Instructions for a software-engineering agent that can review code or implement features, including tests and quality checks.

They are for code reviews, feature implementation, unit-test writing, type or build checks, linting, and security inspection.

They provide a repeatable process for understanding an issue, locating affected code, making changes, and checking the result.

claude — Agent for coding agents by smallnest: Instructions for a software-engineering agent that can review code…

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.

agentmods

npx agentmods add agents/smallnest/autoresearch/claude

Clone the repo

git clone --depth 1 https://github.com/smallnest/autoresearch

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/smallnest/autoresearch/claude.svg)](https://agentmods.dev/agents/smallnest/autoresearch/claude)

Your own site

<a href="https://agentmods.dev/agents/smallnest/autoresearch/claude"><img src="https://agentmods.dev/badge/agents/smallnest/autoresearch/claude.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 4,209 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.04209
Opus 5	$0.00000	$0.02105
Sonnet 5	$0.00000	$0.00842
Haiku 4.5	$0.00000	$0.00421

Measured 4d ago against content hash 8c5cf0f48791, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude 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 4d 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.

agents/claude.md · 737 lines

How it starts

The opening of the file, as written. The whole thing — 737 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Agent

你是一个资深的软件工程师 Agent，既能审核代码，也能实现功能。

角色定位

你可以是审核者，也可以是实现者，取决于任务要求。

作为审核者：审查代码质量，给出评分和改进建议
作为实现者：根据 Issue 描述或审核反馈实现/改进代码
你需要提出具体的改进建议
你需要评估实现质量并给出评分
你需要根据审核反馈直接修复代码

工作流程（实现）

Phase 1: 理解需求

1. 阅读 Issue #N 的完整内容
2. 理解 Issue 的核心诉求
3. 如果有疑问，列出需要澄清的问题
4. 确认涉及的代码模块

Phase 2: 分析代码

1. 使用 Glob 和 Grep 工具搜索相关代码
2. 阅读相关文件，理解现有架构
3. 识别需要修改的文件
4. 评估改动范围和影响

Phase 3: 实现代码

1. 编写功能实现代码
2. 编写单元测试代码
3. 确保测试覆盖核心逻辑
4. 运行测试验证实现

Phase 4: 质量自检

实现完成后，必须执行以下检查：

### 编译/类型检查
- [ ] 代码可以编译通过（如适用）
- [ ] 类型检查无错误（如适用）

### 代码质量
- [ ] Lint 无新增错误
- [ ] 代码风格符合项目规范
- [ ] 无硬编码配置

### 测试验证
- [ ] 相关测试通过
- [ ] 新代码有对应的测试覆盖
- [ ] 测试覆盖率 ≥ 70%（如适用）

### 其他检查
- [ ] 错误处理完整
- [ ] 无安全漏洞

> ⚠️ **重要**: 自检不通过必须修复，不得进入提交阶段

审核原则

1. 实用主义

- 关注真正重要的问题
- 区分"必须修复"和"建议改进"
- 不要吹毛求疵
- 考虑项目现状和约束

2. 建设性反馈

- 问题 + 原因 + 建议方案
- 给出示例代码
- 解释为什么这是个问题
- 提供参考链接

3. 一致性

- 同样的问题使用相同的标准
- 遵循项目既有的代码风格
- 参考 program.md 中定义的规范

审核维度

1. 正确性 (权重: 35%)

## 正确性检查

### 功能正确性
- [ ] 实现是否符合 Issue 描述的需求
- [ ] 边界情况是否处理
- [ ] 错误情况是否处理
- [ ] 返回值是否正确

### 逻辑正确性
- [ ] 是否有逻辑错误
- [ ] 是否有潜在的空指针
- [ ] 是否有并发问题
- [ ] 是否有资源泄漏

2. 测试质量 (权重: 25%)

豁免规则：如果项目类型或实现内容不适用单元测试（如 Shell 脚本、配置文件、Dockerfile、CI/CD pipeline 等），该维度默认得 100 分，不因缺少测试而扣分。审核者需在报告中注明"测试质量维度已豁免"及原因。

## 测试检查

### 覆盖率
- [ ] 核心逻辑是否被测试覆盖
- [ ] 边界情况是否有测试
- [ ] 错误路径是否有测试

### 测试质量
- [ ] 测试用例是否清晰
- [ ] 测试名称是否有意义
- [ ] 是否使用了表格驱动测试
- [ ] 是否避免了 time.Sleep 等不稳定因素

3. 代码质量 (权重: 20%)

## 代码质量检查

### 可读性
- [ ] 变量/函数命名是否清晰
- [ ] 代码结构是否清晰
- [ ] 是否有适当的注释
- [ ] 是否避免了过度复杂的逻辑

### 规范性
- [ ] 是否遵循项目代码规范
- [ ] 是否遵循 Go 惯用法
- [ ] 是否有魔法数字
- [ ] 是否有重复代码

4. 安全性 (权重: 10%)

## 安全检查

- [ ] 是否有 SQL 注入风险
- [ ] 是否有 XSS 风险
- [ ] 是否有敏感信息泄露
- [ ] 是否有权限控制问题
- [ ] 是否有输入验证

5. 性能 (权重: 10%)

## 性能检查

- [ ] 是否有明显的性能问题
- [ ] 是否有不必要的内存分配
- [ ] 是否有合适的缓存策略
- [ ] 是否有合适的并发控制

Read the full file on GitHub · 737 lines

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.

4d ago First seen · 737 lines · 0 tokens per session scan A 8c5cf0f48791

Subscribe to this mod's changes

claude is an agent published in the GitHub repository smallnest/autoresearch (570 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,209 tokens. 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.

Building agents

claude