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/agent-discovery)<a href="https://agentmods.dev/rules/robertsfeir/atelier-pipeline/agent-discovery"><img src="https://agentmods.dev/badge/rules/robertsfeir/atelier-pipeline/agent-discovery.svg" alt="Measured on agentmods" 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 | $0.00641 | $0.00641 |
| Opus 5 | $0.00320 | $0.00320 |
| Sonnet 5 | $0.00128 | $0.00128 |
| Haiku 4.5 | $0.00064 | $0.00064 |
Grade A, and why
agent-discovery 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 7d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Discovery
Eva discovers custom agents at session boot by scanning .cursor/agents/ for
non-core persona files. Discovered agents are additive only -- they never
replace core agent routing.
Core Agent Constant
The following 14 agents are hardcoded core agents. Any .md file in
.cursor/agents/ whose YAML frontmatter name field does not match one of
these names is a discovered agent:
sarah, colby, ellis, agatha, robert, robert-spec, sable, sable-ux, investigator, distillator, sentinel, sherlock
Discovery Protocol
- Scan: Run
Glob(".cursor/agents/*.md")to list all agent files. - Read frontmatter: For each file, read the YAML frontmatter
namefield. - Compare: If the
namedoes not match any core agent constant, it is a discovered agent. Read itsdescriptionfield. - Announce: "Discovered N custom agent(s): [name] -- [description]." If zero non-core agents found, no announcement (or "No custom agents found.").
- Error handling: If the scan fails (Glob error, file read error), log: "Agent discovery scan failed: [reason]. Proceeding with core agents only." Never block session boot on a discovery error.
Conflict Detection
When Eva detects a discovered agent whose description overlaps with a core agent's domain (same intent category in the auto-routing table):
- Eva announces the conflict: "This could go to [core agent] (core) or [discovered agent] (custom). Which do you prefer for [intent]?"
- Eva asks the user once per (intent, agent) pair per session.
- The user's choice is recorded (see Brain Persistence below).
- On subsequent messages with the same intent pattern, Eva uses the recorded preference without re-asking.
- Discovered agents with no description overlap are available only via explicit name mention (e.g., "ask [agent-name] about this").
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.
- 7d ago First seen · 63 lines · 641 tokens per session scan A bd8032233fec
agent-discovery is a cursor rule published in the GitHub repository robertsfeir/atelier-pipeline (25 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 641 tokens to every session, about $0.0032 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
archcore-context
Archcore knowledge base context — document types, MCP tools, and conventions for working with .archcore/ documents.
memento-conventions
Memento OS — reasoning artifact conventions for persistent AI memory.
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.