Evidence-first pull request review with independent critique, selective challenger review, and human handoff.
87
92%
Does it follow best practices?
Impact
87%
1.31xAverage score across 43 eval scenarios
Risky
Do not use without reviewing
{
"context": "Realistic: webhook dedup uses in-memory set that doesn't survive across worker processes",
"type": "weighted_checklist",
"checklist": [
{
"name": "Catches in-memory dedup limitation",
"description": "Identifies that the event deduplication uses an in-memory data structure (set/dict) that is not shared across worker processes — in a multi-process deployment (gunicorn, uwsgi, etc.) each worker has its own copy, so the same event gets processed multiple times",
"max_score": 15
},
{
"name": "Risk classified yellow or higher",
"description": "PR is classified as yellow or higher — it adds webhook event processing",
"max_score": 10
}
]
}evals
scenario-1
scenario-2
scenario-3
scenario-4
scenario-5
scenario-6
scenario-7
scenario-8
scenario-9
scenario-10
scenario-11
scenario-12
scenario-13
scenario-14
scenario-15
scenario-16
scenario-17
scenario-18
scenario-19
scenario-20
scenario-21
scenario-22
scenario-23
scenario-24
scenario-25
scenario-26
scenario-27
scenario-28
scenario-29
scenario-30
scenario-31
scenario-32
scenario-33
scenario-34
scenario-35
scenario-36
scenario-37
scenario-38
scenario-39
scenario-40
scenario-41
scenario-42
scenario-43
rules
skills
challenger-review
finding-synthesizer
fresh-eyes-review
human-review-handoff
pr-evidence-builder
review-retrospective