enforces engineering-governance checks before code changes that may be unnecessary, risky, architectural, or scope-widening. use when the user asks whether to refactor, clean up, redesign, choose a next development step, review a proposed implementation, evaluate architectural consistency, review a pull request, or prevent development drift. do not use as the primary implementation skill for routine debugging, bug fixes, feature coding, or language-specific coding unless a no-op, minimal-diff, or architecture-conflict judgment is needed.
98
100%
Does it follow best practices?
Impact
96%
1.33xAverage score across 5 eval scenarios
Passed
No known issues
{
"context": "Checks whether the agent pushes back on scope creep, duplication, and speculative refactors while giving a brief objection and a safer alternative.",
"type": "weighted_checklist",
"checklist": [
{
"name": "Churn",
"description": "Identifies unnecessary churn",
"max_score": 10
},
{
"name": "Duplication",
"description": "Identifies duplicated capability",
"max_score": 10
},
{
"name": "Ownership",
"description": "Identifies unclear ownership",
"max_score": 10
},
{
"name": "Abstraction",
"description": "Identifies premature abstraction",
"max_score": 10
},
{
"name": "Drift",
"description": "Identifies architecture drift",
"max_score": 10
},
{
"name": "Untested",
"description": "Identifies untested behavior",
"max_score": 10
},
{
"name": "Scope",
"description": "Identifies scope expansion without explicit benefit",
"max_score": 10
},
{
"name": "Pushback",
"description": "Rejects changes justified only by preference, novelty, style, or speculative future needs",
"max_score": 10
},
{
"name": "Objection",
"description": "States the objection briefly and justifies it",
"max_score": 10
},
{
"name": "Safer alternative",
"description": "Proposes the safer alternative",
"max_score": 10
}
]
}