/leonidas's own configuration. It tells Claude Code how to work on leonidas 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 leonidas configures →

Reuse

Borrowing it

Nothing to install: this file belongs to JeremyDev87/leonidas. 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/JeremyDev87/leonidas/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/JeremyDev87/leonidas

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 leonidas CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jeremydev87/leonidas/claude-md/github.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/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 leonidas CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jeremydev87/leonidas/claude-md"><img src="https://agentmods.dev/badge/instructions/jeremydev87/leonidas/claude-md.svg" alt="Reviewed on agentmods" width="80" 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. 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 $0.00944 $0.00944
Opus 5.5 $0.00378 $0.00378
Sonnet 5.5 $0.00189 $0.00189
Haiku 4.5 $0.00094 $0.00094

Measured 2mo ago against content hash fd1e99282dbb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 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.

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. 2mo 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 8mo ago), licensed MIT. It adds 944 tokens to every session, about $0.0038 per session on Opus 5.5. 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

leonidas CLAUDE.md compared with instructions from other repositories

leonidas CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
leonidas CLAUDE.mdJeremyDev87/leonidasInstructions file28mo agoMITA944Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode