Auto-syncs stale docstrings and README when function signatures change. Detects documentation drift after refactors, parameter additions, or return type changes. Dry-run by default — proposes before writing.
87
100%
Does it follow best practices?
Impact
86%
1.59xAverage score across 17 eval scenarios
Passed
No known issues
{
"context": "Tests whether the agent leaves CHANGELOG.md and ADR markdown files completely untouched, even when they contain code-span mentions of a changed symbol. These files are in the never-modify list and must not be proposed or auto-written.",
"type": "weighted_checklist",
"checklist": [
{
"name": "Go doc comment updated",
"description": "pkg/client/client.go doc comment for Connect includes documentation for the new timeout parameter",
"max_score": 30
},
{
"name": "CHANGELOG not modified",
"description": "CHANGELOG.md is byte-for-byte identical to the baseline — the agent did NOT write to it, propose changes to it, or mention updating it",
"max_score": 55
},
{
"name": "ADR not modified",
"description": "decisions/adr-003-api-design.md is byte-for-byte identical to the baseline — the agent did NOT write to or propose changes to the ADR file",
"max_score": 55
},
{
"name": "CHANGELOG absent from report proposals",
"description": "doc-sync-report.md does NOT list CHANGELOG.md under 'Proposed' or 'Would Update' — CHANGELOG is not a candidate for proposals",
"max_score": 50
},
{
"name": "Unified report format",
"description": "doc-sync-report.md contains '## Doc Sync Report' as a top-level heading",
"max_score": 45
}
]
}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