Santa-loop's Reviewer B only tried codex and gemini before falling back
to a same-family Claude reviewer, losing model diversity when neither
was installed. Detect agy (Antigravity CLI, ~/.local/bin/agy) as a
third option, using gemini-3.6-flash-high — despite the "flash" name,
it currently outranks gemini-3.1-pro-high on every published
coding/agentic benchmark (SWE-Bench Pro, Terminal-Bench, MLE-Bench),
with Pro only ahead on PhD-level reasoning benchmarks that don't apply
to code review. Also documents never pointing agy at a Claude model,
which would collapse Reviewer A/B model diversity entirely.
* feat(commands): add santa-loop adversarial review command
Adds /santa-loop, a convergence loop command built on the santa-method
skill. Two independent reviewers (Claude Opus + external model) must
both return NICE before code ships. Supports Codex CLI (GPT-5.4),
Gemini CLI (3.1 Pro), or Claude-only fallback. Fixes are committed
per round and the loop repeats until convergence or escalation.
* fix: address all PR review findings for santa-loop command
- Add YAML frontmatter with description (coderabbit)
- Add Purpose, Usage, Output sections per CONTRIBUTING.md template (coderabbit)
- Fix literal <prompt> placeholder in Gemini CLI invocation (greptile P1)
- Use mktemp for unique temp file instead of fixed /tmp path (greptile P1, cubic P1)
- Use --sandbox read-only instead of --full-auto to prevent repo mutation (cubic P1)
- Use git push -u origin HEAD instead of bare git push (greptile P2, cubic P1)
- Clarify verdict protocol: reviewers return PASS/FAIL, gate maps to NICE/NAUGHTY (greptile P2, coderabbit)
- Specify parallel execution mechanism via Agent tool (coderabbit nitpick)
- Add escalation format for max-iterations case (coderabbit nitpick)
- Fix model IDs: gpt-5.4 for Codex, gemini-2.5-pro for Gemini
affaan-m