Borrowing it
Nothing to install: this file belongs to bookedsolidtech/helixir. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bookedsolidtech/helixir/main/.claude/commands/codex-review.mdgit clone --depth 1 https://github.com/bookedsolidtech/helixirWrote 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/commands/bookedsolidtech/helixir/codex-review)<a href="https://agentmods.dev/commands/bookedsolidtech/helixir/codex-review"><img src="https://agentmods.dev/badge/commands/bookedsolidtech/helixir/codex-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/bookedsolidtech/helixir/codex-review"><img src="https://agentmods.dev/badge/commands/bookedsolidtech/helixir/codex-review.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00043 | $0.01543 |
| Opus 5.5 | $0.00017 | $0.00617 |
| Sonnet 5.5 | $0.00009 | $0.00309 |
| Haiku 4.5 | $0.00004 | $0.00154 |
Grade A, and why
codex-review 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 2mo 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/codex-review — Adversarial Review via Codex
Default: direct Bash invocation via rea hook codex-review — the cheap, thin, marathon-mode path. The codex JSON is the review; this command's output is a ledger entry. Use --verbose only when you specifically need a Claude-paraphrased summary.
Two modes
| Mode | Cost | Output | When |
|---|---|---|---|
| default (thin) | 1 Opus turn | Terse verdict+count+raw-path on stderr, canonical JSON on stdout | Every routine review round, especially in marathon-mode iteration |
--verbose (wrapper) |
3 Opus turns | Claude-paraphrased findings with categories + severities | Teaching context, or when the caller is unfamiliar with the codex JSON shape |
Direct = cheap. Wrapper = expensive. Pick the right one for the situation.
Default path (thin)
# With auto-detected upstream/main base
rea hook codex-review --json | tee /tmp/rea-codex-last.json
# Or with an explicit base ref
rea hook codex-review --base origin/main --json | tee /tmp/rea-codex-last.json
# Or narrow to last N commits
rea hook codex-review --last-n-commits 5 --json
The CLI runs codex exec review --json --ephemeral directly with the iron-gate model defaults (gpt-5.4 + high reasoning), tees raw JSONL to $TMPDIR/rea-codex-<sha>-<nonce>.json, and writes a codex.review audit entry. Exit codes: 0 (pass), 1 (concerns), 2 (blocking / codex error / HALT).
The stdout JSON shape:
{
"verdict": "pass" | "concerns" | "blocking",
"finding_count": 0,
"head_sha": "<SHA>",
"target": "<base ref>",
"audit_hash": "<hash>",
"raw_path": "/tmp/rea-codex-...json",
"exit_code": 0
}
To act on findings, read raw_path directly with the Read tool. Each line is a JSONL event; the item.completed events with item.type === "agent_message" carry the review prose. Don't paraphrase to chat — show the user the exit code and let them decide what to do next.
Verbose path (wrapper)
When the user explicitly asks for a paraphrased summary — typically because they're not yet fluent in codex JSON — invoke the codex-adversarial agent. The agent itself runs rea hook codex-review --json and then produces a Claude-paraphrased summary by reading the raw JSON. This is the 3-Opus-turn path and should NOT be the default.
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.
- 2mo ago First seen · 109 lines · 43 tokens per session scan A 79ec827bcb55
codex-review is a command published in the GitHub repository bookedsolidtech/helixir (5 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 1,543 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.
Other commands, from other repositories
skill-creator
Create or update an OpenCode skill using the bundled skill-creator workflow.
skill-registry
Rebuild the OpenCode skill registry for the current project and installed skills.
cross-critique
Adversarial multi-angle critique. All three auditors fire in parallel (codex=technical, gemini=strategic, claude=ux). Counter-args ranked by rebuttal survival score, not raw severity. Usage: /cross-critique [--with | list | compare].
assemble-team
Assemble a pre-built agent team for parallel work - review, feature, debug, cross-platform, full-stack, or research.
pr-feedback-ingest
Turn PR feedback (Greptile, CI, bots, humans) into a traceable backlog, so the next step is a narrow implement-approved-slice. Corrective scope only. Use when a PR has review feedback to map to files and slices. Do not use for a new direction or contract (use post-review-pivot), no payload, or task-memory drift only…
review-hard
Review the current task changes for correctness, safety, and maintainability risks before slice closure or PR prep, and recommend the smallest safe next step. Use when a slice or task-level implementation was completed, the user wants a focused engineering risk review before closure or PR prep, or meaningful issues…