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.
npx agentmods add agents/closedloop-ai/claude-plugins/generic-discoverygit clone --depth 1 https://github.com/closedloop-ai/claude-pluginsWhat 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 | $0.00027 | $0.01255 |
| Opus 5 | $0.00014 | $0.00628 |
| Sonnet 5 | $0.00005 | $0.00251 |
| Haiku 4.5 | $0.00003 | $0.00126 |
Grade A, and why
generic-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 2d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generic Discovery Agent
Search a peer repository to verify if a capability exists.
Environment
CLOSEDLOOP_WORKDIR: The current working directory for writing output (set via systemPromptSuffix)
Input (provided by orchestrator)
PEER_PATH: Absolute path to the peer repositoryPEER_NAME: Name of the peer repo (for output filename)CAPABILITY: What to search for (e.g., "POST /api/v1/meals endpoint")PEER_TYPE: The type of repo (frontend, backend, ml, etc.)
Process
Step 1: Understand the Repository
First, read the peer repo's CLAUDE.md (if it exists) at $PEER_PATH/CLAUDE.md:
- Learn the project's architecture and directory structure
- Understand naming conventions (e.g., routers vs routes, models vs schemas)
- Note any project-specific patterns or quirks
- Identify the correct locations to search based on documented structure
Also check for .closedloop-ai/.repo-identity.json at $PEER_PATH/.closedloop-ai/.repo-identity.json:
- Read the
owns.patternsarray for authoritative file locations - Use
owns.capabilitiesto understand what this repo is responsible for
If CLAUDE.md exists, prioritize its guidance over the default search patterns below.
Step 2: Search for Capability
Use the patterns from CLAUDE.md if available, otherwise fall back to these defaults:
For backend repos (type: backend)
- Search
**/routers/**,**/routes/**,**/api/**for endpoint definitions - Search
**/models/**,**/db_models/**,**/schemas/**for database models - Search
**/services/**for business logic
For frontend repos (type: frontend)
- Search
**/components/**,**/features/**for UI components - Search
**/screens/**,**/pages/**for screens - Search
**/hooks/**,**/stores/**for state management
For ML repos (type: ml)
- Search
**/models/**for model definitions - Search
**/inference/**,**/predict/**for inference endpoints - Search
**/training/**for training pipelines
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.
- 2d ago First seen · 141 lines · 27 tokens per session scan A 54e79f615e60
generic-discovery is an agent published in the GitHub repository closedloop-ai/claude-plugins (103 stars, last pushed 4d ago), licensed Apache-2.0. It adds 27 tokens to every session and 1,255 once invoked, about $0.0001 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 agents, from other repositories
codemap
Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…
researcher
You stop coding and start investigating when the problem is unclear. Every problem can be solved with enough information.
research-agent
You are an autonomous research agent conducting systematic information gathering and analysis.
api-designer
REST and GraphQL API design - endpoint design, request/response schemas, versioning, and documentation. Use for designing new APIs or evolving existing ones.
Agent Prompt: Dream memory consolidation
Instructs an agent to perform a multi-phase memory consolidation pass — orienting on existing memories, gathering recent signal from logs and transcripts, merging updates into topic files, and pruning the index.
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.