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/commands/zhaixin244-wq/fnw/test-chip-requirement-arch)<a href="https://agentmods.dev/commands/zhaixin244-wq/fnw/test-chip-requirement-arch"><img src="https://agentmods.dev/badge/commands/zhaixin244-wq/fnw/test-chip-requirement-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/commands/zhaixin244-wq/fnw/test-chip-requirement-arch"><img src="https://agentmods.dev/badge/commands/zhaixin244-wq/fnw/test-chip-requirement-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 | $0.00000 | $0.04038 |
| Opus 5 | $0.00000 | $0.02019 |
| Sonnet 5 | $0.00000 | $0.00808 |
| Haiku 4.5 | $0.00000 | $0.00404 |
Grade A, and why
test-chip-requirement-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 11d 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 — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.
调试 chip-requirement-arch
调试芯片需求探索 Agent 的流程与质量。通过双 Agent 自动对话验证流程完整性。
用法
/test-chip-requirement-arch [scenario_id]
可用场景
| 场景 ID | 名称 | 描述 | 用户角色 |
|---|---|---|---|
basic_dma |
基础 DMA | 标准流程测试 | clear_expert |
complex_pcie |
复杂 PCIe | 高级场景测试 | clear_expert |
vague_input |
模糊输入 | 边界测试 | vague_beginner |
edge_cases |
边界条件 | 异常处理测试 | challenging_reviewer |
complex_random |
复杂模块随机 | 从 50 个 40k+ RTL 模块池随机选择,覆盖全部测试维度 | 随机(E/C/V) |
复杂模块池(complex_random)
50 个面向 4 万行以上 RTL 的复杂模块,覆盖 10 个技术领域:
- 互联:PCIe Gen5 RC、CXL 3.0、UCIe、CHI、HBM3、NoC、PCIe Switch、PCIe/CXL 混合交换、PCIe Gen5 PHY
- 存储:NVMe 2.0、DDR5、RAID、ZNS、压缩引擎、NVMe-oF、NAND Flash、DDR5 PHY
- 网络:100G MAC、交换矩阵、DPU SmartNIC、P4 解析器、10G PHY、TSN、RDMA NIC
- 计算:NPU 卷积、GPU Shader、RISC-V 向量/乱序、DSP、AI SoC 互联、张量核心、稀疏加速、Transformer
- 安全:国密加密、安全飞地
- 多媒体:8K 编解码、ISP、显示控制器、音频 DSP
- 汽车:ADAS 融合、CAN-FD 网关
- 内存:LLC、CXL 内存交换
- 可重构:CGRA 加速器、FPGA 重配置
- IO:USB4 Hub、MIPI CSI-2、USB 3.2、HDMI 2.1
- SoC 基础设施:GICv4 中断控制器
详细模块列表和覆盖矩阵见 scenarios/complex_modules/README.md。
执行流程
- 初始化:读取场景配置和用户角色
- 启动对话:用户 Agent 发送初始输入
- 循环执行:双 Agent 交替对话直到完成
- 质量评估:检查流程完整性和交付物质量
- 生成报告:输出对话记录和评估报告
输出位置
.claude/debug/chip-requirement-arch/debug_output/{scenario}_{timestamp}/
├── dialog.md # 完整对话记录
├── evaluation.md # 质量评估报告
├── summary.md # 调试摘要
└── outputs/ # 生成的交付物
示例
# 运行基础 DMA 场景
/test-chip-requirement-arch basic_dma
# 运行模糊输入场景
/test-chip-requirement-arch vague_input
# 运行复杂模块随机场景(从 50 个 40k+ RTL 模块中随机选择)
/test-chip-requirement-arch complex_random
评估标准
复用 .claude/evaluation_criteria/chip-requirement-arch-eva.md 中的评估标准。
执行指令
当用户调用此命令时,执行以下步骤:
1. 解析参数
scenario_id = $1 (默认: basic_dma)
2. 加载配置
标准场景(basic_dma / complex_pcie / vague_input / edge_cases):
场景配置: .claude/debug/chip-requirement-arch/scenarios/{scenario_id}.json
用户角色: .claude/debug/chip-requirement-arch/user-personas/{user_persona}.json
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.
- 11d ago First seen · 339 lines · 0 tokens per session scan A c6e4deb6aeed
test-chip-requirement-arch is a command published in the GitHub repository zhaixin244-wq/fnw (29 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,038 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.