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.
git clone --depth 1 https://github.com/Cristhianzl/claude-skills-czlWrote 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/cristhianzl/claude-skills-czl/dual-review)<a href="https://agentmods.dev/commands/cristhianzl/claude-skills-czl/dual-review"><img src="https://agentmods.dev/badge/commands/cristhianzl/claude-skills-czl/dual-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/cristhianzl/claude-skills-czl/dual-review"><img src="https://agentmods.dev/badge/commands/cristhianzl/claude-skills-czl/dual-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 | $0.00019 | $0.00300 |
| Opus 5 | $0.00010 | $0.00150 |
| Sonnet 5 | $0.00004 | $0.00060 |
| Haiku 4.5 | $0.00002 | $0.00030 |
Grade A, and why
dual-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 12d 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.
What it actually says
Review the current diff with two independent reviewers that don't share context, then converge. This catches what a single pass (or a self-review) misses and kills anchoring bias — neither reviewer is the author, neither sees the other's findings until the end.
-
Run Reviewer A and Reviewer B independently — as two separate subagents / fresh contexts (launch them in parallel). Each applies the
reviewing-codeskill to the same diff and returns severity-labeled findings (Blocker / Important / Recommended / Nice-to-have) plus a verdict: approve / approve-with-nits / request-changes. Give them no hint of each other. -
Converge. Merge both reports and de-duplicate. A finding that either reviewer marks Blocker is a Blocker.
-
Verdict. Approved only if both reviewers return approve / approve-with-nits and there are no open Blockers. Otherwise, list exactly what must change.
-
Up to 2 rounds. After the author fixes the issues, re-run both reviewers fresh (new context). If still not converged after round 2, escalate to the human with the disagreement.
Output the merged review in chat following skills/reviewing-code/references/output-format.md. Never post to GitHub or run git.
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.
- 12d ago First seen · 16 lines · 19 tokens per session scan A 76c1092006f0
dual-review is a command published in the GitHub repository Cristhianzl/claude-skills-czl (5 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 300 once invoked, about $0.0001 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 commands, from other repositories
react-patterns
Review React code for performance and composition patterns — 50+ rules ranked by impact.
bugfix
IMPORTANT: You MUST run this shell command FIRST before doing anything else.
feature
IMPORTANT: You MUST run this shell command FIRST before doing anything else.
confirm-revisions
Toggle Second Pass re-judge after revision. true = verify lift in a loop (more tokens, more confidence). false = trust judge's feedback, ship after one revision (default, cheaper).
passing-grade
Set the Second Pass passing grade. Any output graded below this bar triggers a revision loop. Accepts A, B, C, D, or F.
strict
Set Second Pass to strict mode — passing grade A, iteration cap 5, confirm revisions on. For high-stakes artifacts (client proposals, public-facing copy).