pair-review
01Plugin Claude Code
Plugin marketplace listing 3 plugins: pair-loop, code-critic, pair-review.
Plugin Claude Code
Plugin marketplace listing 3 plugins: pair-loop, code-critic, pair-review.
Settings file Claude Code
Agent settings configuring plansDirectory.
Skill Claude CodeCodex
Update the built-in model configurations for pair-review's AI providers. This skill guides you through checking each provider's CLI for available models, gathering recommendations, and updating the source code.
MCP server Claude CodeCodexCursor +2
MCP server "pair-review" as configured in in-the-loop-labs/pair-review. Runs bin/pair-review.js with node.
Skill Claude CodeCodex
Guidance for selecting models when performing code review with subtasks. Load this skill to enable intelligent model selection for review analysis — choosing faster models for simple tasks and deeper reasoning models for complex analysis.
Skill Claude CodeCodex
Dispatch a review task to 3 randomly-selected reasoning models in parallel for diverse perspectives, then merge all suggestions into a single result.
Instructions file CodexOpenCode
Instructions for in-the-loop-labs/pair-review, a project described as: AI assisted code review with a human in the loop.
Instructions file
Instructions for in-the-loop-labs/pair-review, covering pair-review project requirements, core value propositions, core architecture, key design principles and core workflow.
Plugin Claude Code
AI-powered code review analysis — Run three-level AI analysis directly in your coding agent. Works standalone, no server required.
Skill Claude CodeCodex
Perform AI-powered code review analysis by spawning parallel Task agents directly within the coding agent's context. Does not require the pair-review MCP server — works standalone. Runs Level 1 (diff isolation), Level 2 (file context), and Level 3 (codebase context) as parallel tasks, then orchestrates results into…
Plugin Claude Code
Agent-orchestrated review loop — implement, review with pair-review multi-model councils via the headless CLI, triage, fix, and repeat until a final review returns no blockers. MCP-independent.
Skill Claude CodeCodex
Drive an implement→review→fix loop with pair-review as the review oracle: run multi-model council reviews, triage the findings, apply fixes, and repeat with narrowing instructions until a final review returns no blockers. Use when the user says "pair loop", "review loop", "loop until clean", "review this with…
Plugin Claude Code
pair-review app integration — Open PRs and local changes in the pair-review web UI, run server-side AI analysis, and address review feedback. Requires the pair-review MCP server.
Skill Claude CodeCodex
Fetch AI-generated review suggestions from pair-review and make code changes to address them. Use when the user says "address AI feedback", "address AI suggestions", "fix AI review feedback", or wants to iterate on code based on AI analysis results from pair-review.
Skill Claude CodeCodex
Open local uncommitted changes for review in the pair-review web UI. This only opens the browser — it does not run AI analysis or generate suggestions. Once open, the user can browse the diff, leave comments, and trigger analysis from the web UI themselves. Use when the user says "review my local changes", "review…
Skill Claude CodeCodex
Open the GitHub pull request for the current branch in the pair-review web UI. This only opens the browser — it does not run AI analysis or generate suggestions. Once open, the user can browse the diff, leave comments, and trigger analysis from the web UI themselves. Use when the user says "review this PR", "review…
Skill Claude CodeCodex
Open outstanding GitHub review requests in pair-review for AI-powered code review. Finds open PRs where my review is pending from the past week and starts pair-review analysis for each. Use when the user says "review requests", "review my PRs", "check review requests", "open review requests", "pair-review my…
Skill Claude CodeCodex
Fetch human review comments from pair-review and make code changes to address them. Use when the user says "address review feedback", "fix review comments", "address comments", or wants to iterate on code based on feedback left by a human reviewer in pair-review.