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/routing-detail)<a href="https://agentmods.dev/rules/robertsfeir/atelier-pipeline/routing-detail"><img src="https://agentmods.dev/badge/rules/robertsfeir/atelier-pipeline/routing-detail/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/routing-detail"><img src="https://agentmods.dev/badge/rules/robertsfeir/atelier-pipeline/routing-detail.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 | $0.01045 | $0.01045 |
| Opus 5 | $0.00522 | $0.00522 |
| Sonnet 5 | $0.00209 | $0.00209 |
| Haiku 4.5 | $0.00104 | $0.00104 |
Grade A, and why
routing-detail 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AUTO-ROUTING -- Detail Matrix
Loaded by Eva when she encounters an ambiguous routing case outside an
active pipeline, when a discovered agent appears to overlap a core agent,
or when smart-context detection needs to run against the full artifact
table. The inline summary in .cursor/rules/agent-system.md
<routing id="auto-routing"> covers the common cases and points here for
edge cases.
Intent Detection
| If the user... | Route to | Type |
|---|---|---|
| Describes new idea, feature concept, "what if we..." | robert-spec | subagent |
| Discusses UI, UX, user flows, wireframes, design patterns | sable-ux | subagent |
| Says "review this ADR", "plan this", "how should we architect..." | Sarah | skill |
| References feature spec without ADR | Sarah | skill |
| Says "plan the docs", "what docs do we need", "documentation plan" | Agatha (doc planning) | skill |
| Says "mockup", "prototype", "let me see it" | Scout fan-out → Colby (mockup mode) [<colby-context>] |
subagent |
| Says "scan the codebase", "investigate paths", "map all X", "review the whole codebase" (read-only survey, no existing ADR or bug report) | Explore+haiku scouts → Sonnet reviewer | subagent |
| Sarah just finished ADR with test spec tables | Scout fan-out → Poirot (test spec review) [<qa-evidence>] |
subagent |
| Poirot approved test spec, ready to build | Scout fan-out → Colby + Agatha (parallel) [<colby-context>] |
subagent |
| Says "build this", "implement", "code this" with existing plan | Scout fan-out → Colby + Agatha (parallel) [<colby-context>] |
subagent |
| Says "run tests", "check this", "QA", "validate" | Scout fan-out → Poirot [<qa-evidence>] |
subagent |
| Says "commit", "push", "ship it", "we're done" | Ellis | subagent |
| Says "write docs", "document this", "update the docs" | Agatha (writing) | subagent |
| Asks about infra, CI/CD, deployment, monitoring | Eva (devops) | skill |
| Reports a bug, error, stack trace, "this is broken" | Eva conducts 6-question intake → Sherlock (diagnose, own context, no scouts) → hard pause | subagent |
| Says "go", "next", "continue" after a phase completes | Eva routes to next | (see flow) |
| Says "follow the flow", "pipeline", "run the full pipeline" | Eva (orchestrator) | skill |
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 · 66 lines · 1,045 tokens per session scan A d21af3b4a93a
routing-detail is a cursor rule published in the GitHub repository robertsfeir/atelier-pipeline (25 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,045 tokens to every session, about $0.0052 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.