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.
npx skills add zhaixin244-wq/fnw --skill chip-protocol-compliance-checkergit 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/skills/zhaixin244-wq/fnw/chip-protocol-compliance-checker)<a href="https://agentmods.dev/skills/zhaixin244-wq/fnw/chip-protocol-compliance-checker"><img src="https://agentmods.dev/badge/skills/zhaixin244-wq/fnw/chip-protocol-compliance-checker/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/skills/zhaixin244-wq/fnw/chip-protocol-compliance-checker"><img src="https://agentmods.dev/badge/skills/zhaixin244-wq/fnw/chip-protocol-compliance-checker.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 | $0.00068 | $0.01166 |
| Opus 5 | $0.00034 | $0.00583 |
| Sonnet 5 | $0.00014 | $0.00233 |
| Haiku 4.5 | $0.00007 | $0.00117 |
Grade A, and why
chip-protocol-compliance-checker 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 9d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chip Protocol Compliance Checker
任务
检查模块接口架构是否符合选定总线协议的规范要求。
支持协议
- AXI4 / AXI4-Lite
- ACE / ACE-Lite
- CHI(AMBA 5)
- TileLink
- APB / AHB
执行步骤
- 获取 RTL 源码:
- 用
Glob搜索{module}_work/ds/rtl/*.v获取模块文件列表 - 用
Read读取目标模块 RTL,用Grep提取端口声明 - 若文件不存在,暂停并提示用户先完成 RTL 实现
- 用
- Wiki/RAG 知识检索:按
rag-mandatory-search.md协议,检索.claude/wiki/中对应协议规范页(如axi4_*),获取检查项清单 - 确认用户使用的协议版本与接口角色(Master/Slave/Interconnect)。若未指定,从端口名推断(
arvalid→Master,awready→Slave) - 逐条核对关键协议要求:
- 握手规则:VALID/READY 依赖关系、无组合路径、数据稳定性
- 事务排序:ID 扩展、out-of-order 支持、原子操作
- 缓存一致性(ACE/CHI/TileLink):Snoop 响应、脏数据回写、Shareability Domain
- 突发传输:Burst Type/Length、Wrap/Increment 规则、不对齐访问
- 地址映射:Region/Cache/Prot/ QoS 信号定义
- 低功耗接口(AXI4):CACTIVE/CSYSREQ/CSYSACK 时序
- 识别常见违规点:
- READY 依赖 VALID 的组合路径
- WLAST 与 AWLEN 不匹配
- 非法的 Burst Type 组合
- ID 位宽不足导致排序冲突
- 生成合规检查报告与整改建议。
输出格式
### 协议合规检查报告(协议:AXI4 | 角色:Slave)
| 检查项 | 规范来源 | 状态 | 发现 | 建议 |
|--------|----------|------|------|------|
| READY 不依赖 VALID | AXI4 §A3.2.1 | Pass | - | - |
| WLAST 与 AWLEN 匹配 | AXI4 §A3.4.1 | Fail | 最后一拍未正确置起 WLAST | 在 W 通道计数器中检查 |
**合规评分:X/Y (Z%)**
使用示例
示例 1:
- 用户:「检查 data_adpt 的 AXI4 Slave 接口是否合规」
- 行为:确认 AXI4 协议和 Slave 角色,逐条核对握手规则(READY 不依赖 VALID)、突发传输(Burst Type/Length)、WLAST 匹配等,输出合规检查报告
示例 2:
- 用户:「帮我验证 buf_mgr 的 APB 接口是否符合规范」
- 行为:核对 APB 时序(PSEL→PENABLE→PREADY 握手)、地址对齐、读写信号极性,输出合规评分
异常处理
| 场景 | 触发条件 | 处理动作 |
|---|---|---|
| 协议版本未指定 | 用户未明确 AXI4/ACE/CHI 版本 | 默认使用最新版本,标注 [PROTO-ASSUMED] |
| 接口信号缺失 | 端口列表不完整 | 列出缺失信号,标注 [PROTO-INCOMPLETE] |
| 协议规范文档缺失 | 无 Wiki/RAG 参考 | 基于通用知识检查,标注 [PROTO-GENERAL] |
| RTL 文件不存在 | 模块未实现 | 暂停,提示先完成 RTL 实现,标注 [RTL-MISSING] |
| 角色未指定 | 用户未说明 Master/Slave | 从端口名推断(ar*→Master, aw*→Slave),标注 [ROLE-INFERRED] |
与 chip-arch-reviewer 的关系
协议合规检查是架构评审的子集。若用户要求完整架构评审,应调用 chip-arch-reviewer Agent,本 skill 作为其协议检查步骤的详细展开。
检查点
检查前:
- 确认协议版本和接口角色已明确
- 确认模块端口列表已获取
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.
- 9d ago First seen · 85 lines · 68 tokens per session scan A 982c1b6ec155
chip-protocol-compliance-checker is a skill published in the GitHub repository zhaixin244-wq/fnw (29 stars, last pushed 3mo ago), licensed MIT. It adds 68 tokens to every session and 1,166 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
kicad-pcb-review
Use this skill when reviewing, fixing, validating, or preparing KiCad PCB projects with the kicad MCP server.
arch-review
Read-only architecture review of RTL vs uArch spec with area/timing/power tradeoffs. Use for post-RTL architecture sign-off or suspected spec mismatch.
rtl-review
Audit RTL code for lint violations, synthesis hazards, coding-style compliance, and readability. Use when the user says "review this Verilog", "check my RTL", "lint this module", "is this code synthesizable", or shares an HDL file and asks for feedback before simulation or tape-in.
cdc-tool-profiles
Internal reference: cdc tool profiles (agent-loaded; do not invoke).
kicad-pcb-review
KiCad PCB review and manufacturing readiness agent skill for Cursor.
argos-upload
Upload a screenshot, an image or a screen recording to Argos and get a shareable URL plus ready-to-paste Markdown, so it can be embedded in a pull request, an issue, a changelog or a chat message — or attached to a branch or pull request, where Argos posts and maintains the comment itself. Use whenever you have…