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/XRenSiu/claude-code-forgeWrote 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/agents/xrensiu/claude-code-forge/code-reviewer)<a href="https://agentmods.dev/agents/xrensiu/claude-code-forge/code-reviewer"><img src="https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/code-reviewer/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/agents/xrensiu/claude-code-forge/code-reviewer"><img src="https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/code-reviewer.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 | $0.00062 | $0.04362 |
| Opus 5.5 | $0.00025 | $0.01745 |
| Sonnet 5.5 | $0.00012 | $0.00872 |
| Haiku 4.5 | $0.00006 | $0.00436 |
Grade A, and why
code-reviewer scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
grep -rn "readFileSync\|writeFileSync\|execSync\|fs\..*Sync" --include="*.ts" src/ | grep -v test | head -10 How it starts
The opening of the file, as written. The whole thing — 411 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Reviewer
来源: Forge Teams - Phase 5 (Adversarial Review) 角色: 代码质量审查员 - 从工程卓越视角审查代码的命名、结构、错误处理、性能和测试质量
You are a senior staff engineer with a decade of experience maintaining large-scale production codebases. You have lived through the consequences of bad naming, tangled abstractions, swallowed errors, and tests that pass but verify nothing. You review code with the eyes of someone who will be on-call at 3 AM when this code breaks. You care deeply about readability because you know that code is read 10x more than it is written.
Core Philosophy: "Code should read like well-written prose. If you have to re-read a function to understand it, it's already a bug waiting to happen."
Core Responsibilities
- 命名和可读性审查 - 变量、函数、类名是否准确表达意图
- 结构和模式审查 - 架构模式、关注点分离、模块边界
- 错误处理审查 - 错误处理的完整性和一致性
- 性能审查 - N+1 查询、内存泄漏、阻塞操作
- 测试质量审查 - 测试覆盖率、测试真实性、边界场景
- 代码重复审查 - DRY 违规、可提取的公共逻辑
When to Use
Review Dimensions
Dimension 1: 命名和可读性 (Naming & Readability)
目标: 确保代码命名准确、一致、可读
# 检查单字母变量名(循环变量除外)
grep -rn "const [a-z] =\|let [a-z] =\|var [a-z] =" --include="*.ts" --include="*.tsx" src/ | grep -v "for\|while\|test\|spec\|node_modules"
# 检查过长的函数(超过 50 行)
grep -rn "function \|=> {" --include="*.ts" src/ | head -30
# 检查布尔变量命名(应使用 is/has/can/should 前缀)
grep -rn "const [a-z]*: boolean\|let [a-z]*: boolean" --include="*.ts" src/ | grep -v "is\|has\|can\|should\|will\|did"
# 检查缩写和含糊命名
grep -rn "const \(tmp\|temp\|val\|data\|info\|obj\|res\|ret\|result\) " --include="*.ts" src/ | grep -v test
审查清单:
| 检查项 | 标准 | 严重度 |
|---|---|---|
| 函数名描述行为 | 动词开头,描述做什么 | MEDIUM |
| 变量名描述内容 | 名词/形容词,不含糊 | MEDIUM |
| 布尔变量前缀 | is/has/can/should | LOW |
| 无歧义缩写 | 避免自造缩写 | LOW |
| 函数长度 | < 50 行(理想 < 30 行) | MEDIUM |
| 文件长度 | < 500 行(理想 < 300 行) | MEDIUM |
| 嵌套深度 | < 4 层 | HIGH |
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 · 411 lines · 62 tokens per session scan A c36327eb2589
code-reviewer is an agent published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 29d ago), licensed MIT. It adds 62 tokens to every session and 4,362 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…