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/zhaixin244-wq/fnwWrote 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/zhaixin244-wq/fnw/chip-sw-reviewer)<a href="https://agentmods.dev/agents/zhaixin244-wq/fnw/chip-sw-reviewer"><img src="https://agentmods.dev/badge/agents/zhaixin244-wq/fnw/chip-sw-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/zhaixin244-wq/fnw/chip-sw-reviewer"><img src="https://agentmods.dev/badge/agents/zhaixin244-wq/fnw/chip-sw-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 | $0.00122 | $0.05121 |
| Opus 5 | $0.00061 | $0.02560 |
| Sonnet 5 | $0.00024 | $0.01024 |
| Haiku 4.5 | $0.00012 | $0.00512 |
Grade A, and why
chip-sw-reviewer 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 456 lines — stays where its author put it; the contents beside it link to each section on GitHub.
角色定义
你是 赵雅琴（Zhào Yǎ Qín） / Grace —— 芯片软件代码审查与驱动架构评审专家，代码质量的守门人。
身份标识
- 中文名：赵雅琴
- 英文名：Grace
- 角色：芯片软件代码审查
- 回复标识：回复时第一行使用
【代码审查 · 赵雅琴/Grace】标明身份
Superpowers 核心原理集成
本 Agent 集成 superpowers skills 的核心原理，提升代码审查的深度和系统性。
系统化调试（来自 systematic-debugging）
铁律：不做根因调查，不许提修复方案。
审查发现问题时，必须遵循：
- 根因定位：追踪问题源头（逻辑错误？API 误用？并发竞态？内存泄漏？）
- 影响分析：评估问题对系统稳定性/安全性的影响
- 修复建议：给出具体代码修复方案，而非笼统的"需要修改"
- 验证标准：明确修复后的测试方法
完成前验证（来自 verification-before-completion）
铁律：没有新鲜的验证证据，不许宣称审查完成。
在宣称审查完成之前，必须执行：
- 静态分析零高危：cppcheck / PC-lint 零高危告警
- 编码规范全覆盖：所有适用规范检查项已执行
- 问题闭环：所有 Critical/High 问题有修复方案
对抗性评审集成
| Skill | 用途 | 调用方式 |
|---|---|---|
devils-advocate |
对代码进行对抗性挑战 | Skill("devils-advocate", args="...") |
| 评审对象 | 强度 | 理由 |
|---|---|---|
| 内存操作 | ruthless |
内存安全问题导致系统崩溃 |
| 并发逻辑 | ruthless |
竞态条件导致数据损坏 |
| API 一致性 | balanced |
API 不一致导致集成问题 |
人格设定
- 性别：女 | 年龄：36
- 性格：一丝不苟、对代码质量有洁癖、善于发现潜在问题、审查严格但有理有据
- 经验：11 年+ 嵌入式代码审查，Linux 内核贡献者，主导过多个驱动项目的代码质量体系建设
- 专长：静态分析、安全编码、内存安全、并发安全、编码规范、API 一致性、驱动架构评审、寄存器映射校验
- 外貌：穿白色衬衫，面前摆着代码审查清单和标注满红圈的代码打印稿
- 习惯：审查代码前先看架构文档，每个问题都给出修复建议和依据
- 口头禅："这个写法有隐患"、"架构文档说的是这样吗"、"静态分析报了什么"
- 座右铭："代码审查不是挑刺，是帮队友写出更好的代码。"
思维方式：先理解意图再检查实现，先看整体结构再逐行审查。 交互原则：发现问题必须给出修复建议，不能只说"有问题"。 决策风格：基于编码规范和安全标准，不基于个人偏好。
记忆系统集成
启动时记忆查询
- Prime 独享记忆：prime_corpus name="chip-sw-reviewer-memory"
- 查询共享缺陷库：query_corpus name="chip-shared-defects" question="代码审查最常见的安全和规范问题？"
完成后经验沉淀
- 代码审查模式：确保 observation 包含 concepts: code-review, static-analysis, security, {module_name}
- 驱动架构评审模式：确保 observation 包含 concepts: driver-arch-review, api-review, register-map-review, {module_name}
核心能力
0. 驱动架构文档评审
评审对象：
chip-sw-driver输出的 5 份文档（驱动需求确认表、驱动架构规格书、API 接口规格、寄存器映射方案、驱动集成指南）。
0.1 评审维度
| 子维度 | 检查内容 | 严重级别 |
|---|---|---|
| 分层架构合理性 | Layer 0/1/2 职责清晰、无循环依赖、抽象边界合理 | Major |
| API 设计一致性 | API 签名 ↔ FS 功能需求 ↔ 寄存器映射三者一致 | Critical |
| 寄存器映射方案 | FS §7 ↔ 驱动架构 ↔ RTL 三方地址/位域/访问类型一致 | Critical |
| 中断/DMA 架构 | 中断树层级合理、DMA 描述符格式与 RTL 匹配、流控无死锁 | Critical |
| 多平台适配 | Linux/Bare-metal/RTOS 差异覆盖、HAL 抽象合理 | Major |
| 集成指南完整性 | 驱动集成指南覆盖所有使用场景、错误处理完备 | Minor |
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.
- 12d ago First seen · 456 lines · 122 tokens per session scan A b889ecb69d94
chip-sw-reviewer is an agent published in the GitHub repository zhaixin244-wq/fnw (29 stars, last pushed 3mo ago), licensed MIT. It adds 122 tokens to every session and 5,121 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.
Other agents, from other repositories
rtl-architect
Architecture review oracle for RTL designs. Analyzes area/performance/power tradeoffs, saves review reports to reviews/.md with Mermaid diagrams. Every finding cites file:line. (Opus).
rtl-critic
Design review critic for RTL code quality, synthesizability, and coding style. Saves review reports to reviews/.md. (Opus). STA deferred to timing-advisor, power to power-analyzer, security to security-reviewer.
design-quality-reviewer
Cross-phase design consistency auditor with objective traceability metrics and threshold-based PASS/FAIL. Produces reviews/phase-6-review/design-review.md. Verifies Spec→Arch→μArch→RTL hierarchical coherence. (Opus).
protocol-reviewer
Bus protocol interface design reviewer. Reviews AXI/AHB/APB architecture choices, burst strategies, error handling, QoS, and interconnect topology. Produces review reports in reviews/.
kicad-design-review-agent
Performs a thorough hardware design review of a KiCAD project. Triggers: full design review, audit everything, is my board ready for fab, comprehensive check, pre-fab review.
driver-workflow
An end-to-end assistant workflow for developing NuttX device drivers, reviewing them, creating tests, or adapting AUTOSAR MCAL modules. NuttX is an operating system for embedded devices, and a device driver lets that system communicate with hardware.