Co Review Reconciler — Development agent for Claude Code
Judges code-review findings for correctness and confidence without touching the code.
How to install Co Review Reconciler
Installs to ~/.claude/agents/bestdan-workflow-skills-co-review-reconciler.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/bestdan/workflow-skills/HEAD/agents/co-review-reconciler.md -o ~/.claude/agents/bestdan-workflow-skills-co-review-reconciler.md Restart Claude Code, or start a new session, for it to be picked up.
What Co Review Reconciler does
name: co-review-reconciler description: Judges code-review findings for correctness and confidence without touching the code. Use when a review pass has produced findings from several reviewers — its own, other agents', GitHub comments — and they need an independent verdict before anyone applies or posts them. Reads the diff and the repository for context, returns a JSON verdict array, and never modifies the working tree. tools: Read, Glob, Grep, Bash model: inherit color: yellow
You ar
Alternatives in Development
- Ir Correctness Reviewer — Reviews Slang IR pass changes for correctness, SSA invariants, and type system integrity 5.6k ★
- PR Commenter Batch — Posts sanitized batches of PR review comments or replies through configured review tooling 548 ★
- Dashclaw Gate Runner — Runs the DashClaw verification gates (lint, full vitest suite, build, contract checks) and returns ONLY the fa 297 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Findings Synthesizer
Merges and deduplicates review findings from multiple reviewers with confidence tiering and priority ranking.
Qrspi Code Simplifier
Identifies opportunities to simplify code while preserving all functionality. Deep mode only. Runs after all c
Correctness Critic
Adversarially reviews a code change through the single CORRECTNESS lens (rubric lens 1) and emits a critic-sch
Evidence Reconciler
Reconciles OncoKB vs CiVIC evidence for a single somatic variant and emits a unified AMP/ASCO/CAP tier call wi
Aiskills Code Reviewer
Reviews diffs and pull requests with visible per-dimension passes and severity-classified findings (Blocker/Ma
Reader High
pstack's read-only subagent at high effort, for reviewers, judges, explorers, and explainers. It reads, search
Related Skills
Fugu Review
Fugu-style dry-run review — this session briefs 3 blind reviewers (haiku/sonnet/opus) + an opus verifier, who
Forgeflow Compact Output
Compact allowlisted noisy command output without touching correctness-critical output.
Dotnet Review
Multi-agent .NET code review - up to five reviewers in parallel (correctness, performance, security/observabil