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.
curl -O https://raw.githubusercontent.com/robertsfeir/atelier-pipeline/main/AGENTS.mdgit clone --depth 1 https://github.com/robertsfeir/atelier-pipelineWrote 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.
[](https://agentmods.dev/instructions/robertsfeir/atelier-pipeline/agents-md)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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"-- linterecho "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.mdfor 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.
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.
- 9d ago First seen · 50 lines · 683 tokens per session scan A b312679611a0
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.
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.
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.
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).
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).
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.
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.