code-review

code-review is a skill for Claude Code from lync-cyber/CataForge. It costs 114 tokens per session (5,691 once invoked), scanned A, original, MIT.

A code-review tool for checking business code against requirements, coding rules, security expectations, and tests. It also scans a whole project for signs of decay such as duplicated, unused, or overly complex code.

In plain words
What is it for?
Use it to review a task's changed code or scan the project's src/ directory before a release or when looking for code decay. It produces a report and does not change the reviewed code.
Why use it?
It helps find correctness, security, style, and maintainability problems before release. It reports issues with severity so developers know what needs attention.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: reads .claude/ paths.

Good fit Use it to review a task's changed code or scan the project's src/ directory before a release or when looking for code decay. It produces a report and does not change the reviewed code.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lync-cyber/cataforge/code-review
Install

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.

Any agent
npx skills add lync-cyber/CataForge --skill code-review
Clone the repo
git clone --depth 1 https://github.com/lync-cyber/CataForge

Made for: Claude Code.

Wrote 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.

agentmods badge for code-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/lync-cyber/cataforge/code-review.svg)](https://agentmods.dev/skills/lync-cyber/cataforge/code-review)
Your own site
<a href="https://agentmods.dev/skills/lync-cyber/cataforge/code-review"><img src="https://agentmods.dev/badge/skills/lync-cyber/cataforge/code-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,691 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00114 $0.05691
Opus 5 $0.00057 $0.02846
Sonnet 5 $0.00023 $0.01138
Haiku 4.5 $0.00011 $0.00569

Measured 7d ago against content hash 2b719e6ce584, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

code-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 7d 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.

.cataforge/skills/code-review/SKILL.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

代码评审 (code-review)

能力边界

  • 能做: 功能正确性对照(实现 vs AC/契约)、代码质量审查、命名/风格规范检查、安全漏洞检测、架构合规验证、测试质量审查、项目级腐化指标扫描(重复/死码/复杂度)
  • 不做: 修改代码(仅报告问题)、需求评审;任务依赖图由 task-dep-analysis 负责

输入规范

  • 代码文件或目录(DEV产出)
  • arch#§7开发约定(命名/风格/Git约定)
  • arch#§5非功能架构(安全/错误处理)

输出规范

  • 任务粒度审查: CODE-REVIEW-{task_id}-r{N}.md(问题列表 + 严重等级: CRITICAL/HIGH/MEDIUM/LOW)
  • 项目级扫描: CODE-SCAN-{YYYYMMDD}-r{N}.md(腐化指标聚合 + 严重等级)
  • 审查结论: approved/approved_with_notes/needs_revision

操作指令: 任务粒度评审 (review)

Step 1: Layer 1 — Lint脚本自动检查

前置判断: 读取当前平台 Hook 配置(Claude: .claude/settings.json;Cursor: .cursor/hooks.json),检查是否存在 matcher 为 Edit|Write(Cursor 可为 Write/StrReplace)且 command 包含 lint_format.py 的条目:

  • 已配置 lint hook → 编码阶段已通过 hook 以 --fix 模式实时修复格式/lint问题,跳过 Layer 1,直接进入 Step 2 Layer 2,并在审查报告标题下标注 Layer 1 delegated to hook
  • 未配置 lint hook → 执行: cataforge skill run code-review -- review {file_or_dir}

调用约定: 入口与返回码语义按 COMMON-RULES §Layer 1 调用协议。本 skill 增量:exit 1 时可追加 --fix 自动修复后重新检查——--fix 就地改写被审文件,执行权属仅限 implementer(continuation)/ tdd-engine / lint hook 语境,reviewer 角色(禁改被审对象)禁用,遇 convention 类 finding 记入报告由 implementer continuation 修复;未知参数与非法 --focus 值为用法错误(exit 2);两个模式均支持 --format json 输出结构化 finding(Layer 2 与报告聚合的机读输入)。

工具适配与检查清单见 §Layer 1 检查项;工具不存在时自动跳过并 WARN,不阻断检查流程。

Step 2: Layer 2 — AI语义审查

语言细则: 进入语义审查前,根据 framework.json project.languages,按需载入本 skill references/lang-<lang>.md(仅 active 语言,逐个 Read),作为该语言的评审细则(坏味道、安全陷阱、缺陷模式、性能反模式、评审 checklist)。这是散文评审参考,与 §Plugin-style rules 的 rules/*.yaml(Layer 1 机检 wiring)互补、不重复。

Layer 2 短路条件(降低轻量任务的审查开销,类比 doc-review §Layer 2 短路):

满足以下任一条件且 Layer 1 exit 0 时跳过 Layer 2 直接判定为 approved:

  1. 任务卡 task_kind ∈ CODE_REVIEW_L2_SKIP_TASK_KINDS(默认 [chore, config, docs]
  2. 任务卡 tdd_mode: light + AC 数 ≤ CODE_REVIEW_L2_SKIP_LIGHT_MAX_AC + Layer 1 输出无 security/error-handling 类 finding
  3. 调度方声明 layer1-only 降级(由 ORCHESTRATOR-META-PROTOCOLS §Adaptive Review 反向降级触发;这是 Layer 2 编排参数,不传入 Layer 1 CLI——CLI 只认 review|scan 子命令与 --fix/--focus/--format,未知参数报 exit 2)

Read the full file on GitHub · 168 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 7d ago First seen · 168 lines · 114 tokens per session scan A 2b719e6ce584

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository lync-cyber/CataForge (128 stars, last pushed 1mo ago), licensed MIT. It adds 114 tokens to every session and 5,691 once invoked, about $0.0006 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 2026-08-30.