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": "Agent must flag renamed Go functions for human review without auto-deleting old names or auto-creating new README entries. Baseline models often 'fix' migration docs by deleting old references.",
"type": "weighted_checklist",
"checklist": [
{
"name": "Rename flagged for review",
"description": "The report mentions both FetchUser and GetUser and flags the change as [NEEDS HUMAN REVIEW]",
"max_score": 50
},
{
"name": "README not auto-rewritten",
"description": "The report does NOT contain 'Here is the updated README.md', 'Deleted FetchUser from README', or a markdown rewrite block",
"max_score": 55
},
{
"name": "Unified report format used",
"description": "The output contains '## Doc Sync Report' as the 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