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.

MITAuto-check passed

Install Codex Ab

skills CLI
$ npx skills add oliver-kriska/claude-elixir-phoenix --skill codex-ab -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install oliver-kriska/claude-elixir-phoenix codex-ab --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/oliver-kriska/claude-elixir-phoenix.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/codex-ab .claude/skills/codex-ab && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
codex-ab
GitHub stars
565
Token cost
~977 tokens
SKILL.md length
371 words
Files
3 (incl. scripts)
Skills in repo
111
Repo updated
First seen
Licence
MIT

At a glance

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.

  • Works in 4 steps: Preflight → Run the A/B (background, ~5 min) → Classify → …
  • The branch is fresh
  • SKILL.md covers Usage, Iron Laws, Workflow and Integration, plus 1 more section
  • Runs Shell scripts from its folder; calls codex, bash and git

What it does

Codex Ab is an agent skill from oliver-kriska/claude-elixir-phoenix. 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.

Its SKILL.md is about 980 tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including scripts (for example `scripts/codex-panel-ab.sh` and `triggers.json`).

The repository describes itself as: Claude Code plugin for Elixir/Phoenix/LiveView — 26 specialist agents, Iron Laws enforcement, and Tidewave MCP integration. Plan features with parallel research agents, execute… The licence is MIT.

When your agent uses it

  • The branch is fresh
  • Before any codex review runs

Example prompts

  • “/codex-ab”

Requirements

  • A Bash shell

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Preflight
  2. Run the A/B (background, ~5 min)
  3. Classify
  4. Verdict

What it can do on your machine

Read from SKILL.md and the folder at commit 9767a82. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • codex
    • bash
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Codex Ab loads about 977 tokens when it runs. Until then it costs about 63 tokens; SKILL.md has 371 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~63
When it runs · the whole SKILL.md, loaded when a task matches
~977

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from oliver-kriska/claude-elixir-phoenix at commit 9767a82, republished under its MIT licence (© oliver-kriska). 371 words, ~977 tokens.

Download SKILL.mdSave it as .claude/skills/codex-ab/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
codex-ab
description
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.
effort
medium
argument-hint
[base-branch]

Codex Panel A/B (contributor instrument — verdict decided)

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.

Usage

/codex-ab            # A/B against main (~5 min, 4 codex runs)
/codex-ab develop    # explicit base branch

Iron Laws

  1. FRESH DIFF ONLY — ask the user to confirm this branch has NOT been codex-reviewed yet (cloud or /phx:codex-loop). A drained diff returns NO FINDINGS everywhere and proves nothing — wasted quota
  2. Verify every REAL MISS in the code before counting it — a focused finding only scores if the issue actually exists at that file:line
  3. Read ONLY the findings .md files — streams are diverted to .log files; never cat a log into context (10k+ lines each)
  4. Exactly 4 codex runs, never re-run dimensions — bounded quota
  5. Persist the verdict — an unrecorded experiment is wasted quota

Workflow

Step 1: Preflight

Run command -v codex — missing → STOP with install hint. Then:

  • git status --short dirty → warn (codex flags local dirt as findings)
  • Ask: "Has codex already reviewed this branch (PR review or codex-loop)?" If yes → STOP, explain the fresh-diff requirement (Iron Law 1)
Show full SKILL.md (131 more words)Show less
Step 2: Run the A/B (background, ~5 min)
bash
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.

Step 3: Classify

Read the 4 findings files (holistic.md, security.md, ecto.md, liveview.md — small). For EACH focused finding:

ClassMeaningTest
DUPLICATEHolistic already found itSame file + same defect
REAL MISSGenuine issue holistic missedRead the code at file:line — defect confirmed (Iron Law 2)
FALSE POSITIVEManufactured, pre-existing, or wrongCode check fails, or issue exists on base branch too
Step 4: Verdict

Present:

markdown
## 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.

Integration

text
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

References

  • ${CLAUDE_SKILL_DIR}/scripts/codex-panel-ab.sh — the 4-run harness
  • Related: /phx:codex-loop (holistic fix loop), /phx:review --codex

© oliver-kriska, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (scripts) in .claude/skills/codex-ab of oliver-kriska/claude-elixir-phoenix.

  • SKILL.md
  • scripts/codex-panel-ab.sh
  • triggers.json

Open the folder on GitHubat commit 9767a82

Compare with similar skills

Codex Ab next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Codex Ab compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Codex Ab this skilloliver-kriska/claude-elixir-phoenix565—~977Automated safety check: PassMIT
Finding ExperimentsPostHog/posthog40k—~826Automated safety check: PassCustom licence
ExperimentsArize-ai/phoenix12k—~1.8kAutomated safety check: PassCustom licence
Scroll Experiencesickn33/agentic-awesome-skills47k2 repos~534Automated safety check: PassMIT
Webgl Experiencenexu-io/open-design100k—~903Automated safety check: PassApache-2.0
Creating ExperimentsPostHog/posthog40k—~2.7kAutomated safety check: PassCustom licence

Similar skills

  • Finding Experiments

    PostHog/posthog

    Official

    Resolves a PostHog experiment reference from natural language to a concrete experiment ID by browsing experiment-list (not feature-flag tools), with disambiguation when multiple experiments match.

    40k GitHub stars~826 tokensUpdated today
    Frontend & DesignAuto-check passed
  • Experiments

    Arize-ai/phoenix

    Run, read, and compare dataset-backed experiments to find evidence that a prompt or pipeline is improving.

    12k GitHub stars~1.8k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Scroll Experience

    sickn33/agentic-awesome-skills

    Expert in building immersive scroll-driven experiences - parallax storytelling, scroll animations, interactive narratives, and cinematic web experiences.

    47k GitHub starsUsed in 2 repos~534 tokens
    Writing & ContentAuto-check passed
  • Webgl Experience

    nexu-io/open-design

    A full-screen, real-time WebGL/WebGL2 experience — animated shaders, 3D scenes, generative visuals, particle fields — rendered live on the GPU with a typographic overlay.

    100k GitHub stars~903 tokensUpdated today
    Game DevelopmentAuto-check passed
  • Creating Experiments

    PostHog/posthog

    Official

    Guides agents through experiment creation: reading the project's setup with experiment-setup-context, defining the hypothesis, configuring rollout and bucketing, setting up analytics and running…

    40k GitHub stars~2.7k tokensUpdated today
    Marketing & SEOAuto-check passed
  • Scroll Experience

    davila7/claude-code-templates

    Expert in building immersive scroll-driven experiences - parallax storytelling, scroll animations, interactive narratives, and cinematic web experiences.

    32k GitHub starsUsed in 3 repos~1.5k tokens
    Frontend & DesignAuto-check passed

More from oliver-kriska/claude-elixir-phoenix

All 111 skills in this repo
  • Audit

    oliver-kriska/claude-elixir-phoenix

    Project health audit and health check — architecture, performance, tests, dependencies, code quality.

    565 GitHub stars~2k tokensUpdated 3 days ago
    Auto-check passed
  • Compound Docs

    oliver-kriska/claude-elixir-phoenix

    Searchable Elixir/Phoenix/Ecto solution documentation system with; Use when consulting past solutions…

    565 GitHub stars~528 tokensUpdated 3 days ago
    Auto-check passed
  • Compound Docs

    oliver-kriska/claude-elixir-phoenix

    Searchable Elixir/Phoenix/Ecto solution documentation system with YAML frontmatter.

    565 GitHub stars~547 tokensUpdated 3 days ago
    Auto-check passed
  • Deploy

    oliver-kriska/claude-elixir-phoenix

    Elixir/Phoenix deployment patterns — Dockerfile, fly.toml, runtime.exs, mix release, rel/ overlays.

    565 GitHub stars~1.1k tokensUpdated 3 days ago
    Auto-check passed
  • Deps Update

    oliver-kriska/claude-elixir-phoenix

    Bump outdated Hex deps — inventory, snapshot changelogs, update, fix breaks, split reviewable PRs (patches bundled, majors solo).

    565 GitHub stars~1.4k tokensUpdated 3 days ago
    Auto-check passed
  • Deps Vet

    oliver-kriska/claude-elixir-phoenix

    Record a vetted Hex package version in hexvet.exs after a security review — manages the audit ledger, not the scanner.

    565 GitHub stars~1.5k tokensUpdated 3 days ago
    Auto-check passed

Questions about Codex Ab

What does Codex Ab do?

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. Codex Ab is an agent skill from oliver-kriska/claude-elixir-phoenix. 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.

When should I use Codex Ab?

Codex Ab fits situations like: the branch is fresh; before any codex review runs.

How do I install Codex Ab in Claude Code?

Run `npx skills add oliver-kriska/claude-elixir-phoenix --skill codex-ab -a claude-code`. Or copy the skill folder (.claude/skills/codex-ab in oliver-kriska/claude-elixir-phoenix) into .claude/skills/codex-ab in your project. Claude Code loads it when a task matches its description.

How do I install Codex Ab in Codex?

Run `npx skills add oliver-kriska/claude-elixir-phoenix --skill codex-ab -a codex`. Or copy the skill folder (.claude/skills/codex-ab in oliver-kriska/claude-elixir-phoenix) into .agents/skills/codex-ab in your project. Codex loads it when a task matches its description.

Can I use Codex Ab in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add oliver-kriska/claude-elixir-phoenix --skill codex-ab -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/codex-ab, .gemini/skills/codex-ab, .github/skills/codex-ab and .opencode/skills/codex-ab in your project.

What does Codex Ab need to run?

Going by SKILL.md and its folder, Codex Ab needs a shell for the scripts in its folder and the command-line tools its instructions call (codex, bash and git). Our summary lists: A Bash shell.

Does Codex Ab access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Codex Ab safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Codex Ab use?

Codex Ab is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Codex Ab use?

About 977 tokens (SKILL.md is roughly 3.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Codex Ab?

Skills that share tags, products or a category with Codex Ab: Finding Experiments (PostHog/posthog, 40k stars), Experiments (Arize-ai/phoenix, 12k stars), Scroll Experience (sickn33/agentic-awesome-skills, 47k stars) and Webgl Experience (nexu-io/open-design, 100k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Codex Ab?

oliver-kriska (a GitHub user) maintains it in oliver-kriska/claude-elixir-phoenix, which has 565 GitHub stars. The repository holds 111 skills in this directory. The repository was last updated on October 5, 2026.

Source: oliver-kriska/claude-elixir-phoenix on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.