Awesome Reviewers

Verification · Code review

Agentic exploration

An agent with read, search and run tools investigates a change: follows a suspicion across files, runs code, and returns findings with evidence.

Sub-techniques

  • Breadth survey V1034.001

    A first pass that lists concerns across the whole diff.

  • Deep exploration V1034.002

    Focused sub-agents that investigate one concern each.

  • Tiered depth V1034.003

    Route small or low-risk changes to a shallow pass and risky ones to deep exploration.

How to build it

  1. Give the agent read-only tools first: read file, grep, list directory.
  2. Split into a survey step and per-concern investigation steps.
  3. Require each finding to cite file, line and the evidence that supports it.

Signals in a repository

  • Agent configuration files (AGENTS.md, CLAUDE.md) and review bot comments that cite multiple files.