CtrlK
BlogDocsLog inGet started
Tessl Logo

uinaf/review-gang

Review existing code, diffs, branches, or pull requests by spawning mandatory concern-specific reviewer subagents, then synthesize a ship-it / needs-review / blocked verdict.

87

1.19x
Quality

90%

Does it follow best practices?

Impact

81%

1.19x

Average score across 4 eval scenarios

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

Evaluation results

98%

14%

Auth Token Module Review

Criteria
Without context
With context

any type flagged

100%

100%

Unsafe cast flagged

30%

100%

Non-null assertion flagged

100%

100%

Dead code identified

100%

100%

Duplicate logic identified

100%

100%

Catch-all error flagged

100%

100%

Error classification recommended

60%

100%

Narrating comments flagged

100%

100%

Findings tied to impact

100%

100%

Valid verdict

80%

100%

Compact verdict block

50%

75%

98%

23%

Review: Payment Retry Logic Changes

Criteria
Without context
With context

CLAUDE.md loaded

100%

100%

File references in findings

100%

100%

Line-level evidence

100%

100%

Verdict present

50%

100%

Findings by severity

100%

100%

Error classification finding

100%

100%

Silent failure finding

100%

100%

Mock-heavy test concern

33%

100%

Dead code identified

100%

100%

Unverified surfaces marked

12%

100%

Recommended follow-up

100%

100%

No nit inflation

100%

100%

Reviewer gang listed

0%

100%

Compact verdict block

62%

75%

34%

-8%

Quick Review: Documentation Typo Fix

Criteria
Without context
With context

Default gang spawned

0%

0%

General persona used

37%

25%

Comments persona used

40%

30%

Tests persona included

25%

25%

Code-shape persona included

0%

0%

Verdict present

50%

0%

Scope stated

75%

75%

Personas listed in output

0%

0%

No nit inflation

100%

100%

Docstring accuracy noted

100%

100%

Unverified areas or residual risk

25%

50%

Recommended follow-up

50%

0%

Compact verdict block

50%

62%

96%

25%

Code Review: Authentication Middleware Refactor

Criteria
Without context
With context

Default gang spawned

0%

100%

Subagent authorization honored

0%

87%

Types persona included

80%

100%

Cleanup persona included

75%

100%

Comments persona omitted

100%

100%

Repo guidance loaded

100%

100%

Personas listed in output

0%

100%

Verdict present

100%

100%

Scope stated

66%

100%

Findings ordered by severity

100%

100%

Evidence for findings

100%

100%

Silent failures finding

100%

100%

Unverified areas acknowledged

66%

100%

Recommended follow-up

100%

100%

Compact verdict block

50%

50%

Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents