agent-discovery

agent-discovery is a cursor rule for Cursor from robertsfeir/atelier-pipeline. It costs 641 tokens per session, scanned A, original, Apache-2.0.

A routing rule that lets an agent discover additional custom agents by scanning a project's .cursor/agents folder. It compares each agent with a fixed list of core agents and reports any extra ones without replacing the core routing.

In plain words
What is it for?
Use it when starting a session that may contain custom Cursor agents, checking which agents are available, handling discovery errors, or detecting conflicts between discovered and core agents.
Why use it?
It keeps custom agents available while preserving the main agent assignments. It also defines what to do when discovery fails and how to detect conflicts or save routing preferences.

Cursor rule for Cursor

Written for Cursor: a Cursor plugin manifest.

Good fit Use it when starting a session that may contain custom Cursor agents, checking which agents are available, handling discovery errors, or detecting conflicts between discovered and core agents.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/robertsfeir/atelier-pipeline/agent-discovery
Install

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.

Clone the repo
git clone --depth 1 https://github.com/robertsfeir/atelier-pipeline

Made for: Cursor.

Wrote 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.

agentmods badge for agent-discovery

README.md
[![agentmods](https://agentmods.dev/badge/rules/robertsfeir/atelier-pipeline/agent-discovery.svg)](https://agentmods.dev/rules/robertsfeir/atelier-pipeline/agent-discovery)
Your own site
<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>
Per session 641 This file is loaded in full into every session.
When invoked 641 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 7d ago against content hash bd8032233fec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

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.

.cursor-plugin/rules/agent-discovery.mdc · 63 lines

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

  1. Scan: Run Glob(".cursor/agents/*.md") to list all agent files.
  2. Read frontmatter: For each file, read the YAML frontmatter name field.
  3. Compare: If the name does not match any core agent constant, it is a discovered agent. Read its description field.
  4. Announce: "Discovered N custom agent(s): [name] -- [description]." If zero non-core agents found, no announcement (or "No custom agents found.").
  5. 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):

  1. Eva announces the conflict: "This could go to [core agent] (core) or [discovered agent] (custom). Which do you prefer for [intent]?"
  2. Eva asks the user once per (intent, agent) pair per session.
  3. The user's choice is recorded (see Brain Persistence below).
  4. On subsequent messages with the same intent pattern, Eva uses the recorded preference without re-asking.
  5. Discovered agents with no description overlap are available only via explicit name mention (e.g., "ask [agent-name] about this").

Read the full file on GitHub · 63 lines

Changes

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.

  1. 7d ago First seen · 63 lines · 641 tokens per session scan A bd8032233fec

Subscribe to this mod's changes

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.