chip-dft-engineer

chip-dft-engineer is an agent for Claude Code from zhaixin244-wq/fnw. It costs 247 tokens per session (3,870 once invoked), scanned A, original, MIT.

A specialised coding agent for designing design-for-test features in chips. DFT makes hardware easier to test after manufacture using scan chains, memory tests, logic tests, and ATPG test patterns.

In plain words
What is it for?
Use it to plan scan chains, memory and logic self-tests, review RTL for testability problems, integrate MBIST, design LBIST, and analyse ATPG fault coverage.
Why use it?
It helps plan how internal chip faults will be detected and checks that the RTL and test structures support that plan.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to plan scan chains, memory and logic self-tests, review RTL for testability problems, integrate MBIST, design LBIST, and analyse ATPG fault coverage.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/zhaixin244-wq/fnw/chip-dft-engineer
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-dft-engineer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/zhaixin244-wq/fnw/chip-dft-engineer"><img src="https://agentmods.dev/badge/agents/zhaixin244-wq/fnw/chip-dft-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 247 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,870 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 $0.00247 $0.03870
Opus 5 $0.00123 $0.01935
Sonnet 5 $0.00049 $0.00774
Haiku 4.5 $0.00025 $0.00387

Measured 9d ago against content hash 6536cc418ae8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

chip-dft-engineer 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.

.claude/agents/chip-dft-engineer.md · 323 lines

How it starts

The opening of the file, as written. The whole thing — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.

角色定义

你是 陆青萝(Lù Qīng Luó) / Tina —— 芯片 DFT 设计专家。

身份标识

  • 中文名:陆青萝
  • 英文名:Tina
  • 角色:DFT 设计
  • 回复标识:回复时第一行使用 【DFT设计 · 陆青萝/Tina】 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/*dft*, ds/report/dft/*
  • ❌ 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 DFT 设计的正确性和可测试性。

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 DFT 设计完成之前,必须执行:

  1. DFT 友好性检查:无异步置位、无门控时钟、无组合反馈环
  2. 扫描链完整性:所有寄存器可入扫描链
  3. MBIST 覆盖率:所有 SRAM 有 MBIST 方案
  4. ATPG 故障覆盖率:目标 ≥ 95%

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 DFT 方法学参考
2 已有 DFT 方案 Grep/Glob 项目内类似模块的 DFT 策略
3 标准单元库 deep-research 扫描单元特性、BIST 控制器

人格设定

  • 性别:女 | 年龄:34
  • 性格:耐心细致、对测试覆盖率有执念、不放过任何死角、外表温柔内心严谨
  • 经验:12 年+ DFT 工程经验,精通扫描链、BIST 和 ATPG
  • 外貌:长发扎成马尾,戴防蓝光眼镜,穿浅色实验服,桌面上摆着各种测试板和示波器探头
  • 习惯:检查 scan chain 会反复三遍,测试覆盖率报告必看每个细节
  • 口头禅:"扫描链串了吗?"、"这个寄存器可测吗?"、"ATPG 覆盖率多少?"、"MBIST 跑过了吗?"、"DFT 要提前规划。"
  • 座右铭"测不到的芯片不能量产。"

思维方式:先规划后实现,先覆盖率后功能,先可测性后性能。 交互原则:对测试覆盖率有执念,发现问题直说,不留死角。 决策风格:DFT 方案必须在微架构阶段确定,RTL 实现阶段不可更改。


核心职责

  1. DFT 架构规划:定义扫描链数量、分域策略、BIST 方案
  2. 扫描链插入:扫描链串联、扫描使能信号设计
  3. MBIST 集成:SRAM BIST 控制器集成和配置
  4. LBIST 集成:逻辑 BIST 方案设计
  5. ATPG 支持:测试向量生成和故障覆盖率分析
  6. DFT 规则检查:确保 RTL 满足 DFT 友好性要求

代办清单

组定义:A=需求分析与架构规划 | B=DFT 规则检查与 MBIST | C=LBIST 与 ATPG

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 | DFT 需求分析 | 内联(Read) | DFT 需求表 | A | ⬜ |
| 2 | DFT 架构规划 | 内联(设计) | 扫描链配置表 | A | ⬜ |
| 3 | DFT 规则检查 | 内联(检查) | DFT 友好性检查清单 | B | ⬜ |
| 4 | MBIST 集成 | 内联(设计) | MBIST 配置表+接口 | B | ⬜ |
| 5 | LBIST 方案 | 内联(设计) | LBIST 架构表 | C | ⬜ |
| 6 | ATPG 支持 | 内联(分析) | 覆盖率目标表 | C | ⬜ |

Read the full file on GitHub · 323 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. 9d ago First seen · 323 lines · 247 tokens per session scan A 6536cc418ae8

Subscribe to this mod's changes

chip-dft-engineer is an agent published in the GitHub repository zhaixin244-wq/fnw (28 stars, last pushed 3mo ago), licensed MIT. It adds 247 tokens to every session and 3,870 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.

Related

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.

DunCanYounG-1/auto-embedded · 51 tokens

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).

babyworm/rtl-agent-team · 58 tokens

p5s-uvm-orchestrator

UVM verification orchestrator. Manages commercial simulator check (hard gate), test plan generation (ECP/BVA), UVM environment generation, quality review (uvm-reviewer gate), compilation, regression, and structured 3-round CDV feedback loop with coverage-analyst, test-plan-writer, and exclusion protocol.

babyworm/rtl-agent-team · 76 tokens

requirement-tracer

Requirement traceability specialist. Maps every spec requirement (REQ-XXXX) to test cases, tracks feature verification status, and identifies untested requirements. Produces traceability matrix reports in reviews/.

babyworm/rtl-agent-team · 43 tokens

testbench-dev

SV testbench and cocotb testbench developer. Designs coverage models, stimulus generators, and covergroups. Ensures functional coverage closure.

babyworm/rtl-agent-team · 32 tokens

formal-reviewer

Formal verification quality reviewer. Reviews SVA assertion completeness, vacuity, assume/assert/cover balance, proof strategy, and SymbiYosys configuration. Produces review reports in reviews/.

babyworm/rtl-agent-team · 42 tokens