cpzai-mcp-server: Agent for Claude Code

.claude/agents/swarm-finder.md

swarm-finder is an agent for Claude Code from CPZ-Lab/cpzai-mcp-server. It costs 36 tokens per session (357 once invoked), scanned A, original, MIT.

A read-only defect-finding agent for workflows where several agents inspect different parts or aspects of a codebase. It reports only defects supported by code evidence and includes the failure scenario.

In plain words
What is it for?
Investigating assigned areas of a repository, tracing code paths, finding reproducible defects, and returning structured findings without editing files.
Why use it?
It helps teams avoid speculative bug reports by requiring each finding to show where the problem occurs and how it can fail.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is CPZ-Lab/cpzai-mcp-server's own configuration. It tells Claude Code how to work on cpzai-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cpzai-mcp-server configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/CPZ-Lab/cpzai-mcp-server/main/.claude/agents/swarm-finder.md
Clone the repo
git clone --depth 1 https://github.com/CPZ-Lab/cpzai-mcp-server

Made for: Claude Code.

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 swarm-finder

README.md
[![agentmods](https://agentmods.dev/badge/agents/cpz-lab/cpzai-mcp-server/swarm-finder/github.svg)](https://agentmods.dev/agents/cpz-lab/cpzai-mcp-server/swarm-finder)
Your own site
<a href="https://agentmods.dev/agents/cpz-lab/cpzai-mcp-server/swarm-finder"><img src="https://agentmods.dev/badge/agents/cpz-lab/cpzai-mcp-server/swarm-finder/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.

agentmods 80×15 button for swarm-finder

Your own site · 80×15
<a href="https://agentmods.dev/agents/cpz-lab/cpzai-mcp-server/swarm-finder"><img src="https://agentmods.dev/badge/agents/cpz-lab/cpzai-mcp-server/swarm-finder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 357 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00036 $0.00357
Opus 5 $0.00018 $0.00179
Sonnet 5 $0.00007 $0.00071
Haiku 4.5 $0.00004 $0.00036

Measured 9d ago against content hash 19a5a89a0557, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

swarm-finder 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 9d 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.

.claude/agents/swarm-finder.md · 21 lines

What it actually says

You are a defect finder in an agent swarm. Many finders run in parallel, each with a different lens; an adversarial verification panel will try to refute everything you report. Your score is confirmed findings, and false positives cost you, so report only what you can prove.

Method:

  1. If .claude/swarm-context.md exists in the repo root, read it first. It lists this repo's stack, invariants, and known traps.
  2. Hunt strictly within your assigned lens and scope. Depth beats breadth: trace real code paths end to end rather than skimming many files.
  3. A finding must be evidenced by code you actually read. Cite the file, the line, and the exact mechanism of failure.
  4. Every finding needs a concrete failure scenario: specific inputs or state that lead to wrong output, data loss, security exposure, or a crash.
  5. Do not re-report anything on the already-known list you are given.

Rules:

  • No style nits, no hypotheticals, no "could be cleaner", no TODO archaeology.
  • Bash is for read-only investigation only (git log, ls, grep, reading configs). Never modify files. Never run anything with side effects.
  • Severity: critical = money loss, data loss, or security breach; high = user-visible breakage; medium = incorrect behavior with a workaround; low = latent trap.
  • Your final output is consumed by a machine. Return findings exactly in the requested structure, nothing else.
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. 9d ago First seen · 21 lines · 36 tokens per session scan A 19a5a89a0557

Subscribe to this mod's changes

swarm-finder is an agent published in the GitHub repository CPZ-Lab/cpzai-mcp-server (1 stars, last pushed 18d ago), licensed MIT. It adds 36 tokens to every session and 357 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.

Related

Other agents, from other repositories

jd-fix-agent

You are a judgment-day surgical fix agent. Execute the fix instructions provided in the delegate prompt exactly.

Gentleman-Programming/gentle-ai · 35 tokens

bug-hunter

Use this agent when reviewing local code changes or in the pull request to identify bugs and critical issues through systematic root cause analysis. This agent should be invoked proactively after completing a logical chunk of work.

NeoLabHQ/context-engineering-kit · 43 tokens

fec-performance-optimizer

Front-end performance analysis and optimization specialization: Core Web Vitals, packaging volume, runtime and rendering, network and cache, memory leak troubleshooting; can cooperate with Lighthouse, Bundle analysis and Profiler. Use it when users mention page slowness, lag, first screen, package size, poor…

bovinphang/frontend-craft · 0 tokens

fec-ui-checker

Use this subagent to troubleshoot visual defects, layout confusion, CSS issues, responsive exceptions, and inconsistencies between interaction and design in the front-end UI, and save the report as a Markdown file. Supports obtaining design data from Figma, Sketch, MasterGo, Pixso, Moko, and Mock, compares the design…

bovinphang/frontend-craft · 0 tokens

silent-failure-hunter

Review code for silent failures, swallowed errors, bad fallbacks, and missing error propagation.

Fmarzochi/EGC · 24 tokens

code-reviewer-bug

name: code-reviewer-bug description: Specialized code reviewer for bug patterns — null safety, race conditions, resource leaks, logic and error-handling defects. Returns scored findings (severity × impact × confidence). skills: code-review model: inherit.

zxpmail/ReqForge · 0 tokens