Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add oliver-kriska/claude-elixir-phoenix --skill codex-abgit clone --depth 1 https://github.com/oliver-kriska/claude-elixir-phoenixWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/oliver-kriska/claude-elixir-phoenix/codex-ab)<a href="https://agentmods.dev/skills/oliver-kriska/claude-elixir-phoenix/codex-ab"><img src="https://agentmods.dev/badge/skills/oliver-kriska/claude-elixir-phoenix/codex-ab.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00060 | $0.01066 |
| Opus 5 | $0.00030 | $0.00533 |
| Sonnet 5 | $0.00012 | $0.00213 |
| Haiku 4.5 | $0.00006 | $0.00107 |
Grade A, and why
codex-ab scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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
- 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 - Verify every REAL MISS in the code before counting it — a focused finding only scores if the issue actually exists at that file:line
- Read ONLY the findings
.mdfiles — streams are diverted to.logfiles; never cat a log into context (10k+ lines each) - Exactly 4 codex runs, never re-run dimensions — bounded quota
- 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 --shortdirty → 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)
Step 2: Run the A/B (background, ~5 min)
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.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 101 lines · 60 tokens per session scan A 4f1db25f0c2e
codex-ab is a skill published in the GitHub repository oliver-kriska/claude-elixir-phoenix (539 stars, last pushed 2d ago), licensed MIT. It adds 60 tokens to every session and 1,066 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
059-design-atdd
Use when reviewing whether an OpenSpec change's execution goal, acceptance criteria, and implementation or verification tasks are aligned. This should trigger for requests such as Review this OpenSpec change with ATDD; Check acceptance criteria against tasks; Find acceptance criteria without task coverage; Detect…
056-design-avoid-breaking-changes
Use when you need to review a plan, OpenSpec change, specification, or implementation proposal for breaking-change risk across commands, skills, generated outputs, XML sources, README/docs, tests, CI, APIs, schemas, configuration, data, migration, and release guidance. This should trigger for requests such as Review…
053-design-simple-rules
Use when Java design, refactoring, or implementation tradeoffs should be evaluated with Kent Beck's simple design rules, including passes the tests, reveals intention, has no duplication, and has the fewest elements. This should trigger for requests such as Apply simple design rules; Review this design with Beck's…
test-strategy
Coverage-design method for qa-engineer — pyramid ratios per archetype, equivalence/boundary/property case selection, mutation score as the real coverage signal, and a flake-quarantine policy. Turns "coverage is 90%" (a number with no method) into a defensible test plan. Emits TEST-STRATEGY-{slug}.md, which the QA gate…
craft-pest
Testing Craft CMS 5 plugins and modules with Pest — test isolation, database safety, and the markhuot/craft-pest-core harness. ALWAYS load when writing, running, fixing, or reviewing tests for a Craft plugin or module, and whenever a suite touches a real Craft install. Covers why rollback is opt-in, tests/Pest.php +…
spike-consumer-adversarial
OI-3 spike harness — heavy consumer, ADVERSARIAL arm. Worst-case early-exit test: the mid-workflow Skill call has no continuation guardrail and the guidance skill ends with a final-sounding anchor. Use only when explicitly invoked by the spike harness with a TRIALID and data path.