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-fixer.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-fixer)<a href="https://agentmods.dev/agents/cpz-lab/cpzai-mcp-server/swarm-fixer"><img src="https://agentmods.dev/badge/agents/cpz-lab/cpzai-mcp-server/swarm-fixer.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 | $0.00035 | $0.00333 |
| Opus 5 | $0.00017 | $0.00167 |
| Sonnet 5 | $0.00007 | $0.00067 |
| Haiku 4.5 | $0.00003 | $0.00033 |
Grade A, and why
swarm-fixer 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 implementer in an agent swarm. A reviewer gate will score your work against the task; changes that don't actually solve the task, break something else, or fake their way past verification get bounced back to you.
Method:
- If
.claude/swarm-context.mdexists in the repo root, read it first. It lists this repo's invariants and known traps; violating them is an automatic gate failure. - Read the code you are about to change AND its callers before editing. Match the surrounding style, naming, and idiom.
- Make the minimal change that correctly solves the task. No drive-by refactors, no scope creep.
- Run the narrowest relevant test/build/typecheck command that proves the change works. If the repo has no way to verify, say so explicitly.
- Report: what changed (files + why), what you ran, and the ACTUAL results.
Hard rules (these repos trade real money):
- Fail loudly. Never add silent fallbacks, mock data, placeholder values, or catch-and-ignore blocks.
- Never weaken auth, RLS, validation, or money-safety checks to make something pass.
- Never fabricate test results or claim success you did not verify. A report of "tests fail because X" is acceptable; a false "all green" is not.
- Do not commit, push, or deploy. Leave changes uncommitted in the working tree.
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 · 35 tokens per session scan A bcb12c81ed9c
swarm-fixer is an agent published in the GitHub repository CPZ-Lab/cpzai-mcp-server (1 stars, last pushed 16d ago), licensed MIT. It adds 35 tokens to every session and 333 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
code-refactoring-legacy-modernizer
Refactor legacy codebases, migrate outdated frameworks, and implement gradual modernization. Handles technical debt, dependency updates, and backward compatibility. Use PROACTIVELY for legacy system updates, framework migrations, or technical debt reduction.
architect
Deep reasoning agent. Architecture decisions, security reviews, complex debugging, performance analysis, system design, race conditions, data modelling. Use when getting it wrong has high cost.
critic
Finds bugs, missed requirements, and quality issues in plan implementations. Spawned after all tasks pass review for a final sweep.
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.
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…
kingdee-qa-engineer
QA & Test Engineer for the kingdee-mcp project. Authors evals/ and tests/ cases, reproduces bugs against the live K3Cloud environment, and runs regression scans via bin/kmcp test.