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 will-pagane/claude-superdev-harness --skill codex-reviewgit clone --depth 1 https://github.com/will-pagane/claude-superdev-harnessWrote 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/will-pagane/claude-superdev-harness/codex-review)<a href="https://agentmods.dev/skills/will-pagane/claude-superdev-harness/codex-review"><img src="https://agentmods.dev/badge/skills/will-pagane/claude-superdev-harness/codex-review.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00271 | $0.04729 |
| Opus 5 | $0.00135 | $0.02364 |
| Sonnet 5 | $0.00054 | $0.00946 |
| Haiku 4.5 | $0.00027 | $0.00473 |
Grade B, and why
codex-review scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- Do NOT pin `-m` unless the user asks. The user's `~/.codex/config.toml` default model is used. Pinning `gpt-5.x-codex` variants fails on ChatGPT-account auth. How it starts
The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex-Review — Adversarial Plan-Review Loop
Two models, one plan, a bounded argument. Claude is the builder and orchestrator. Codex is a read-only critic that can read the repo and the plan but cannot touch a single file. They communicate strictly through this run's plan file ($PLAN_FILE, under a timestamped $RUN_DIR) + a Codex session that persists across rounds. The human enters at exactly two points: kickoff and final sign-off.
This is a deliberate, high-stakes tool — reach for it on auth, data models, concurrency, migrations, payments, anything expensive to get wrong. Skip it for obvious/cheap work.
Prerequisites (verify once, fast)
- Codex CLI installed and recent:
codex --version(need ≥ 0.130; the defaultgpt-5.5model errors on older CLIs). - Codex authenticated: a prior
codex login(ChatGPT account is fine). If a run returns an auth/model error, surface it to the user — do not silently retry. - Do NOT pin
-munless the user asks. The user's~/.codex/config.tomldefault model is used. Pinninggpt-5.x-codexvariants fails on ChatGPT-account auth. - Sandbox flag differs between the two commands.
codex execaccepts-s read-only.codex exec resumedoes NOT — it rejects-s("unexpected argument"). On resume you MUST force read-only via-c sandbox_mode="read-only", becauseconfig.tomlmay defaultsandbox_modetodanger-full-access(+approval_policy="never") — which would let Codex WRITE files mid-loop. This is the single most important safety detail in this skill: verified end-to-end on 2026-06-04.
Tunable variables (read from skill args, else default)
| Var | Default | Meaning |
|---|---|---|
MAX_ROUNDS |
5 |
Cap on review rounds. The loop terminates here unless rounds=until-approved. |
SLUG |
derived from the task (2–5 kebab-case words) | Names the run. Keep it descriptive, e.g. wave5-cleanup, anon-rpc-hardening. |
STAMP |
$(date +%Y%m%d-%H%M) |
Run timestamp. Makes the run dir unique so parallel sessions never collide. |
RUN_DIR |
docs/codex-review/<SLUG>-<STAMP>/ |
Per-run, session-owned folder. All of this run's artifacts live here — nothing at repo root. Mirrors how docs/superpowers/ scopes its artifacts. Created at kickoff. |
PLAN_FILE |
$RUN_DIR/PLAN.md |
Where the evolving plan lives (inside the run dir, never repo root). |
LOG_FILE |
$RUN_DIR/PLAN-REVIEW-LOG.md |
Append-only transcript of the argument (every round's critique + what changed). The artifact. |
VERDICT_FILE |
$RUN_DIR/codex-verdict.txt |
Codex's last-message capture. Per-run, NOT /tmp — a shared /tmp/codex-verdict.txt clobbers across concurrent runs. |
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.
- 7d ago First seen · 198 lines · 271 tokens per session scan B 7797cdbefbd1
codex-review is a skill published in the GitHub repository will-pagane/claude-superdev-harness (4 stars, last pushed 5d ago), licensed MIT. It adds 271 tokens to every session and 4,729 once invoked, about $0.0014 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
codebase-audit
A read-only method for auditing an entire codebase across contracts, data integrity, errors, security, architecture, technical debt, configuration, and caching. It produces prioritized findings and a repair roadmap.
sol-luna-router
Route substantial coding or repository-review work through a two-stage Sol commander/verifier and separate Luna Max CLI worker. Use when the user explicitly asks Sol to direct or supervise Luna, explicitly requests this router, needs an isolated auditable Luna-owned implementation with a Sol review loop, or asks to…
idea-team
A structured group discussion for exploring a product idea through three roles: researcher, critic, and analogy finder. The roles look for evidence, weaknesses, and useful comparisons.
codex-agent
Use when you want a second-opinion review via Codex CLI, cross-verification after another agent implements changes, debugging help, or alternative implementation proposals. Requires Codex CLI to be installed and authenticated.
project-health-auditor
Comprehensive codebase health analysis. Use when reviewing code quality, identifying technical debt, checking dependencies, or assessing project structure.
review-gate
Use before an agent-produced diff is committed, pushed, opened as a PR, merged, landed, or applied to user files when explicit implementation approval is missing. Trigger for review gate, review pack, approve before landing, diff first then land, human approval, merge gate, commit gate, push gate, or PR readiness.…