- name
SKILL.md
Le fichier du skill reste dans le dépôt de l'éditeur.
Collez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add oliver-kriska/claude-elixir-phoenix --skill codex-ab -a cursor -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add oliver-kriska/claude-elixir-phoenix --skill codex-ab -a claude-code -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add oliver-kriska/claude-elixir-phoenix --skill codex-ab -a codex -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add oliver-kriska/claude-elixir-phoenix --skill codex-ab -a grok -yEnvoyez le message copié dans un chat Grok Bot. Le Bot récupère ce SKILL.md sur GitHub et l'ajoute aux skills que partagent tous vos Bots.
Install this skill: https://github.com/oliver-kriska/claude-elixir-phoenix/tree/HEAD/.claude/skills/codex-abDe l'éditeur
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.mdVue d'ensemble
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
Téléchargez .claude/skills/codex-ab/SKILL.md auprès de l'éditeur, ou copiez le chemin et ouvrez le dépôt. PlugMCP répertorie le skill et n'héberge pas le fichier.
L'éditeur le maintient sur https://github.com/oliver-kriska/claude-elixir-phoenix.
Claude, Cursor, Codex et Grok Build peuvent lire un SKILL.md que vous ajoutez depuis le dépôt de l'éditeur. Grok Bot l'installe lorsque vous envoyez dans un chat le lien du dossier GitHub du skill.