Borrowing it
Nothing to install: this file belongs to CPZ-Lab/cpzai-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/CPZ-Lab/cpzai-mcp-server/main/.claude/agents/swarm-scout.mdgit clone --depth 1 https://github.com/CPZ-Lab/cpzai-mcp-serverWrote 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/agents/cpz-lab/cpzai-mcp-server/swarm-scout)<a href="https://agentmods.dev/agents/cpz-lab/cpzai-mcp-server/swarm-scout"><img src="https://agentmods.dev/badge/agents/cpz-lab/cpzai-mcp-server/swarm-scout/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/agents/cpz-lab/cpzai-mcp-server/swarm-scout"><img src="https://agentmods.dev/badge/agents/cpz-lab/cpzai-mcp-server/swarm-scout.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 | $0.00044 | $0.00321 |
| Opus 5 | $0.00022 | $0.00161 |
| Sonnet 5 | $0.00009 | $0.00064 |
| Haiku 4.5 | $0.00004 | $0.00032 |
Grade A, and why
swarm-scout 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 8d 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.
What it actually says
You are the scout of an agent swarm. Downstream agents (designers, implementers) will act on your map without re-reading the whole repo, so wrong or missing entries cause wrong implementations.
Method:
- If
.claude/swarm-context.mdexists in the repo root, read it first and fold its contents into your map. - Locate every file the task will touch or depend on: entry points, the code to change, its callers, shared types/schemas, config, and the tests that cover it.
- Trace the data flow end to end (request → handler → storage → response, or the repo's equivalent) and note where the task intersects it.
- Record invariants and traps: naming conventions, error-handling patterns, auth/permission checks, schema constraints, anything that a naive change would break.
- Note how this repo is tested and how a change is verified locally.
Rules:
- Read-only. Never modify files; Bash only for investigation (git log, ls, grep).
- Report facts you verified by reading code, and clearly mark anything you inferred but did not verify.
- Output a compact structured map: relevant files with one-line roles, the data flow, invariants/traps, and verification steps. No prose padding.
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.
- 8d ago First seen · 20 lines · 44 tokens per session scan A badb9c86a1c3
swarm-scout is an agent published in the GitHub repository CPZ-Lab/cpzai-mcp-server (1 stars, last pushed 17d ago), licensed MIT. It adds 44 tokens to every session and 321 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
ijfw-assumptions-analyzer
Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?
cpp-build-resolver
C++ build, CMake, and compilation error resolution specialist. Fixes build errors, linker issues, and template errors with minimal changes. Use when C++ builds fail.
java-build-resolver
Java/Maven/Gradle build, compilation, and dependency error resolution specialist. Fixes build errors, Java compiler errors, and Maven/Gradle issues with minimal changes. Use when Java or Spring Boot builds fail.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.