agentmods.dev

oss-autopilot: Instructions file for Claude Code

CLAUDE.md

oss-autopilot CLAUDE.md is an instructions file for Claude Code from costajohnt/oss-autopilot. It costs 2,441 tokens per session, scanned A, original, MIT.

Project instructions for installing and configuring OSS Autopilot, a Claude Code plugin for managing open-source work.

In plain words
What is it for?
They help check Node.js and GitHub CLI access, install the plugin, restart Claude Code, and run its setup command.
Why use it?
They tell users which prerequisites are needed and what to run when the plugin is first installed.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

This is costajohnt/oss-autopilot's own configuration. It tells Claude Code how to work on oss-autopilot 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 oss-autopilot configures →

not rated 13repo changed 2d ago A scan 2,441 tokens original MIT
View source ↗ costajohnt/oss-autopilot
Reuse

Borrowing it

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

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 oss-autopilot CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/costajohnt/oss-autopilot/claude-md"><img src="https://agentmods.dev/badge/instructions/costajohnt/oss-autopilot/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,441 This file is loaded in full into every session.
When invoked 2,441 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 $0.02441 $0.02441
Opus 5 $0.01221 $0.01221
Sonnet 5 $0.00488 $0.00488
Haiku 4.5 $0.00244 $0.00244

Measured 2d ago against content hash 177d99dc4b51, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

oss-autopilot 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 2d 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 · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 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.

IMPORTANT: If User Just Pasted This Repo URL

Guide them through installation immediately. Don't wait for them to ask.

Say: "I see you want to install OSS Autopilot! Let me help you set it up."

Then follow the steps below.

Step 1: Check prerequisites

node --version  # Need 22+
gh auth status  # Need GitHub CLI authenticated

If gh is not installed or authenticated:

"You'll need the GitHub CLI for this plugin. Install it from https://cli.github.com/ and run gh auth login."

Step 2: Install the plugin (marketplace)

/plugin marketplace add costajohnt/oss-autopilot
/plugin install oss-autopilot@oss-autopilot

Step 3: Restart and run setup

"Great! The plugin is installed. Please restart Claude Code to load it, then run /setup-oss to configure your preferences."

After restart, /oss and /setup-oss commands will be available.

The CLI auto-builds on first run (requires Node.js 22+ and npm).

For Developers: Project Overview

oss-autopilot is a Claude Code plugin with a TypeScript CLI backend for managing open source contributions. The repo is structured as a pnpm monorepo.

Architecture

The system has three layers:

  1. Plugin Layer (commands/, agents/, skills/) — Markdown-based Claude Code plugin components. Commands like /oss orchestrate the workflow. Agents handle specific tasks (PR response, CI diagnosis, issue scouting). Skills contain contribution best practices.

  2. TypeScript CLI (packages/core/src/cli.ts → packages/core/dist/cli.bundle.cjs) — Commander-based CLI that the plugin invokes with --json for structured output. Entry point is packages/core/src/cli.ts, which registers subcommands from packages/core/src/commands/. The CLI is bundled into a single CJS file via esbuild for portability.

  3. Core Logic (packages/core/src/core/) — The domain layer. Key modules:

    • types.ts — All type definitions. Key PR type: FetchedPR (ephemeral, fetched fresh each run in v2). TrackedPR was removed in v2.
    • state.ts — StateManager singleton. Reads/writes ~/.oss-autopilot/state.json. Handles v1→v2→v3→v4 migration and auto-backups
    • pr-monitor.ts — PRMonitor class. Fetches open PRs from GitHub Search API, enriches each with CI status, review decision, merge conflicts, maintainer comments, and computes FetchedPRStatus
    • github.ts — Shared Octokit instance with @octokit/plugin-throttling for rate limit handling
    • utils.ts — GitHub URL parsing, date helpers, token detection (tries $GITHUB_TOKEN then gh auth token)
    • Issue discovery and vetting are delegated to @oss-scout/core via commands/scout-bridge.ts

Read the full file on GitHub · 196 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. 2d ago Changed 177d99dc4b51
  2. 9d ago First seen · 196 lines · 2,441 tokens per session scan A a533911d0af2

Subscribe to this mod's changes

oss-autopilot CLAUDE.md is an instructions file published in the GitHub repository costajohnt/oss-autopilot (13 stars, last pushed 2d ago), licensed MIT. It adds 2,441 tokens to every session, about $0.0122 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.

Claude CodeTypeScriptclideveloper-toolsgithubopen-source
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 · 5,153 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