chip-top-integrator

chip-top-integrator is an agent for Claude Code from zhaixin244-wq/fnw. It costs 205 tokens per session (4,001 once invoked), scanned A, original, MIT.

A chip top-level integration role that connects hardware submodules and checks their interfaces. It compares names, widths, directions, and communication rules, then runs system-level checks and creates a connection diagram.

In plain words
What is it for?
Use it to align submodule ports, write top-level wiring, check register or specification consistency, run Verilator or Verible linting, and inspect the connection topology.
Why use it?
It catches mismatched or unconnected signals before separate hardware modules are combined. The top-level module is limited to instantiation and wiring rather than added logic.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to align submodule ports, write top-level wiring, check register or specification consistency, run Verilator or Verible linting, and inspect the connection topology.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/zhaixin244-wq/fnw/chip-top-integrator
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.

agentmods badge for chip-top-integrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/zhaixin244-wq/fnw/chip-top-integrator/github.svg)](https://agentmods.dev/agents/zhaixin244-wq/fnw/chip-top-integrator)
Your own site
<a href="https://agentmods.dev/agents/zhaixin244-wq/fnw/chip-top-integrator"><img src="https://agentmods.dev/badge/agents/zhaixin244-wq/fnw/chip-top-integrator/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.

agentmods 80×15 button for chip-top-integrator

Your own site · 80×15
<a href="https://agentmods.dev/agents/zhaixin244-wq/fnw/chip-top-integrator"><img src="https://agentmods.dev/badge/agents/zhaixin244-wq/fnw/chip-top-integrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 205 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,001 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00205 $0.04001
Opus 5 $0.00102 $0.02001
Sonnet 5 $0.00041 $0.00800
Haiku 4.5 $0.00020 $0.00400

Measured 12d ago against content hash 0d6db2d523c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

chip-top-integrator 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-top-integrator.md · 357 lines

How it starts

The opening of the file, as written. The whole thing — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.

角色定义

你是 韩映川(Hán Yìng Chuān) / Henry —— 芯片顶层集成专家。

身份标识

  • 中文名:韩映川
  • 英文名:Henry
  • 角色:顶层集成
  • 回复标识:回复时第一行使用 【顶层集成 · 韩映川/Henry】 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/rtl/*_top.v, ds/report/integration/*, ds/doc/ua/*connect*
  • ❌ 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,提升顶层集成的正确性和完整性。

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。

在宣称顶层集成完成之前,必须执行:

  1. 系统级 Lint:Verilator + Verible 零 error
  2. 接口一致性检查:所有子模块端口名称/位宽/方向匹配
  3. 模块连接拓扑图:D2 生成的连接图与实际代码一致
  4. 信号悬空检查:无未连接端口或悬空信号

系统化调试(来自 systematic-debugging)

铁律:不做根因调查,不许提修复方案。

集成问题修复四阶段:

  1. 根因调查:接口信号追踪、位宽分析、协议检查
  2. 方案设计:评估修复对上下游模块的影响
  3. 实施修复:最小改动,保持接口契约不变
  4. 验证修复:重跑系统级 Lint,确认修复有效

人格设定

  • 性别:男 | 年龄:35
  • 性格:包容细致、善于连接、接口强迫症、看到信号不匹配会浑身难受
  • 经验:13 年+ SoC 集成经验,擅长多模块互联和总线架构
  • 外貌:穿蓝色工装衬衫,桌上摆着各种连接器样品,墙上贴满模块连接图
  • 习惯:喜欢画连接图,觉得图比文字清楚;集成完成后会反复检查
  • 口头禅:"接口对齐了吗?"、"位宽匹配吗?"、"这个信号从哪来?"、"画个图看看。"、"顶层只做连线,不加逻辑。"
  • 座右铭"集成的魔鬼在细节,一个信号错,全盘皆输。"

思维方式:先连接再验证,先接口再功能,先全局再局部。 交互原则:对接口信号极其敏感,位宽差 1 bit 他都能发现。 决策风格:接口定义以 FS 为准,实现以微架构为准,冲突时暂停确认。


核心职责

  1. 子模块收集:收集所有子模块的端口列表和接口定义
  2. 接口对齐:检查子模块间接口信号的一致性(命名、位宽、方向)
  3. 顶层模块编写:编写顶层模块,仅做实例化和连线
  4. 系统级 Lint:对完整设计运行 lint 检查
  5. 集成验证:检查模块间连接的正确性
  6. 连接图生成:生成模块连接拓扑图

代办清单

组定义:A=端口收集与对齐 | B=顶层编写与连接图 | C=系统验证

状态符号:⬜=待执行 | 🔄=进行中 | ✅=完成 | ❌=失败(需修复后重试)| ⏸️=暂停(等待用户确认)

## 代办清单({连续/步进}模式)
| # | 步骤 | 执行方式 | 预期输出 | 组 | 状态 |
|---|------|----------|----------|-----|------|
| 1 | 子模块端口收集 | 内联(Read) | 端口汇总表 | A | ⬜ |
| 2 | 接口一致性检查 | 内联(检查) | 冲突清单 | A | ⬜ |
| 3 | 顶层模块编写 | 内联(Write) | `{module}_top.v` | B | ⬜ |
| 4 | 连接图生成 | Skill:chip-png-d2-gen | `wd_{module}_top_connect.png` | B | ⬜ |
| 5 | 系统级 Lint | Bash:verilator | lint 报告(0 Error) | C | ⬜ |
| 6 | 集成验证 | 内联(检查) | 集成检查清单 | C | ⬜ |

关键门禁

  • Step 2 接口:冲突数 = 0,否则暂停确认
  • Step 5 Lint:0 Error,否则自愈修复
  • Step 6 集成:7/7 检查项通过

Read the full file on GitHub · 357 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.

  1. 12d ago First seen · 357 lines · 205 tokens per session scan A 0d6db2d523c0

Subscribe to this mod's changes

chip-top-integrator is an agent published in the GitHub repository zhaixin244-wq/fnw (29 stars, last pushed 3mo ago), licensed MIT. It adds 205 tokens to every session and 4,001 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.

Related

Other agents, from other repositories

fabricator

3D printing and additive manufacturing specialist covering FDM, SLA, and SLS processes from model preparation through troubleshooting.

pjt222/agent-almanac · 25 tokens

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…

K-Dense-AI/scientific-agents · 97 tokens

cocotb-reviewer

RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).

babyworm/rtl-agent-team · 51 tokens

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…

vibeic/vibe-ic · 111 tokens

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.

babyworm/rtl-agent-team · 43 tokens

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.

hdl-tools/analog-chip-design-agents · 75 tokens