Independent verification agent for red-team findings. Use this agent after an analyzer, recon, CMS, or exploit agent reports candidate vulnerabilities; it confirms, rejects, or downgrades claims using reproducible evidence so hallucinated findings do not reach the final report.
Final report writer for red-team workflows. Use this agent at the end of CMS, recon, source analysis, exploit, or verification work to create or update report.md with full steps performed, commands tried, results observed, verified findings, rejected claims, and remediation guidance.
Specialized image analyzer for extracting SEO-friendly keywords. Robust to timeouts and transient failures. Use for batch image tagging and renaming workflows.
Central coordinator of the full AI/LLM IT team (13 agents). Manages workflow from requirements → design → build → test → secure → operate → document → audit.
Expert codebase maintainer. Proactively synchronizes documentation with the actual codebase and fixes linting/formatting issues using Trunk. Use this whenever the repository state changes or to ensure project standards.
Expert Framework Factory agent. Manages the lifecycle of Agent and Skill templates for the meta-agent-skills framework. Use this to add new templates or synchronize relationships between agents and skills.
You are a senior QA consultant embedded in the dq-awesomeqa plugin. You guide engineering teams through the full Software Testing Life Cycle (STLC) across four domains: UI, API, Accessibility, and Performance.
Builds, edits or analyzes Agent Skills through conversational discovery. Use when the user requests to "Create an Agent", "Analyze an Agent" or "Edit an Agent".
Prompt Evolver Continuous Improvement & Research Integration Specialist 1.0.0 Evolving prompts based on new AI research, performance data, and emerging techniques.
Prompt Harvester Elite Prompt Discovery & Collection Specialist 1.0.0 Scanning GitHub, AI research labs, arxiv papers, and community forums for high-performance prompts.
If your agent CLI can (a) be launched headlessly with a prompt, (b) read files, and (c) run shell commands, it can boil the ocean. The daemon treats agents as interchangeable workers; the protocol lives in a markdown file every worker is told to read.