parallel-adversarial-review — tool profile and history

Two Claude Code skills for adversarial code review (single-model PAR and multi-model MMAR with cross-critique to catch hallucinations), plus a fixture-based eval suite.

Dormant

Canonical source ↗

Language
Python
Created
Last activity
Topics
  • ai-agents
  • claude-code-plugin
  • code-review
  • evals
  • python

Install /plugin marketplace add prime-radiant-inc/parallel-adversarial-review

Current measurement

17GitHub starsstable
measured growth

Momentum uses available readings from the last 7 days: measured with at least two comparable readings, estimated otherwise.

Reading history

90 days · 90 maximum readings
DateValueMetric
17GitHub stars
17GitHub stars
17GitHub stars
17GitHub stars
17GitHub stars
17GitHub stars
17GitHub stars
17GitHub stars
17GitHub stars
17GitHub stars
17GitHub stars
17GitHub stars
17GitHub stars
17GitHub stars
17GitHub stars
17GitHub stars
17GitHub stars
17GitHub stars
17GitHub stars
17GitHub stars
17GitHub stars
17GitHub stars
17GitHub stars
17GitHub stars
17GitHub stars

Classifications

Domains
Type
Agent skills
Use cases