- name
SKILL.md
스킬 파일은 게시자의 저장소에 그대로 있습니다.
복사한 명령을 터미널에 붙여넣습니다. 이 SKILL.md가 해당 에이전트에 설치됩니다.
npx skills add oliver-kriska/claude-elixir-phoenix --skill codex-ab -a cursor -y복사한 명령을 터미널에 붙여넣습니다. 이 SKILL.md가 해당 에이전트에 설치됩니다.
npx skills add oliver-kriska/claude-elixir-phoenix --skill codex-ab -a claude-code -y복사한 명령을 터미널에 붙여넣습니다. 이 SKILL.md가 해당 에이전트에 설치됩니다.
npx skills add oliver-kriska/claude-elixir-phoenix --skill codex-ab -a codex -y복사한 명령을 터미널에 붙여넣습니다. 이 SKILL.md가 해당 에이전트에 설치됩니다.
npx skills add oliver-kriska/claude-elixir-phoenix --skill codex-ab -a grok -y복사한 메시지를 Grok Bot 채팅에 보냅니다. Bot이 GitHub에서 이 SKILL.md를 가져와 모든 Bot이 공유하는 스킬에 추가합니다.
Install this skill: https://github.com/oliver-kriska/claude-elixir-phoenix/tree/HEAD/.claude/skills/codex-ab게시자 제공
Answer one question with evidence: do dimension-focused codex passes find
real issues that one holistic codex exec review misses? Runs both on the
same diff, then classifies every focused finding against the holistic pass.
DECIDED 2026-07-10 after 4 runs (2 fresh): panel KILLED. Fresh-only 1 real miss / 1 false positive plus one zero-value run at 4× cost — real misses did not outnumber FPs. Kept as contributor tooling (NOT distributed) for one possible retest: a UI-heavy diff with a single extra liveview-focused pass (2× cost). Scoreboard:
.claude/research/2026-07-03-codex-review-integration.md§7.
/codex-ab # A/B against main (~5 min, 4 codex runs)
/codex-ab develop # explicit base branch
/phx:codex-loop). A drained diff returns
NO FINDINGS everywhere and proves nothing — wasted quota.md files — streams are diverted to .log
files; never cat a log into context (10k+ lines each)Run command -v codex — missing → STOP with install hint. Then:
git status --short dirty → warn (codex flags local dirt as findings)bash ${CLAUDE_SKILL_DIR}/scripts/codex-panel-ab.sh {base} \
.claude/reviews/codex-ab-$(date +%Y-%m-%d-%H%M)
Use run_in_background — it runs 1 holistic codex exec review + 3
focused codex exec workers (security / ecto / liveview) in parallel,
all streams redirected. Do other work or wait; never poll.
Read the 4 findings files (holistic.md, security.md, ecto.md,
liveview.md — small). For EACH focused finding:
Present:
## Codex Panel A/B — {branch} vs {base}
| dimension | findings | duplicate | real miss | false positive |
Holistic-only findings: {n}
Verdict this run: {REAL MISS count} real miss vs {FP count} false positive
Decision rule: build --codex-panel only if real misses outnumber false
positives across 2-3 fresh branches.
Write the verdict table to .claude/reviews/codex-ab-{date}/VERDICT.md.
Suggest repeating on the next 1–2 fresh branches before deciding.
fresh branch → /codex-ab (YOU ARE HERE) → verdict logged
├─ real misses win across runs → build /phx:review --codex-panel
└─ duplicates/FPs win → keep holistic /phx:codex-loop, drop panel idea
└─ OUTCOME 2026-07-10: this branch won — panel dropped
${CLAUDE_SKILL_DIR}/scripts/codex-panel-ab.sh — the 4-run harness/phx:codex-loop (holistic fix loop), /phx:review --codexRun an A/B codex review experiment — holistic codex review vs 3 focused dimension passes (security, ecto, liveview) on the branch diff, classify findings, report a panel-value verdict. Use when the br
---name: codex-abdescription: Run an A/B codex review experiment — holistic codex review vs 3 focused dimension passes (security, ecto…---# .claude/skills/codex-ab/SKILL.md개요
Run an A/B codex review experiment — holistic codex review vs 3 focused dimension passes (security, ecto, liveview) on the branch diff, classify findings, report a panel-value verdict. Use when the branch is fresh, before any codex review runs.
FAQ
게시자에게서 .claude/skills/codex-ab/SKILL.md를 다운로드하거나 경로를 복사해 저장소를 엽니다. PlugMCP는 스킬을 목록에 올릴 뿐 파일을 호스팅하지 않습니다.
게시자가 https://github.com/oliver-kriska/claude-elixir-phoenix에서 관리합니다.
Claude, Cursor, Codex, Grok Build는 게시자의 저장소에서 추가한 SKILL.md를 읽을 수 있습니다. Grok Bot은 채팅에서 스킬의 GitHub 폴더 링크를 보내면 설치합니다.