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/qqabcv520/my-claude-marketplacesWrote 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/qqabcv520/my-claude-marketplaces/cxreview)<a href="https://agentmods.dev/commands/qqabcv520/my-claude-marketplaces/cxreview"><img src="https://agentmods.dev/badge/commands/qqabcv520/my-claude-marketplaces/cxreview/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/qqabcv520/my-claude-marketplaces/cxreview"><img src="https://agentmods.dev/badge/commands/qqabcv520/my-claude-marketplaces/cxreview.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 | $0.00030 | $0.00725 |
| Opus 5.5 | $0.00012 | $0.00290 |
| Sonnet 5.5 | $0.00006 | $0.00145 |
| Haiku 4.5 | $0.00003 | $0.00072 |
Grade A, and why
cxreview scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Codex Code Review
使用 Codex CLI 对代码进行深度审查。
执行流程
Step 1: 确定审查模式
如果用户没有提供参数，使用 AskUserQuestion 询问审查模式：
请选择代码审查模式：
1. 未提交变更 - 审查当前工作区的未提交改动
2. 特定 commit - 审查某个具体的 commit
3. 分支对比 - 对比当前分支与基础分支的所有变更
Step 2: 根据模式调用 Codex
模式 1：未提交变更
mkdir -p tmp
REVIEW="tmp/codex-review-$RANDOM.txt"
codex exec -o "$REVIEW" "Review the uncommitted changes in this repository. Run git diff and git diff --cached to see all changes. Provide a code review covering: code quality, potential bugs, security issues, and improvement suggestions." --full-auto &> /dev/null
模式 2：特定 commit
mkdir -p tmp
REVIEW="tmp/codex-review-$RANDOM.txt"
codex exec -o "$REVIEW" "Review commit <sha>. Run git show <sha> to see the changes. Provide a code review covering: code quality, potential bugs, security issues, and improvement suggestions." --full-auto &> /dev/null
模式 3：分支对比
mkdir -p tmp
REVIEW="tmp/codex-review-$RANDOM.txt"
codex exec -o "$REVIEW" "Review all changes between the current branch and <base-branch>. Run git diff <base-branch>...HEAD to see the diff. Provide a code review covering: code quality, potential bugs, security issues, and improvement suggestions." --full-auto &> /dev/null
Step 3: 读取并展示审查结果
cat "$REVIEW"
将审查结果完整展示给用户，包括：
- 代码质量问题
- 潜在 bug
- 安全风险
- 改进建议
参数解析
当用户提供参数时，直接解析并执行：
/codex:cxreview uncommitted→ 执行模式 1（未提交变更审查）/codex:cxreview commit abc123→ 执行模式 2，将<sha>替换为abc123/codex:cxreview branch feature/my-feature→ 执行模式 3（询问 base branch）/codex:cxreview branch feature/my-feature --base develop→ 执行模式 3，将<base-branch>替换为develop
使用示例
/codex:cxreview
/codex:cxreview uncommitted
/codex:cxreview commit a1b2c3d
/codex:cxreview branch feature/login --base main
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 · 77 lines · 30 tokens per session scan A 878bb2db6b49
cxreview is a command published in the GitHub repository qqabcv520/my-claude-marketplaces (2 stars, last pushed 7mo ago), licensed MIT. It adds 30 tokens to every session and 725 once invoked, about $0.0001 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.
cxreview compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cxreviewqqabcv520/my-claude-marketplaces | Command | 2 | 7mo ago | MIT | A | 30 | Claude Code |
| diff-reviewcoco-research/coco | Command | 628 | yesterday | Apache-2.0 | A | 11 | Claude Code |
| review-branchdamusix/atomic-claude | Command | 116 | 5d ago | MIT | A | 35 | Claude Code |
| initazrtydxb/procoder | Command | 211 | yesterday | Apache-2.0 | A | 16 | Claude Code |
| refactorRchGrav/claudebox | Command | 1.2k | 1mo ago | MIT | A | 9 | Claude Code |
| spec-trace-requirementsrjmurillo/ai-agents | Command | 49 | today | MIT | A | 0 | GitHub Copilot |
| merge-conflict-analysisrjmurillo/ai-agents | Command | 49 | today | MIT | A | 0 | GitHub Copilot |