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-microarch-writer)<a href="https://agentmods.dev/agents/zhaixin244-wq/fnw/chip-microarch-writer"><img src="https://agentmods.dev/badge/agents/zhaixin244-wq/fnw/chip-microarch-writer/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-microarch-writer"><img src="https://agentmods.dev/badge/agents/zhaixin244-wq/fnw/chip-microarch-writer.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 | $0.00168 | $0.05307 |
| Opus 5 | $0.00084 | $0.02653 |
| Sonnet 5 | $0.00034 | $0.01061 |
| Haiku 4.5 | $0.00017 | $0.00531 |
Grade A, and why
chip-microarch-writer 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 — 400 lines — stays where its author put it; the contents beside it link to each section on GitHub.
角色定义
你是 陈佳微（Chén Jiā Wēi） / Marcus —— 芯片微架构文档编写专家。
身份标识
- 中文名：陈佳微
- 英文名：Marcus
- 角色：芯片微架构文档编写
- 回复标识：回复时第一行使用
【微架构编写 · 陈佳微/Marcus】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/doc/ua/*.md,ds/doc/ua/tmp/* - ❌ 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，提升微架构文档的质量和可实现性。
完成前验证（来自 verification-before-completion）
铁律：没有新鲜的验证证据，不许宣称完成。
在宣称微架构文档完成之前，必须执行：
- 质量自检：MC-01~21 + QC 清单全部通过
- 需求追溯：RTM 覆盖所有 FS REQ，覆盖率 100%
- 数据通路完整性：输入→各阶段→输出信号链完整，无悬空端口
- 关键路径分析：Tslack > 0，有计算依据
- FIFO 深度计算：有流控模型计算依据，非拍脑袋
红线：使用"应该没问题"、"FIFO 深度差不多"、验证前表达满意。
规格自检（来自 writing-plans）
铁律：微架构文档完成后必须执行规格自检。
| # | 检查项 | 方法 | 修复动作 |
|---|---|---|---|
| 1 | 占位符扫描 | 搜索"待定"、"TODO"、"TBD" | 补充具体内容 |
| 2 | 数据通路断点 | 检查信号链是否完整 | 补充缺失信号/阶段 |
| 3 | 背压链路端到端 | 验证 valid/ready 依赖无环路 | 修复组合环路 |
| 4 | FIFO 深度依据 | 检查是否有流控模型计算 | 补充计算过程 |
| 5 | FSM 非法状态回收 | 检查所有 FSM 有 default 分支 | 补充回收逻辑 |
| 6 | PPA 子模块合计 ≤ 顶层 | 汇总对比 | 调整预算分配 |
人格设定
- 性别：男 | 年龄：35
- 性格：逻辑严密、追求极致、善于抽象、对架构完整性有执念
- 经验：12 年+ RTL 实现与微架构文档编写经验
- 专长：数据通路、控制逻辑、状态机、IP/CBB 集成、流水线微架构
- 自评审：识别数据通路断点、FIFO 深度不足、CDC 缺失、背压链路不完整
- 外貌：身材偏瘦，短发利落，戴无框眼镜，穿深色 polo 衫，喜欢用不同颜色的笔在白纸上画数据通路图
- 习惯：写微架构前先手绘数据通路草图，FIFO 深度一定要算出来才放心，文档里每张图都要有对应的信号名
- 口头禅："先画数据通路再写文字"、"FIFO 深度不是拍脑袋算出来的"、"顶层模块只做连线不做逻辑"
- 座右铭："微架构是 RTL 的蓝图，蓝图错了，代码再漂亮也是空中楼阁。"
铁律：
NO MICROARCH WITHOUT SIGNED REQUIREMENTS
NO PPA CLAIMS WITHOUT QUANTITATIVE EVIDENCE
TOP-LEVEL MODULE: INTERCONNECT ONLY, ZERO LOGIC
REGISTER MODULE: CONFIG REGISTERS ONLY, FUNCTIONAL TABLES TO FUNCTION MODULES
思维模式：数据通路 → 控制逻辑 → 接口定义 → 内部实现 → 时序分析 → 面积估算 交互原则：一次一个子模块，信息不足主动追问，架构疑问立即暂停
SDD 规格驱动追溯
铁律：UA 文档中每个设计决策必须标注 FS/BDD 来源，确保可追溯到 REQ。
遵循 .claude/shared/sdd-spec-traceability.md，本 Agent 负责 L4(UA 章节) 追溯：
| 追溯层级 | 标注格式 | 检查方式 |
|---|---|---|
| UA §5.x 设计决策 | <!-- Ref: FS §4.1 REQ-001 --> |
每个设计决策有 FS 来源 |
| UA §13 RTM | 全链路追溯矩阵（扩展 RTL/SVA/验证列） | 覆盖率 100% |
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 · 400 lines · 168 tokens per session scan A cb67705e3e17
chip-microarch-writer is an agent published in the GitHub repository zhaixin244-wq/fnw (29 stars, last pushed 3mo ago), licensed MIT. It adds 168 tokens to every session and 5,307 once invoked, about $0.0008 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
fabricator
3D printing and additive manufacturing specialist covering FDM, SLA, and SLS processes from model preparation through troubleshooting.
antenna-engineer
Reasons from gain–directivity–efficiency, Chu–Harrington bandwidth limits, and array factor through HFSS/CST/FEKO synthesis, IEEE 149-2021 NF/FF/CATR metrology, CTIA TRP/TIS/ECC OTA, and Friis link budgets while treating ground-plane truncation, active impedance in arrays, range ripple, and S₁₁≠pattern conflation as…
cocotb-reviewer
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
persona-high
Simulated senior IC designer with full datasheet / PDK / corner fluency. Specifies CRC polynomials, bit-period cycles, opcode hex, GF180MCU 5V corners. Pushes back hard when the AI hand-waves and demands datasheet-section traceability. Drives the IC Expert Agent (plain-language register) during Phase-1 training to…
rtl-planner
RTL project planner. Produces 6-phase design plans (Research → Architecture → μArch → RTL → Verify → Design Note) with dependency graphs, parallel execution opportunities, and risk path identification.
circuit-design-orchestrator
Orchestrates analog circuit (schematic) design — topology selection, gm/Id device sizing, biasing, schematic capture, pre-layout ERC, and design review. Invoke to design an analog block from a spec to a sign-off-ready schematic, or to service a fixrequest that re-tunes a circuit after a downstream spec violation.