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.

92

1.22x
Quality

97%

Does it follow best practices?

Impact

81%

1.22x

Average score across 4 eval scenarios

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

Evaluation results

100%

22%

Auth Token Module Review

Criteria
Without context
With context

any type flagged

100%

100%

Unsafe cast flagged

0%

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

100%

100%

Narrating comments flagged

100%

100%

Findings tied to impact

100%

100%

Valid verdict

0%

100%

Compact verdict block

62%

100%

91%

22%

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

37%

100%

Findings by severity

100%

100%

Error classification finding

100%

100%

Silent failure finding

62%

100%

Mock-heavy test concern

16%

83%

Dead code identified

100%

100%

Unverified surfaces marked

0%

100%

Recommended follow-up

100%

100%

No nit inflation

100%

100%

Reviewer gang listed

0%

0%

Compact verdict block

50%

100%

52%

Quick Review: Documentation Typo Fix

Criteria
Without context
With context

Default gang spawned

0%

0%

General persona used

50%

37%

Comments persona used

60%

50%

Tests persona included

37%

50%

Verdict present

50%

40%

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

75%

100%

Recommended follow-up

30%

40%

Compact verdict block

75%

62%

84%

17%

Code Review: Authentication Middleware Refactor

Criteria
Without context
With context

Default gang spawned

0%

50%

Types persona included

60%

80%

Cleanup persona included

62%

75%

Comments persona omitted

100%

100%

Repo guidance loaded

100%

100%

Personas listed in output

0%

0%

Verdict present

62%

100%

Scope stated

83%

83%

Findings ordered by severity

100%

100%

Evidence for findings

100%

100%

Silent failures finding

87%

100%

Unverified areas acknowledged

16%

100%

Recommended follow-up

100%

100%

Compact verdict block

50%

83%

Evaluated
Agent
Claude
Model
Claude Sonnet 4.6

Table of Contents