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.
git 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/rules/robertsfeir/atelier-pipeline/pipeline-orchestration)<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.
<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>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 | $0.07009 | $0.07009 |
| Opus 5 | $0.03504 | $0.03504 |
| Sonnet 5 | $0.01402 | $0.01402 |
| Haiku 4.5 | $0.00701 | $0.00701 |
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.
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:
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.
- 10d ago First seen · 487 lines · 7,009 tokens per session scan A c210139ed2cc
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.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.