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-phases)<a href="https://agentmods.dev/rules/robertsfeir/atelier-pipeline/pipeline-phases"><img src="https://agentmods.dev/badge/rules/robertsfeir/atelier-pipeline/pipeline-phases/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-phases"><img src="https://agentmods.dev/badge/rules/robertsfeir/atelier-pipeline/pipeline-phases.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 | $0.02526 | $0.02526 |
| Opus 5 | $0.01263 | $0.01263 |
| Sonnet 5 | $0.00505 | $0.00505 |
| Haiku 4.5 | $0.00253 | $0.00253 |
Grade A, and why
pipeline-phases 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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pipeline Phases Reference
JIT-loaded sections extracted from pipeline-orchestration.md. Eva loads this
file on demand per the triggers in that file's Loading Strategy table:
| Trigger | Protocol / Section |
|---|---|
| First state write | State File Descriptions |
| Pipeline sizing decision | Phase Sizing Rules |
| Pipeline sizing decision | Budget Estimate Gate |
| Session boot with concurrent stale state | Concurrent Session Detection |
| Debug flow entered | Investigation Discipline |
All anchor IDs below (<section id="...">, <gate id="...">,
<protocol id="...">) are preserved from the original orchestration file --
downstream references still resolve by ID.
Investigation Discipline
When Eva enters a debug flow, she creates (or resets)
docs/pipeline/investigation-ledger.md with the symptom and an empty
hypothesis table. Eva updates it after each investigation step.
Layer Escalation Protocol
Every investigation considers four system layers:
- Application -- state, components, routes, handlers, data access
- Transport -- HTTP headers, auth tokens, SSE/WebSocket, CORS, proxy
- Infrastructure -- containers, networking, DNS, TLS, load balancing
- Environment -- env vars, config files, secrets, feature flags
Threshold rule: 2 rejected hypotheses at the same layer -> Eva MUST investigate the next layer before proposing more hypotheses at the original layer.
Hypothesis Tracking
Before proposing a fix, Eva records each hypothesis in the investigation ledger with: the hypothesis, which layer it targets, what evidence was found, and whether it was confirmed or rejected. Eva re-reads the ledger before forming new hypotheses to avoid repetition.
Concurrent Session Detection
At session boot, if stale_context: true AND the stale state's phase is not
idle or complete, Eva HARD PAUSES and presents three options:
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 · 205 lines · 2,526 tokens per session scan A 1cd8139c10ed
pipeline-phases is a cursor rule published in the GitHub repository robertsfeir/atelier-pipeline (25 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 2,526 tokens to every session, about $0.0126 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.