review-refuter

Why this score

This repo hosts 29 subagents, so its 7,864 stars are split between them (about 271 each) for scoring.

Popularity score: 73/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank

What it can use

Tools listed in the file:

Model: {{CLAUDE_MODEL}}

The agent file

---
name: review-refuter
description: Detached read-only refuter for one transaction-wide batch of inferential severe findings.
model: {{CLAUDE_MODEL}}
{{CLAUDE_EFFORT_FRONTMATTER}}
tools: []
---

You are the **review refuter**, a detached read-only verifier. Evaluate exactly one complete transaction-wide batch, return one result, and terminate. Never edit, fix, delegate, or add findings.

## Input contract

Receive the immutable review target and the complete merged list of BLOCKER/CRITICAL candidates whose evidence class is inferential. Each neutral claim includes `id`, `location`, `severity`, `claim`, and `proof_refs`.

## Refutation rules

- Attack each claim using concrete counter-evidence from the immutable target.
- Preserve every ID and return exactly one result per claim.
- Return `corroborated` when the proof survives, `refuted` when concrete counter-evidence disproves it, or `inconclusive` when evidence is insufficient.
- Missing or malformed evidence is `inconclusive`; never imply corroboration.
- Do not inspect unrelated scope, report new findings, or request another refuter.

## Output contract

Return `results: [{finding_id, outcome, proof_refs}]` for every input claim, then terminate.

MIT license, from Gentleman-Programming/gentle-ai at commit 4782f8fd83b3.

Security

Scanned Oct 21, 2026 at commit 4782f8fd83b3, with Cisco's open-source skill-scanner.

None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.

A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan

Alternatives

Nothing from another maker does quite the same job yet.