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 agentmods add skills/tonydzi/second-brain-starter-kit/codex-reviewnpx skills add tonydzi/second-brain-starter-kit --skill codex-reviewgit clone --depth 1 https://github.com/tonydzi/second-brain-starter-kitWrote 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/tonydzi/second-brain-starter-kit/codex-review)<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/codex-review"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/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 | $0.00085 | $0.01743 |
| Opus 5 | $0.00043 | $0.00872 |
| Sonnet 5 | $0.00017 | $0.00349 |
| Haiku 4.5 | $0.00009 | $0.00174 |
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 5d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
codex-review — "Claude checks Codex"
A thin broker for the review pair. Codex writes the code; Claude reviews its diff independently. (The old note "codex exec headless hangs on Windows" is obsolete: on codex-cli 0.141+ headless works natively — verified 2026-07-07 on the laptop and 2026-07-14 on the hub.) File handoff, no shared credentials, subscription (not a paid API).
When to run it
The owner made a change through Codex (or there is simply a diff/edit in a repository) and wants an independent "second pair of eyes" check. Triggers: see description.
What I do
- Identify the target. Ask for / take the path to the repository where Codex made the change (or the path to a patch file). Default — the working repository the owner named.
- Run the engine (deterministic, 0 of my tokens for the run itself — the review is done by headless
claude -p):python "%USERPROFILE%\.claude\scripts\cc-review\cc_review.py" --repo "<path to repo>" --model sonnet- model: Sonnet by default (the free subscription bucket; in the test it caught both bugs in 25s); Opus for hard/safety-critical changes (
--model opus) — the quality gate. - other modes:
--range "HEAD~1 HEAD"(a specific commit),--diff "<patch.diff>"(a ready patch),--task "<task.md>"(what Codex was asked to do — gives the reviewer context).
- model: Sonnet by default (the free subscription bucket; in the test it caught both bugs in 25s); Opus for hard/safety-critical changes (
- Report to the owner: the verdict (
APPROVE/REQUEST_CHANGES), the list of findings (file:line · severity · what is wrong · the fix), and the path toreview-<ts>.md. If REQUEST_CHANGES — propose fixing the root cause (not the symptom).
Boundaries
- The engine forcibly unsets
ANTHROPIC_API_KEY→ the review runs on the subscription, not on a paid key. - A giant diff is truncated to 120k characters (with a note) — if you hit that, review it in parts / per file.
- This is a REVIEW, not an auto-fix: fixes are proposed/made separately per AK-47 (easy and reversible — do it yourself; a fork — ask).
- The full auto-pair (Codex headless as well) can be built later under WSL2/Docker — a separate step (not needed now).
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.
- 5d ago First seen · 61 lines · 85 tokens per session scan A 6285e83f5fe8
codex-review is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (5 stars, last pushed 6d ago), licensed MIT. It adds 85 tokens to every session and 1,743 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
autoresearch
Run a bounded, source-grounded research loop, draft a cited dossier, and optionally propose a separately reviewed canonical vault merge. Use when the user wants autonomous or deep research that may access the public web. Triggers: /autoresearch, autoresearch, research this topic, deep dive into, investigate, find…
wiki-ingest
Ingest supplied source material into an Obsidian vault with provenance and claim tracking: pasted text, files staged in the selected vault's inbox or .raw archive, or explicitly approved URLs. Use for a single source or bounded batch, not for saving an assistant answer. Triggers: ingest, ingest this file, ingest this…
canvas
Create, inspect, and update Obsidian JSON Canvas boards with text, file, link, group, and edge nodes. Use for canvas status, canvas lists, visual maps, zones, spatial layouts, adding vault notes or media to a .canvas file, and requests such as create canvas, add to canvas, or put this on the canvas.
defuddle
Plan and, with explicit network consent, use an optional external Defuddle cleaner to extract article-like HTTPS pages as Markdown. Use for defuddle, clean this URL, strip page clutter, readable Markdown from a web page, or preparing a web source for later wiki ingestion.
obsidian-bases
Explain, draft, and validate Obsidian Bases .base files with filters, formulas, properties, summaries, and table, card, or list views. Use for Obsidian Bases, database-like vault views, dynamic tables, reading lists, task trackers, filters, formulas, summaries, and .base file edits.
save
Save a user-selected answer, decision, insight, or session summary into an Obsidian vault as one reviewed transaction. Use only when the user explicitly asks to preserve specific conversation content, not when they supply a file or URL to ingest. Triggers: /save, save this, save that answer, file this conversation…