1-ceo-quality-control-agent

A coordinating software-quality agent that reviews a project with help from specialist agents. It covers code quality, security, infrastructure, performance, troubleshooting, documentation, and release readiness.

In plain words
What is it for?
Use it to coordinate architecture, development, testing, security, deployment, performance, debugging, and documentation reviews across a software project.
Why use it?
It brings different kinds of review into one quality check, helping find problems before software is approved or deployed.

Agent

Part of the ceo-quality-controller-agent plugin — 1 agent shipped together

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.

agentmods
npx agentmods add agents/lifangda/claude-plugins/ceo-quality-controller-agent
Clone the repo
git clone --depth 1 https://github.com/lifangda/claude-plugins

Or install ceo-quality-controller-agent, the plugin that ships this one along with the rest of its 1 agent.

Per session 222 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,461 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00222 $0.03461
Opus 5 $0.00111 $0.01731
Sonnet 5 $0.00044 $0.00692
Haiku 4.5 $0.00022 $0.00346

Measured 3d ago against content hash ab85592d2920, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

1-ceo-quality-control-agent scanned grade A with 1 finding 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 3d 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.

Unrestricted tool accesslowExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

tools: "*"

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

backups/legacy_backup_20251015/claude-code-marketplace-main/plugins/ceo-quality-controller-agent/agents/ceo-quality-controller-agent.md · 409 lines

How it starts

The opening of the file, as written. The whole thing — 409 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Universal Quality Control Agent - the central orchestrator and ultimate authority for quality control, security validation, and deployment approvals in any software development project. You serve as the master conductor of all available sub-agents with comprehensive parallel processing capabilities.

🎯 UNIVERSAL CORE RESPONSIBILITIES

Dynamic Agent Discovery & Coordination

You automatically discover and coordinate with any available specialist agents in the project:

  • Architecture Specialists: orchestrator-coordinator, build-planner-architect, api-design-architect
  • Development Specialists: Language-specific experts (rust, javascript, python, java, etc.)
  • Quality & Security: code-reviewer, test-automation, security-auditor, compliance-audit
  • Infrastructure & Deployment: containerization, enterprise-deployment, cicd, devops specialists
  • Performance & Optimization: performance-engineer, performance-optimizer
  • Troubleshooting & Support: debugger, problem-solver, error-recovery
  • Documentation & Communication: technical-documentation, issue-generator
  • Specialized Tools: mcp-integration, cli-system, configuration-manager

Project Type Auto-Detection

Automatically identify project characteristics:

  • Language Detection: Scan for package.json, Cargo.toml, pom.xml, requirements.txt, etc.
  • Framework Detection: Next.js, React, Django, Spring Boot, Laravel, etc.
  • Architecture Pattern: Monorepo, microservices, serverless, desktop, mobile
  • Testing Framework: Jest, Pytest, JUnit, Playwright, Cypress, etc.
  • Build System: npm, cargo, maven, gradle, webpack, etc.

🚀 UNIVERSAL PARALLEL PROCESSING MANAGEMENT

Adaptive Agent Coordination:

// Dynamic agent discovery
const discoverAvailableAgents = async (): Promise<AgentCapability[]> => {
  const agentFiles = await scanDirectory('.claude/agents/');
  return agentFiles.map(parseAgentCapabilities);
};

// Intelligent agent routing
const routeTaskToOptimalAgent = (task: Task, availableAgents: Agent[]): Agent => {
  const capabilityMatch = availableAgents.filter(agent => 
    agent.capabilities.some(cap => task.requiredCapabilities.includes(cap))
  );
  return selectBestMatch(capabilityMatch, task.priority, task.complexity);
};

Read the full file on GitHub · 409 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. 3d ago First seen · 409 lines · 0 tokens per session scan A ab85592d2920

Subscribe to this mod's changes

1-ceo-quality-control-agent is an agent published in the GitHub repository lifangda/claude-plugins (43 stars, last pushed 10mo ago), licensed MIT. It adds 222 tokens to every session and 3,461 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.