atelier-pipeline: Instructions file for Claude Code

AGENTS.md

atelier-pipeline AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from robertsfeir/atelier-pipeline. It costs 683 tokens per session, scanned A, original, Apache-2.0.

Project instructions for Atelier Pipeline, a Cursor plugin that coordinates several AI coding agents. They describe its agents, commands, enforcement scripts, quality rules, and optional memory service.

In plain words
What is it for?
Use them when changing the Cursor plugin, its agent personas, commands, hooks, references, pipeline state, or Node.js and PostgreSQL memory service.
Why use it?
They provide a common way to run the agent pipeline and apply quality checks, so work is less dependent on undocumented project knowledge.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: PreToolUse hook event, but also the file is AGENTS.md. Also seen: mentions subagents.

This is robertsfeir/atelier-pipeline's own configuration. It tells Claude Code, Codex and OpenCode how to work on atelier-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 atelier-pipeline configures →

Reuse

Borrowing it

Nothing to install: this file belongs to robertsfeir/atelier-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/robertsfeir/atelier-pipeline/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/robertsfeir/atelier-pipeline

Made for: Claude Code, Codex, OpenCode.

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 atelier-pipeline AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/robertsfeir/atelier-pipeline/agents-md/github.svg)](https://agentmods.dev/instructions/robertsfeir/atelier-pipeline/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/robertsfeir/atelier-pipeline/agents-md"><img src="https://agentmods.dev/badge/instructions/robertsfeir/atelier-pipeline/agents-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 atelier-pipeline AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/robertsfeir/atelier-pipeline/agents-md"><img src="https://agentmods.dev/badge/instructions/robertsfeir/atelier-pipeline/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 683 This file is loaded in full into every session.
When invoked 683 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 $0.00683 $0.00683
Opus 5 $0.00342 $0.00342
Sonnet 5 $0.00137 $0.00137
Haiku 4.5 $0.00068 $0.00068

Measured 9d ago against content hash b312679611a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

atelier-pipeline AGENTS.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 9d 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.

AGENTS.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Atelier Pipeline

A Cursor plugin providing multi-agent orchestration with quality gates, continuous QA, and persistent institutional memory (Atelier Brain).

Tech Stack

  • Hooks/Enforcement: Bash shell scripts (PreToolUse hooks)
  • Brain MCP Server: Node.js (server.mjs), PostgreSQL with pgvector and ltree extensions
  • Agent System: Markdown persona files, slash commands, orchestration rules
  • Plugin System: Cursor plugin format (.cursor-plugin/plugin.json)

Test Commands

  • echo "no test suite configured" -- full test suite (pending ADR-0003 Step 6)
  • echo "no linter configured" -- linter
  • echo "no typecheck configured" -- type checker

Source Structure

source/          # Template files -- copied to target projects by /pipeline-setup
  rules/         # Eva persona, orchestration rules (always-loaded by Cursor)
  agents/        # Subagent personas (9 agents)
  commands/      # Slash command definitions (7 commands)
  references/    # Quality framework, retro lessons, invocation templates, operations, agent preamble, QA checks, branch/MR mode
  hooks/         # Enforcement hook scripts (3 scripts + 1 config)
  pipeline/      # Pipeline state file templates (5 files)
  variants/      # Strategy variant templates (branching lifecycle)
brain/           # Atelier Brain MCP server (Node.js + PostgreSQL)
skills/          # Plugin skills (pipeline-setup, brain-setup, brain-hydrate, pipeline-overview)
.cursor/         # Installed pipeline files (this project eats its own cooking)
docs/            # User guide, technical reference, ADRs, pipeline state
scripts/         # Plugin lifecycle scripts (update checks)

Key Conventions

  • Roz-first TDD: Roz writes test assertions before Colby builds. Colby never modifies Roz's assertions.
  • Eva never writes code: Eva orchestrates and routes. Colby implements. Ellis commits.
  • Dual tree: source/ contains templates with {placeholders}. .cursor/ contains installed copies with literal values. Both must stay in sync within their respective contexts.
  • ADR immutability: ADRs are never updated in place. New ADRs supersede old ones.
  • Mechanical enforcement: PreToolUse hooks block agents from writing outside their designated paths. Behavioral guidance is backed by shell-script enforcement.
  • Living artifacts: Specs and UX docs are updated at pipeline end. Pipeline state files track session recovery.
  • Shared preamble: Agent personas reference agent-preamble.md for shared DoR/DoD, retro, and brain protocols. Domain-specific behavior stays in persona files.
  • Cross-layer wiring: Cal designs vertical slices (producer + consumer per step). Colby documents contract shapes. Roz and Poirot verify wiring. Orphan endpoints are blockers.

Read the full file on GitHub · 50 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. 9d ago First seen · 50 lines · 683 tokens per session scan A b312679611a0

Subscribe to this mod's changes

atelier-pipeline AGENTS.md is an instructions file published in the GitHub repository robertsfeir/atelier-pipeline (25 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 683 tokens to every session, about $0.0034 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.

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