Plugin Claude Code
Marketplace for AI-to-AI peer review plugins. Multiple perspectives catch more issues than one.
33 26d ago A
tokens not measured
original MIT
Instructions file
Instructions for jcputney/agent-peer-review, covering project conventions, architecture, file organization, writing guidelines and prompts and skills.
33 26d ago A 407 tokens
original MIT
Plugin Claude Code
Symmetric two-AI peer review using OpenAI Codex CLI. Both AIs review independently in a blind pass, then debate per-issue with terminal states until convergence. Catches significantly more issues than single-pass validation.
33 26d ago A
tokens not measured
original MIT
Agent
Use this agent to run peer review validation with Codex CLI. Dispatches to a separate context to keep the main conversation clean. Returns synthesized peer review results.
33 26d ago B 38 tokens
original MIT
Command
Trigger peer review validation with Codex CLI. Default is symmetric blind-pass debate. Use --mode classic for legacy single-pass validation, init to set up Codex profiles, or pass a question for broad technical validation.
33 26d ago B 48 tokens
original MIT
SessionStart
06Hook
Runs when a session starts, executing peer-review-reminder.sh via bash. From jcputney/agent-peer-review.
33 26d ago A
tokens not measured
original MIT
Hook
Runs when you submit a prompt, before the agent sees it, executing user-prompt-check.sh via bash. From jcputney/agent-peer-review.
33 26d ago A
tokens not measured
original MIT
Stop
08Hook
Runs when the agent finishes a response, executing stop-peer-review-check.sh via bash. From jcputney/agent-peer-review.
33 26d ago A
tokens not measured
copy · 59% MIT
PreToolUse
09Hook
Runs before the agent uses a tool for ExitPlanMode, Task and Write tool calls, executing plan-peer-review-check.sh, task-peer-review-check.sh and write-peer-review-check.sh via bash (3 commands). From jcputney/agent-peer-review.
33 26d ago A
tokens not measured
original MIT
Skill Claude CodeCodex
This skill should be invoked BEFORE presenting implementation plans, architecture recommendations, code review findings, or answers to broad technical questions. Use proactively when about to "recommend", "suggest", "propose", "design", "plan", or answer "how should", "what's the best way", "which approach". MANDATORY…
33 26d ago B 84 tokens
original MIT