Auto-activates REVIEWER (Senior Engineer) and DEVELOPER (Mid-level Engineer) agents on every Claude Code session. Runs an automated review loop with configurable max iterations. Includes security, architectural, system-design, clean-code, and senior-architect skills.
Plugin patchduo from marketplace patchduo in Tushar-Banswal/patchDuo. Commands read from the repo's manifest — 19 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
architecturalArchitectural review checklist for the REVIEWER. Activate when evaluating module boundaries, dependency direction, coupling, cohesion, and design pattern usage. Apply to any change that touches module interfaces, adds new abstractions, or crosses layer boundaries.
clean-codeApplies Clean Code principles when writing or reviewing any source file. The DEVELOPER activates this skill after every implementation to self-review all changed files before reporting back to the REVIEWER.
developerExplicitly delegate to the PatchDuo DEVELOPER agent using the tracked workflow.
reviewerExplicitly delegate to the PatchDuo REVIEWER agent using the tracked workflow.
securitySecurity review checklist for the REVIEWER. Activate when auditing code involving user input, authentication, session management, data storage, API calls, file system access, or any external service interaction. A single blocking issue found here must result in REJECTED.
senior-architectSenior Architect meta-framework for the REVIEWER. Activate as the holistic decision lens for any major change, new pattern, or cross-cutting concern. Guides trade-off analysis, farsighted thinking, blast-radius assessment, and the final APPROVE / REJECT call after all other review skills have run.
system-designSystem design review lens for the REVIEWER. Activate when evaluating changes that touch scalability, service interactions, data flows, caching strategies, background jobs, or distributed system concerns. Also apply to any database query changes or API contract modifications.
developerMid-level DEVELOPER agent. Invoke AFTER the REVIEWER has produced an implementation brief. Implements changes with a minimum footprint, strictly following project customs from CLAUDE.md / AGENTS.md. Reads official documentation before using unfamiliar APIs. Asks the user when any implementation deta
reviewerSenior Engineer REVIEWER. Invoke first for any new task — scans CLAUDE.md, AGENTS.md, git log, and directory structure, clarifies requirements, and writes a precise implementation brief for the DEVELOPER. After implementation, audits all changes for security, architecture, and project-rule complianc
node "${CLAUDE_PLUGIN_ROOT}/hooks/patchduo-activate.js"
Multi-agent orchestration system with 51 specialized agents for development workflows, code quality, deployment, research, games, and more. Includes orchestrators for checkpoint, deploy, quality, fullstack, research, games, corpus, web, and python workflows.
51 agents
Autonomous development methodology for Claude Code
11 commands · 22 agents
Disciplined Agentic Engineering (DAE) — methodology kit for Claude Code. Skills that implement the DAE pipeline: feature intake, AC discovery, spec writing, planning, implementation, verification, hardening.
25 skills · 6 agents
The most comprehensive Claude Code extension for PHP developers. 26 commands, 68 agents, 283 skills.
200 skills · 26 commands · 68 agents · hooks
Native Meta-Harness — run a harness-optimization loop natively: propose scaffolding variants around a fixed model, score each with a $0 deterministic test, keep the Pareto-best, loop.
1 skill
pair-review app integration — Open PRs and local changes in the pair-review web UI, run server-side AI analysis, and address review feedback. Includes MCP server.
6 skills · 1 MCP server
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.