agentmods.dev

Claude-Pipeline: Instructions file for Claude Code

CLAUDE.md

Claude-Pipeline CLAUDE.md is an instructions file for Claude Code, Codex from TheAstrelo/Claude-Pipeline. It costs 4,731 tokens per session, scanned A, original, MIT.

Project instructions for Claude-Pipeline, a development pipeline that sends a task through multiple review and coding phases. Its main executable is a shell script that runs Claude or Codex subprocesses for each phase.

In plain words
What is it for?
Running or modifying the Claude-Pipeline workflow, including its phase prompts, slash-command wrappers, validation gates, and optional final commit.
Why use it?
They explain how the pipeline is structured and which file actually runs it. This avoids confusing interactive helper commands with the standalone pipeline engine.

Instructions file for Claude CodeCodex

Written for Codex and Claude Code: runs codex exec, but also the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is TheAstrelo/Claude-Pipeline's own configuration. It tells Claude Code and Codex how to work on Claude-Pipeline 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 Claude-Pipeline configures →

not rated 45repo +1 5d ago A scan 4,731 tokens original MIT
View source ↗ TheAstrelo/Claude-Pipeline
Reuse

Borrowing it

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

Made for: Claude Code, Codex.

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 Claude-Pipeline CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/theastrelo/claude-pipeline/claude-md"><img src="https://agentmods.dev/badge/instructions/theastrelo/claude-pipeline/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,731 This file is loaded in full into every session.
When invoked 4,731 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 $0.04731 $0.04731
Opus 5 $0.02365 $0.02365
Sonnet 5 $0.00946 $0.00946
Haiku 4.5 $0.00473 $0.00473

Measured 10d ago against content hash 3b78f76cc373, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

Claude-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 10d 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 · 347 lines

How it starts

The opening of the file, as written. The whole thing — 347 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.

Project Overview

This is a provider-agnostic 13-phase (0–12) development pipeline for Claude Code and Codex. It transforms a task description into reviewed, optionally committed code. The single engine is run-pipeline.sh.

The One Engine

run-pipeline.sh is the single real executable. It runs each phase as a fresh claude -p --no-session-persistence or codex exec --ephemeral subprocess, persists and validates the returned report, applies the gate, and optionally commits after Phase 12.

  • run-pipeline.sh — the engine. Run it directly: bash run-pipeline.sh [options] "task".
  • .claude/commands/auto-pipeline.md — a thin /auto-pipeline slash-command wrapper that runs the engine with PIPELINE_NONINTERACTIVE=1 and interprets its exit code.
  • The per-phase slash commands (/design, /plan-review, /ar, /security-review, …) are interactive helpers that dispatch to .claude/agents/ via the Task tool. The engine does not use them — it builds every phase prompt inline in build_prompt().

Commands

# Run the pipeline (standalone)
bash run-pipeline.sh "add a GET /api/version endpoint"
bash run-pipeline.sh --provider=codex "add a GET /api/version endpoint"
bash run-pipeline.sh --provider=claude "add a GET /api/version endpoint"
bash run-pipeline.sh --profile=paranoid --mode=dev "handle payments"

# Demo starter project (demo/starter-project/)
npm install && npm test

# Full test battery (one command; auto-discovers every tests/*.sh suite)
bash tests/run-all.sh          # sequential
bash tests/run-all.sh -p       # parallel

Flags the engine actually parses: --provider=auto|claude|codex, --profile=yolo|fast|standard|paranoid, --mode=auto|dev, --push (publish the committed run branch to the remote), --pr (--push plus pull-request guidance), --budget=elastic|strict, --skip-arm (skip Phase 1), --skip-ar (skip Phase 3), --skip-pmatch (skip Phase 5), --model-strong=, --model-fast=, --max-budget-usd= (per-phase cap), --max-run-budget-usd= (whole-run cap), --no-commit, --allow-dirty, --allow-untested-commit (explicit recorded no-test auto-commit waiver), --resume=RUN_ID, --policy-rollout=legacy|shadow|enforced, --retention-days=, --retention-max-runs=, --help. Env knobs: PIPELINE_PROVIDER_TIMEOUT_SECONDS (default 2400), PIPELINE_PROVIDER_RETRIES (default 1), PIPELINE_AUTH_PREFLIGHT=0, PIPELINE_BASELINE_CHECKS=0, PIPELINE_COMMAND_TIMEOUT_SECONDS (default 900), PIPELINE_WORKTREE=0 (legacy in-place mode), PIPELINE_WORKTREE_LINK_PATHS (gitignored build state symlinked into the run worktree; default node_modules .venv venv vendor), PIPELINE_ALLOW_REMOTE_DEPS=1 (recorded waiver for git/https dependency specifiers), --budget=elastic|strict / PIPELINE_BUDGET_POLICY (elastic default: a capped phase retries with a doubled cap within the run cap, ledger-recorded; budgets are excluded from the resume identity so a run-cap halt resumes with a higher cap), PIPELINE_BUDGET_EXTENSIONS (default 2), PIPELINE_COLLAPSE=0 (full planning ladder in yolo/fast), PIPELINE_BUILD_FIX_ATTEMPTS (default 2; in-build verify/fix loop, 0 disables). PIPELINE_PUSH_REMOTE (default origin). Resume requires the original task and an exact engine/config/Git/evidence match. Still not implemented: --template, --batch-qa, --fix, and a --yolo shorthand.

Read the full file on GitHub · 347 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. 10d ago First seen · 347 lines · 4,731 tokens per session scan A 3b78f76cc373

Subscribe to this mod's changes

Claude-Pipeline CLAUDE.md is an instructions file published in the GitHub repository TheAstrelo/Claude-Pipeline (45 stars, last pushed 5d ago), licensed MIT. It adds 4,731 tokens to every session, about $0.0237 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.

Building agentsagenticai-agentsaideranthropicautomationclaude
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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens