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 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/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/skills/tonydzi/second-brain-starter-kit/codex-review"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/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 | $0.00074 | $0.01841 |
| Opus 5.5 | $0.00030 | $0.00736 |
| Sonnet 5.5 | $0.00015 | $0.00368 |
| Haiku 4.5 | $0.00007 | $0.00184 |
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 yesterday.
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 — 59 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.
- yesterday Changed 4afb82b98c0c
- 14d ago Changed · -1 lines 582026819b42
- 19d ago Changed · +17 lines · -65 tokens per session 9b07f84be5f7
- 28d ago Changed · -19 lines · +65 tokens per session d69d6674a42b
- 1mo ago Changed · +1 lines · -11 tokens per session 76694c630d07
- 1mo 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 (12 stars, last pushed 3d ago), licensed MIT. It adds 74 tokens to every session and 1,841 once invoked, about $0.0003 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 skills, from other repositories
wiki-retrieve
Build and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, chunk search, vault search, semantic search, find relevant passages, or retrieval diagnostics. Derived caches stay under .vault-meta…
wiki
Initialize, adopt, and route work for a separate Obsidian knowledge vault through the portable claude-obsidian core. Use for vault setup, scaffolding, workspace selection, cross-project configuration, or choosing the correct wiki sub-skill. Triggers: /wiki, set up wiki, scaffold vault, create knowledge base, adopt…
defuddle
Plan optional Defuddle extraction and retain already available local source files through reviewed filesystem capture. Use for defuddle, clean this URL, strip page clutter, readable Markdown from a web page, or preparing a web source for later wiki ingestion. Network extraction remains unavailable until an enforcing…
obsidian-markdown
Explain, draft, or validate Obsidian Flavored Markdown syntax: properties, wikilinks, embeds, callouts, tags, comments, highlights, block references, math, and Mermaid. Use when the user explicitly requests Obsidian note formatting or syntax help, not for general Markdown or broad vault operations.
wiki-fold
Create a bounded, extractive, structurally idempotent rollup of recent Obsidian wiki log entries, with dry-run preview by default and one optional transaction apply. Use for manual log compression without modifying child pages. Triggers: fold the log, run a fold, run wiki-fold, log rollup, roll up log entries, commit…
wiki-mode
Read or configure the vault filing methodology and suggest destinations for planned knowledge creation under Generic, LYT, PARA, or Zettelkasten. Use for wiki mode, methodology mode, what is my vault mode, set vault mode, switch to PARA, use LYT, Zettelkasten setup, change mode, configure mode, or methodology routing.…