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-operations)<a href="https://agentmods.dev/rules/robertsfeir/atelier-pipeline/pipeline-operations"><img src="https://agentmods.dev/badge/rules/robertsfeir/atelier-pipeline/pipeline-operations/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-operations"><img src="https://agentmods.dev/badge/rules/robertsfeir/atelier-pipeline/pipeline-operations.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 | $0.08408 | $0.08408 |
| Opus 5 | $0.04204 | $0.04204 |
| Sonnet 5 | $0.01682 | $0.01682 |
| Haiku 4.5 | $0.00841 | $0.00841 |
Grade A, and why
pipeline-operations 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 — 679 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pipeline Operations Reference
Eva reads this file at pipeline start for detailed operational procedures.
Invocation Format
All subagent invocations use XML tags. Eva constructs prompts with <task>,
<brain-context>, <context>, <hypotheses>, <read>, <warn>,
<constraints>, and <output> tags. See {config_dir}/references/xml-prompt-schema.md
and {config_dir}/references/invocation-templates.md for the full tag vocabulary
and per-agent examples.
Brain Context Prefetch
Eva prefetches brain context before invoking agents. Reinforced by prompt-brain-prefetch.sh PreToolUse hook.
- Calls
agent_searchwith a query derived from the feature area - Injects results into the
<brain-context>tag in the invocation prompt - Captures are mechanically gated (ADR-0053): a SubagentStop hook marks
{pipeline_state_dir}/.pending-brain-capture.jsonfor allowlisted agents (sarah, colby, agatha, robert, robert-spec, sable, sable-ux, ellis); a PreToolUse hook onAgentblocks Eva's next invocation until she callsagent_capturewith curated content; PostToolUse onagent_captureclears the marker. Eva curates -- the brain stays a curated knowledge store, not a transcript dump.
When the brain is unreachable, Eva touches
{pipeline_state_dir}/.brain-unavailable; the gate honors the sentinel and
passes through. Eva clears the sentinel on the next successful
atelier_stats probe.
Continuous QA (Wave-Level Poirot + Colby)
Sarah's ADR steps become work units grouped into waves. Colby writes tests when Sarah names a failure mode per wave, Colby implements per unit, QA runs per wave.
Test authoring (Colby, when ADR names a failure mode): Colby writes tests only when Sarah's ADR step explicitly names a failure mode or acceptance criterion that is verifiable in code. Colby does not write structural pinning tests. Tests are written as part of the build unit -- not in a separate pre-build pass.
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 · 679 lines · 8,408 tokens per session scan A 336188e554b4
pipeline-operations is a cursor rule published in the GitHub repository robertsfeir/atelier-pipeline (25 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 8,408 tokens to every session, about $0.0420 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-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
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.