CtrlK
BlogDocsLog inGet started
Tessl Logo

tessl-labs/pr-review-guardrails

Evidence-first pull request review with independent critique, selective challenger review, and human handoff.

87

1.31x
Quality

92%

Does it follow best practices?

Impact

87%

1.31x

Average score across 43 eval scenarios

SecuritybySnyk

Risky

Do not use without reviewing

Overview
Quality
Evals
Security
Files

criteria.jsonevals/scenario-16/

{
  "context": "Edge case: AI-assisted PR removing error handling",
  "type": "weighted_checklist",
  "checklist": [
    {
      "name": "Detects AI authorship",
      "description": "Detects that the PR was AI-assisted via Co-Authored-By commit trailers",
      "max_score": 5
    },
    {
      "name": "Catches removed error handling",
      "description": "Identifies that the PR removes error checking (if err != nil blocks) which will cause silent failures and potential panics",
      "max_score": 15
    },
    {
      "name": "Catches removed context propagation",
      "description": "Identifies that replacing real contexts with context.Background() breaks cancellation, timeout, and tracing",
      "max_score": 8
    },
    {
      "name": "Risk classified red",
      "description": "PR is classified as red despite the innocuous title — the changes are dangerous",
      "max_score": 10
    }
  ]
}

README.md

tile.json