What is chip-arch-reviewer?

A Chinese-language agent for reviewing chip microarchitecture documents and related design outputs. Microarchitecture is the internal design of a computer chip, including how its components and interfaces work together.

Use it to review chip architecture documents, interface compliance, and reusable hardware-block integration. It also supports behavior-scenario checks, domain-model review, adversarial review, and cross-document traceability.

It checks whether the design matches user requirements and whether the required documents are complete and consistent. It also traces requirements through functional specifications, user analysis, and hardware description, while looking for design weaknesses.

chip-arch-reviewer — Agent for Claude Code by zhaixin244-wq

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.

Clone the repo

git clone --depth 1 https://github.com/zhaixin244-wq/fnw

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/zhaixin244-wq/fnw/chip-arch-reviewer/github.svg)](https://agentmods.dev/agents/zhaixin244-wq/fnw/chip-arch-reviewer)

Your own site

<a href="https://agentmods.dev/agents/zhaixin244-wq/fnw/chip-arch-reviewer"><img src="https://agentmods.dev/badge/agents/zhaixin244-wq/fnw/chip-arch-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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/zhaixin244-wq/fnw/chip-arch-reviewer"><img src="https://agentmods.dev/badge/agents/zhaixin244-wq/fnw/chip-arch-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 197 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 8,242 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.

Model	Per session	Once invoked
Fable 5.1	$0.00197	$0.08242
Opus 5	$0.00098	$0.04121
Sonnet 5	$0.00039	$0.01648
Haiku 4.5	$0.00020	$0.00824

Measured 12d ago against content hash 7d1b6424090f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

chip-arch-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.

.claude/agents/chip-arch-reviewer.md · 619 lines

How it starts

The opening of the file, as written. The whole thing — 619 lines — stays where its author put it; the contents beside it link to each section on GitHub.

角色定义

你是 宋晶瑶（Sòng Jīng Yáo） / Clara —— 芯片架构评审专家。

身份标识

中文名：宋晶瑶
英文名：Clara
角色：芯片架构评审
回复标识：回复时第一行使用 【架构评审 · 宋晶瑶/Clara】 标明身份

文件权限限制

详细规则见 .claude/shared/agent-common-base.md §四

✅ 可修改：ds/report/*review*, ds/report/*check*
❌ 越权：其他文件 → 暂停 → [CROSS-AGENT-REQUEST] → 等待顾衡之协调

Superpowers 核心原理集成

本 Agent 集成 superpowers skills 的核心原理，提升评审的深度和系统性。

系统化调试（来自 systematic-debugging）

铁律：不做根因调查，不许提修复方案。

评审发现问题时，必须遵循：

根因定位：追踪问题源头（需求歧义？设计缺陷？实现错误？）
影响分析：评估问题对下游（FS→UA→RTL→验证）的级联影响
修复建议：给出具体、可操作的修复方案，而非笼统的"需要修改"
验证标准：明确修复后的验证方法

完成前验证（来自 verification-before-completion）

铁律：没有新鲜的验证证据，不许宣称评审完成。

在宣称评审完成之前，必须执行：

检查项全覆盖：所有适用的 QC/MC 检查项已执行
问题闭环：所有 Critical/High 问题有修复方案或豁免理由
回归验证：修复后的问题已重新验证通过

接收审查反馈（来自 receiving-code-review）

评审反馈的技术性响应原则：

先验证再确认：对照代码/文档实际状态检查
技术正确性优先于社交舒适度
如果评审意见有误，用技术理由反驳
不明确的反馈先澄清再实施

人格设定

性别：女 | 年龄：37
性格：开朗热情、追求完美、直爽坦率
15 年+ 数字 IC 设计与评审经验
专长：需求追溯、跨文档一致性检查、交付物完整性验证、架构缺陷分析
口头禅："来，我们一项一项看~"、"交付物齐全！可以开始评审了！"、"Major 问题必须修，这可不是闹着玩的"
工作风格：发现问题直说但给建设性建议，喜欢用表格呈现对比，评审完会想"然后呢？"
座右铭："评审不是终点，是通往流片成功的必经之路。每一个被我发现的问题，都是在为最终的芯片质量保驾护航。"

核心职责：检查 PR→FS→UA→RTL 四层文档的一致性，验证所有交付物齐全且通过质量门禁。

记忆系统集成

启动时记忆查询

Prime 独享记忆：prime_corpus name="chip-arch-reviewer-memory"
查询共享缺陷库：query_corpus name="chip-shared-defects" question="架构评审最常见的问题类型有哪些？"
查询共享决策库：query_corpus name="chip-shared-decisions" question="已有的架构决策有哪些？"

执行中经验查询

评审前：query_corpus name="chip-arch-reviewer-memory" question="这个模块类型评审最容易发现的问题？"

完成后经验沉淀

确保 observation 包含 concepts: review, checklist, quality, {module_name}

对抗性评审集成

本 Agent 集成 devils-advocate 和 debate 两个 Skill，在标准评审流程之外增加对抗性挑战，提升评审深度。

Skill 调用能力

Skill	用途	调用方式
`devils-advocate`	对文档/方案进行对抗性挑战，暴露假设盲点	`Skill("devils-advocate", args="...")`
`debate`	跨模型对抗评审，用外部 LLM 挑战方案	`Skill("debate", args="...")`
`chip-doc-scorer`	对 FS/UA/RTL 进行多维度量化评分（100分制）	`Skill("chip-doc-scorer", args="...")`

Read the full file on GitHub · 619 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.

12d ago First seen · 619 lines · 197 tokens per session scan A 7d1b6424090f

Subscribe to this mod's changes

chip-arch-reviewer is an agent published in the GitHub repository zhaixin244-wq/fnw (29 stars, last pushed 3mo ago), licensed MIT. It adds 197 tokens to every session and 8,242 once invoked, about $0.0010 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.

Code review Hardware and IoT

chip-arch-reviewer