opensource-pipeline CLAUDE.md

opensource-pipeline CLAUDE.md is an instructions file for coding agents from herakles-dev/opensource-pipeline. It costs 566 tokens per session, scanned A, original, MIT.

A three-stage Claude Code workflow for turning a private project into an open-source project. It copies the project, removes secrets and private references, checks the result, and prepares documentation and packaging files.

In plain words
What is it for?
It helps fork a project for public release, verify that sensitive data was removed, and generate files such as a README, license, setup script, and contribution guide.
Why use it?
It addresses the risk of publishing credentials or other private material by adding an independent sanitization check before release. It also reduces the manual work needed to prepare basic project files.

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/herakles-dev/opensource-pipeline/claude-md
Clone the repo
git clone --depth 1 https://github.com/herakles-dev/opensource-pipeline

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 opensource-pipeline CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/herakles-dev/opensource-pipeline/claude-md.svg)](https://agentmods.dev/instructions/herakles-dev/opensource-pipeline/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/herakles-dev/opensource-pipeline/claude-md"><img src="https://agentmods.dev/badge/instructions/herakles-dev/opensource-pipeline/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 566 This file is loaded in full into every session.
When invoked 566 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 $0.00566 $0.00566
Opus 5 $0.00283 $0.00283
Sonnet 5 $0.00113 $0.00113
Haiku 4.5 $0.00057 $0.00057

Measured 4d ago against content hash b15ff9ec0561, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

opensource-pipeline 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 4d 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 · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

opensource-pipeline

Stack: Claude Code Skills + Agents (Markdown) Purpose: Safely open-source any project through automated secret stripping, sanitization, and packaging.

What

A 3-agent pipeline for Claude Code that takes any private project and makes it safely open-sourceable. Strips secrets, verifies sanitization, generates professional docs (CLAUDE.md, setup.sh, README, LICENSE, CONTRIBUTING).

Quick Start

./setup.sh                          # Install skill + agents into ~/.claude/
claude                              # Open Claude Code
# Then say: /opensource fork my-project

Architecture

skills/opensource/SKILL.md          # Orchestrator — routes commands, chains agents
agents/opensource-forker.md         # Stage 1: Copy, strip secrets, replace refs
agents/opensource-sanitizer.md      # Stage 2: Independent audit (read-only)
agents/opensource-packager.md       # Stage 3: Generate CLAUDE.md, setup.sh, README

Flow: User -> Skill (orchestrator) -> Forker -> Sanitizer -> Packager -> User review -> GitHub

Commands

/opensource fork PROJECT            # Full pipeline
/opensource verify PROJECT          # Run sanitizer only
/opensource package PROJECT         # Run packager only

Key Files

skills/opensource/SKILL.md          Main skill — the entry point (routes to agents)
agents/opensource-forker.md         Copies project, strips secrets, generates .env.example
agents/opensource-sanitizer.md      Scans for leaked secrets, PII, internal refs (30+ patterns)
agents/opensource-packager.md       Generates CLAUDE.md, setup.sh, README, LICENSE, CONTRIBUTING
setup.sh                           One-command installer

How It Works

  1. Forker copies the project, strips secrets (API keys, tokens, passwords), replaces internal references (domains, paths, IPs) with placeholders, generates .env.example
  2. Sanitizer independently audits the fork — 6 scan categories, 30+ regex patterns, PASS/FAIL verdict
  3. Packager generates professional open-source packaging — CLAUDE.md, setup.sh, README, LICENSE, CONTRIBUTING, issue templates
  4. User reviews, approves, and publishes to GitHub

Read the full file on GitHub · 58 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. 4d ago First seen · 58 lines · 566 tokens per session scan A b15ff9ec0561

Subscribe to this mod's changes

opensource-pipeline CLAUDE.md is an instructions file published in the GitHub repository herakles-dev/opensource-pipeline (2 stars, last pushed 1mo ago), licensed MIT. It adds 566 tokens to every session, about $0.0028 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.