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 metago-ai/metagolifeform --skill metago-code-review-deepgit clone --depth 1 https://github.com/metago-ai/metagolifeformWrote 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/metago-ai/metagolifeform/metago-code-review-deep)<a href="https://agentmods.dev/skills/metago-ai/metagolifeform/metago-code-review-deep"><img src="https://agentmods.dev/badge/skills/metago-ai/metagolifeform/metago-code-review-deep/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/metago-ai/metagolifeform/metago-code-review-deep"><img src="https://agentmods.dev/badge/skills/metago-ai/metagolifeform/metago-code-review-deep.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 | $0.00095 | $0.01084 |
| Opus 5.5 | $0.00038 | $0.00434 |
| Sonnet 5.5 | $0.00019 | $0.00217 |
| Haiku 4.5 | $0.00010 | $0.00108 |
Grade A, and why
metago-code-review-deep 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.
What it actually says
深度代码审查（metago-code-review-deep）
描述
对代码进行多维度分级审查，检测逻辑错误、安全漏洞、性能问题、可维护性缺陷、风格不一致。输出含修复建议和优先级的结构化报告。
触发条件
- 用户请求代码审查、PR Review、Code Review 时激活
- 代码提交前审查（pre-commit hook 场景）
- 与
metago-decision-lock协同：开发者任务输出代码时强制触发
核心流程
1. 静态结构分析
- 文件组织与模块划分是否合理
- 函数/类职责是否单一
- 依赖关系是否清晰（无循环依赖）
- 代码重复度检测（DRY 原则）
2. 逻辑正确性审查
- 边界条件处理（空值、极值、越界）
- 异常路径覆盖（错误处理、资源释放）
- 并发安全（竞态条件、死锁）
- 算法正确性（时间复杂度、空间复杂度）
3. 安全漏洞审查
- 注入漏洞（SQL/命令/XSS）
- 认证授权缺陷
- 敏感信息泄露（硬编码密钥、日志泄密）
- 依赖漏洞（已知 CVE）
4. 性能审查
- 数据库查询效率（N+1、全表扫描）
- 内存泄漏风险
- 不必要的同步阻塞
- 资源未释放（文件句柄、连接池）
5. 可维护性审查
- 命名清晰度（变量、函数、类）
- 注释完整度（复杂逻辑、公共 API）
- 单一职责原则遵循度
- 开闭原则遵循度
分级标准
| 级别 | 含义 | 处理时机 |
|---|---|---|
| 🔴 Critical | 必须立即修复（安全漏洞、数据丢失、崩溃） | 阻断合并 |
| 🟠 Major | 应在合并前修复（逻辑错误、性能严重问题） | 阻断合并 |
| 🟡 Minor | 建议修复（可维护性、风格） | 可后续修复 |
| 🔵 Info | 提示性建议（优化、最佳实践） | 仅记录 |
输出格式
【深度代码审查报告】
文件：path/to/file.ext
审查范围：函数/类/模块
总体评分：XX/100
🔴 Critical（N 项）
[C-001] 行 XX: 问题描述
影响：...
修复建议：...
依据：...
🟠 Major（N 项）
[M-001] 行 XX: 问题描述
影响：...
修复建议：...
🟡 Minor（N 项）
[m-001] 行 XX: 问题描述
建议改进：...
🔵 Info（N 项）
[i-001] 建议优化：...
审查结论：✅ 通过 / ❌ 需修复后重新审查
与其他技能的协同
- 与
metago-critique协同：审查过程应用 L1-L5 批判性分析 - 与
metago-fact-check协同：检测虚构 API、不存在的函数（幻觉代码） - 与
metago-decision-lock协同：审查报告需通过决策锁校验 - 与
metago-problem-trace协同：问题无限溯源至根本原因 - 与
metago-security-audit协同：安全维度联动深度安全审计 - 与
metago-refactor-suggest协同：可维护性问题联动重构建议
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 · 104 lines · 95 tokens per session scan A 414bfa0d3d2e
metago-code-review-deep is a skill published in the GitHub repository metago-ai/metagolifeform (5 stars, last pushed today), licensed MIT. It adds 95 tokens to every session and 1,084 once invoked, about $0.0004 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
codebase-design
Design maintainable module interfaces, review scoped code changes, and simplify implementations with behavioral verification. Use for code review, cleanup, testability, and module design work.
pr-blocker-summarizer
Summarizes open pull requests into a blockers-first standup digest. Activates when the user asks to summarize open PRs, find blocked pull requests, generate a PR standup, or triage review backlog from a PR export.
ponytail-lazy-senior-dev
Applies the "lazy senior developer" mindset. Use this skill whenever generating, modifying, reviewing code, or fixing bugs to prioritize code reuse, minimalism, YAGNI principles, and root-cause fixes. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni"…
review
Review Playwright tests for quality. Use when user says "review tests", "check test quality", "audit tests", "improve tests", "test code review", or "playwright best practices check".
tech-lead/code-review
A checklist-based method for examining code for correctness, security, performance, clarity, and ease of maintenance.
adr
Create and manage Architecture Decision Records. Documents significant technical decisions with context, alternatives, and consequences. Also supports evaluate (assess proposals) and design (system design) modes.