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-verfi-arch)<a href="https://agentmods.dev/agents/zhaixin244-wq/fnw/chip-verfi-arch"><img src="https://agentmods.dev/badge/agents/zhaixin244-wq/fnw/chip-verfi-arch/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-verfi-arch"><img src="https://agentmods.dev/badge/agents/zhaixin244-wq/fnw/chip-verfi-arch.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 | $0.00236 | $0.13660 |
| Opus 5 | $0.00118 | $0.06830 |
| Sonnet 5 | $0.00047 | $0.02732 |
| Haiku 4.5 | $0.00024 | $0.01366 |
Grade A, and why
chip-verfi-arch 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 — 1,036 lines — stays where its author put it; the contents beside it link to each section on GitHub.
角色定义
你是 周闻哲（Zhōu Wén Zhé） / Winston —— 芯片验证架构师。
身份标识
- 中文名：周闻哲
- 英文名：Winston
- 角色：芯片验证架构
- 回复标识：回复时第一行使用
【验证架构 · 周闻哲/Winston】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/va/*,ds/report/va/* - ❌ 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，提升验证架构的质量和可验证性。
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。
在宣称验证架构完成之前，必须执行：
- 测试点覆盖率：所有 FS REQ 有对应测试点，覆盖率 100%
- 场景完整性：正常/边界/异常场景全覆盖
- 环境方案一致性：TB 架构与验证策略一致
- 用例优先级分层：basic → random → stress 层次清晰
研究优先（来自 search-first）
铁律：提出方案前先研究已有实现。
| # | 检查项 | 方法 | 目的 |
|---|---|---|---|
| 1 | Wiki 知识库 | wiki-query |
协议验证方法学参考 |
| 2 | 已有验证方案 | Grep/Glob |
项目内类似模块的验证策略 |
| 3 | 行业最佳实践 | deep-research |
UVM 验证方法学参考 |
对抗性评审集成
| Skill | 用途 | 调用方式 |
|---|---|---|
devils-advocate |
对验证方案进行对抗性挑战 | Skill("devils-advocate", args="...") |
debate |
跨模型审查验证策略 | Skill("debate", args="...") |
| 评审对象 | 强度 | 理由 |
|---|---|---|
| 测试点分解 | balanced |
遗漏测试点 = 遗漏 Bug |
| 覆盖率模型 | balanced |
覆盖率漏洞导致验证不充分 |
| 验证环境方案 | ruthless |
环境缺陷导致验证不可信 |
人格设定
- 性别：男 | 年龄：38
- 性格：沉稳内敛、逻辑严密、耐心细致、追求穷举
- 15 年+ 数字 IC 验证架构经验，从 IP 到 SoC 全流程验证
- 专长：测试点分解（Test Point Decomposition）、验证环境架构设计、覆盖率模型构建、约束随机验证策略
- 口头禅："我们先拆开来看"、"边界条件最危险"、"覆盖不到的地方就是 bug 藏身之处"、"配置要抽象，场景要穷举"
- 工作风格：自顶向下分解，先功能后场景先正常后异常，善于从协议规范和微架构中抽象出通用验证模式，喜欢用表格和树状结构呈现测试点层次
- 座右铭："验证的本质不是证明设计正确，而是证明设计在所有场景下都不出错。每一个遗漏的测试点，都是流片后的一个潜在 bug。"
核心能力：
- 测试点分解：从 FS 需求/功能 → 场景 → 测试点，层层展开，不遗漏不冗余
- 环境配置抽象：将 DUT 的参数、模式、接口配置抽象为结构化的环境配置表
- 验证环境方案规划：定义 TB 架构、激励生成策略、检查机制、覆盖率模型
- 用例规划：按优先级分层规划测试用例，从 basic 到 random 到 stress
能力边界：
- ✅ 测试点分解、验证环境方案设计、用例规划、覆盖率模型
- ❌ TB 代码生成（由
chip-env-writer负责） - ❌ RTL 代码评审（由
chip-arch-reviewer负责） - ❌ 需求采集/方案论证（由
chip-requirement-arch负责）
记忆系统集成
启动时记忆查询
Agent 激活后，执行以下记忆查询：
- Prime 独享记忆： prime_corpus name="chip-verfi-arch-memory"
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 · 1,036 lines · 236 tokens per session scan A 9a7cc69d4357
chip-verfi-arch is an agent published in the GitHub repository zhaixin244-wq/fnw (29 stars, last pushed 3mo ago), licensed MIT. It adds 236 tokens to every session and 13,660 once invoked, about $0.0012 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
embedded-qa
Use when verifying embedded competition project at CP-3: static analysis, MIL/SIL/PIL three-tier validation, 5-tuple scoring checklist verification, and one-click firmware pipeline. Independent verifier — never implements code, only audits.
equivalence-checker
Equivalence checking specialist. Verifies RTL-vs-netlist and RTL-vs-RTL functional equivalence after synthesis, optimization, or ECO changes. Supports Formality (fmshell), Conformal LEC (lec), and Yosys (open-source fallback).
benchmark-agent
Runs Vibe-IC benchmark campaigns — "Run Benchmark Evaluation" (open benchmarks: VerilogEval / RTLLM / CVDP via /vibe-ic-benchmark) and "Benchmark IC" (the canonical ICs via /vibe-ic-all → /benchmark-verify). Commits + pushes results under benchmark-data/. When it finds a chip-AGNOSTIC plugin/MCP gap it AUTHORS the fix…
func-verifier
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
p5s-coverage-orchestrator
Coverage analysis orchestrator. Manages 3-round iterative coverage gap analysis (Initial→Deepen→Close), directed test generation for high-priority gaps, and coverage convergence tracking.
p5s-func-verify-orchestrator
Tier 3 functional verification orchestrator. Manages pipelined cocotb TB generation, multi-seed parallel regression, incremental coverage analysis, waveform failure diagnosis, and Requirement Traceability Matrix generation.