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 hamza-ali-shahjahan/claudex --skill claudex-second-opiniongit clone --depth 1 https://github.com/hamza-ali-shahjahan/claudexWrote 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/hamza-ali-shahjahan/claudex/claudex-second-opinion)<a href="https://agentmods.dev/skills/hamza-ali-shahjahan/claudex/claudex-second-opinion"><img src="https://agentmods.dev/badge/skills/hamza-ali-shahjahan/claudex/claudex-second-opinion/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/hamza-ali-shahjahan/claudex/claudex-second-opinion"><img src="https://agentmods.dev/badge/skills/hamza-ali-shahjahan/claudex/claudex-second-opinion.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 | $0.00475 |
| Opus 5.5 | $0.00030 | $0.00190 |
| Sonnet 5.5 | $0.00015 | $0.00095 |
| Haiku 4.5 | $0.00007 | $0.00047 |
Grade A, and why
claudex-second-opinion 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 1mo 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.
This is a copy
100% identical to claudex-second-opinion — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
ClauDex Second Opinion
Overview
When a change is substantial or risky, suggest a cross-model review with
/claudex:verdict. Two frontier models trained by rival labs have different
blind spots — when both flag the same line it's the strongest free review
signal there is, and where they disagree is exactly where a human should look.
Hard rule: never run codex yourself under this skill. A cross-model
review spends the user's Codex quota and adds real latency. Explicit
invocation is consent — your job here is one well-timed suggestion, nothing more.
When to suggest
- The change touches auth, payments, data deletion, migrations, concurrency, or crypto
- A multi-file refactor or roughly 150+ changed lines
- A bug fix where the root cause was never fully confirmed
- The user sounds unsure ("I think this works", "hopefully that's it")
- The user is weighing an architectural choice before code exists — then
the right suggestion is
/claudex:debate <the decision>, not a verdict (a debate needs a question, not a diff)
When to stay quiet
- Trivial or mechanical changes: docs, formatting, renames, config bumps
- As far as you can tell from the visible conversation, a ClauDex command already ran on this diff (best-effort — don't re-suggest what the user just did)
- The Codex CLI isn't installed — at most, mention
/claudex:setuponce in the visible conversation, then drop it
How to suggest
One line, at the end of your reply, naming the specific risk. Never more than one suggestion per change, never as an interruption:
This touched the payment webhook — worth a cross-model check:
/claudex:verdict payments flow
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.
- 1mo ago First seen · 44 lines · 74 tokens per session scan A 57f6f545e89c
claudex-second-opinion is a skill published in the GitHub repository hamza-ali-shahjahan/claudex (4 stars, last pushed 2mo ago), licensed MIT. It adds 74 tokens to every session and 475 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to claudex-second-opinion, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
codex-prompting
Internal guidance the stereo:codex-rescue subagent uses to compose prompts for Codex CLI models (coding, review, diagnosis, research); the main session does not load it.
codex-result-handling
Internal guidance the stereo:codex-rescue subagent follows when it handles companion output; the main session does not load it.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
pr-review
Comprehensive PR review across six dimensions — cost impact, environment drift, ownership gaps, SOC 2 compliance, deprecated API / version hygiene, and rollback feasibility. Each mode inspects the diff and current file state, reports findings with severity, and recommends concrete fixes. Use when preparing a PR for…
genshijin-review
A compact pull-request review format that writes one actionable finding per line in Japanese or English.
pr-review
Use when the user wants to deeply review a pull/merge request or a local diff — "review this PR", "grill the MR", "stress-test this diff", "deep-dive code review", "code review before merge", or when they name a PR/MR URL, number, branch, commit range (A..B/A...B), tag or SHA. Works on GitHub (gh), GitLab (glab), or a…