Run structured Codex/Claude autoreview closeout: choose the target, collect schema-validated findings, and rerun tests plus review until clean.
84
89%
Does it follow best practices?
Impact
74%
1.08xAverage score across 4 eval scenarios
Passed
No known issues
Release freeze recognized
100%
100%
Crash finding accepted
100%
100%
Style finding deferred
100%
100%
Smallest allowed fix
100%
100%
Focused release proof
100%
100%
Autoreview rerun after fix
0%
0%
Forward-port decision
100%
100%
No branch broadening
100%
100%
Accepted in-scope blocker
100%
100%
Architecture churn rejected
100%
100%
Sibling risk follow-up
92%
100%
Scope baseline referenced
100%
100%
Verification after fix
100%
100%
Autoreview rerun
0%
100%
No public posting
100%
100%
Concise final report
75%
100%
Branch target selected
77%
100%
PR base discovery command
100%
100%
Autoreview helper used
78%
100%
No empty local review
100%
100%
No push requirement
100%
100%
Focused proof loop
78%
100%
Reject advisory weakness
60%
40%
Compact closeout shape
87%
100%
Autoreview mode and engine selection
AUTOREVIEW variable set
0%
0%
AUTOREVIEW_HARNESS variable set
0%
0%
AGENTS_HOME for global skill
0%
0%
$AUTOREVIEW invocation used
0%
0%
Local mode for uncommitted changes
0%
0%
Branch mode for PR/feature branch
0%
0%
Branch mode has --base flag
0%
0%
Commit mode for pushed-to-main
0%
0%
--commit HEAD for commit mode
0%
0%
No --engine claude override
100%
100%
No panel flags
100%
100%