pipeline-orchestration

pipeline-orchestration is a cursor rule for Claude Code, Cursor from robertsfeir/atelier-pipeline. It costs 7,009 tokens per session, scanned A, original, Apache-2.0.

A set of operating procedures for Eva, an automated pipeline coordinator that manages work through defined stages and state files.

In plain words
What is it for?
Use it to coordinate agents, manage pipeline state, load investigation guidance when needed, detect concurrent sessions, capture telemetry, and handle terminal transitions.
Why use it?
It keeps pipeline work consistent by enforcing required checks, recording decisions and outputs, and controlling when stages can proceed.

Cursor rule for Claude CodeCursor

Written for Claude Code and Cursor: SubagentStop hook event, but also a Cursor plugin manifest. Also seen: mentions CLAUDE.md; mentions subagents.

Good fit Use it to coordinate agents, manage pipeline state, load investigation guidance when needed, detect concurrent sessions, capture telemetry, and handle terminal transitions.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/robertsfeir/atelier-pipeline/pipeline-orchestration
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.

Clone the repo
git clone --depth 1 https://github.com/robertsfeir/atelier-pipeline

Made for: Claude Code, Cursor.

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 pipeline-orchestration

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

Your own site · 80×15
<a href="https://agentmods.dev/rules/robertsfeir/atelier-pipeline/pipeline-orchestration"><img src="https://agentmods.dev/badge/rules/robertsfeir/atelier-pipeline/pipeline-orchestration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 7,009 This file is loaded in full into every session.
When invoked 7,009 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 $0.07009 $0.07009
Opus 5 $0.03504 $0.03504
Sonnet 5 $0.01402 $0.01402
Haiku 4.5 $0.00701 $0.00701

Measured 10d ago against content hash c210139ed2cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

pipeline-orchestration 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.

.cursor-plugin/rules/pipeline-orchestration.mdc · 487 lines

How it starts

The opening of the file, as written. The whole thing — 487 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pipeline Orchestration -- Operational Procedures

Loads automatically when Eva reads {pipeline_state_dir}/ files. Contains ALWAYS-loaded content: mandatory gates, brain capture model, pipeline flow, agent standards, terminal transition. JIT sections load from sibling reference files on the triggers listed below.

Loading Strategy

ALWAYS sections live in this file: Brain Access, Mandatory Gates, Terminal Transition, Agent Output Masking, Subagent Invocation & DoR/DoD, Pipeline Flow, Agent Standards, CI Watch. JIT sections live in sibling references; Eva reads only the referenced file on the listed trigger.

JIT Section Trigger Location
Telemetry Capture (+ Darwin Auto-Trigger, Pattern Staleness, Dashboard Bridge) After first agent returns / pipeline end telemetry-metrics.md (<protocol id="telemetry-capture">)
Investigation Discipline Debug flow entered pipeline-phases.md (<protocol id="investigation">)
Concurrent Session Detection Session boot with stale active state pipeline-phases.md (<protocol id="concurrent-session-hard-pause">)
State File Descriptions First state write pipeline-phases.md (<section id="state-files">)
Phase Sizing Rules Pipeline sizing decision pipeline-phases.md (<section id="phase-sizing">)
Budget Estimate Gate Pipeline sizing decision pipeline-phases.md (<gate id="budget-estimate">)
Worktree-Per-Session Isolation Pipeline start (before Colby) / Ellis cleanup worktree-isolation.md (<protocol id="worktree-per-session">)

Brain Access (when brain is available)

When brain_available: true, Eva performs these brain operations at mechanical gates. Brain captures are gated mechanically by a three-hook loop (per ADR-0053); Eva is the curator.

Three-Hook Capture Gate (ADR-0053)

The brain-extractor agent no longer exists. Brain capture is enforced by three type: command hooks that form a closed loop around Eva's curation:

Read the full file on GitHub · 487 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 · 487 lines · 7,009 tokens per session scan A c210139ed2cc

Subscribe to this mod's changes

pipeline-orchestration is a cursor rule published in the GitHub repository robertsfeir/atelier-pipeline (25 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 7,009 tokens to every session, about $0.0350 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.