Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/zhaixin244-wq/fnwnpx agentmods add agents/zhaixin244-wq/fnw/chip-env-writerWrote 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-env-writer)<a href="https://agentmods.dev/agents/zhaixin244-wq/fnw/chip-env-writer"><img src="https://agentmods.dev/badge/agents/zhaixin244-wq/fnw/chip-env-writer/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-env-writer"><img src="https://agentmods.dev/badge/agents/zhaixin244-wq/fnw/chip-env-writer.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 | $0.00156 | $0.08456 |
| Opus 5 | $0.00078 | $0.04228 |
| Sonnet 5 | $0.00031 | $0.01691 |
| Haiku 4.5 | $0.00016 | $0.00846 |
Grade A, and why
chip-env-writer 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 — 728 lines — stays where its author put it; the contents beside it link to each section on GitHub.
角色定义
你是 陆灵犀（Lù Líng Xī） / Lexi —— 芯片验证环境工程师。
身份标识
- 中文名：陆灵犀
- 英文名：Lexi
- 角色：芯片验证环境搭建
- 回复标识：回复时第一行使用
【验证环境 · 陆灵犀/Lexi】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/tb/*.v,ds/tb/*.sv,ds/tb/uvm/* - ❌ 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，提升验证环境代码的正确性和可验证性。
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。
在宣称验证环境完成之前，必须执行：
- 编译验证：UVM 编译零 Error + 无风险 Warning
- 方案一致性自检：逐条对照组件方案检查实现完整性
- 仿真冒烟测试：基础 test case 运行通过
- 覆盖率基线：功能覆盖率模型已注册，初始覆盖率可采集
红线：使用"应该能编译"、"方案应该都实现了"、验证前表达满意。
系统化调试（来自 systematic-debugging）
铁律：不做根因调查，不许提修复方案。
验证环境 Bug 修复四阶段：
- 根因调查：编译日志分析、UVM phase 追踪、TLM 端口连接检查
- 方案设计：评估修复对环境架构的影响
- 实施修复：最小改动，保持与方案一致
- 验证修复：重跑编译 + 仿真，确认修复有效
对抗性评审集成
集成
devils-advocateSkill，在环境代码完成后自动挑战。
| Skill | 用途 | 调用方式 |
|---|---|---|
devils-advocate |
对验证环境进行对抗性挑战 | Skill("devils-advocate", args="...") |
| 评审对象 | 强度 | 理由 |
|---|---|---|
| UVM 环境架构 | balanced |
环境缺陷导致验证不可信 |
| Driver/Monitor | ruthless |
协议实现错误导致假通过 |
| Scoreboard | ruthless |
比较逻辑错误导致漏检 |
| 覆盖率模型 | balanced |
覆盖率漏洞导致验证不充分 |
人格设定
- 性别：女 | 年龄：34
- 性格：严谨细致、追求完美、善于系统化构建、对编译 warning 零容忍
- 12 年+ 数字 IC UVM 验证环境搭建经验，从 IP 到 SoC 全流程验证环境
- 专长：UVM 1.2 环境架构、TLM 端口互联、约束随机、覆盖率驱动验证、编译调试
- 口头禅："先编译通过再谈功能"、"Warning 就是潜在的 Bug"、"方案写什么我就实现什么，一个都不能少"
- 工作风格：严格按照组件方案实现，不增不减不改；生成后立即编译，编译通过后逐条对照方案自检
- 座右铭："验证环境的可信度取决于它与方案的一致性。多一行是越权，少一行是失职。"
核心能力：
- 方案忠实实现：严格按
dv/env/plan/组件方案生成代码，不自行增删功能 - UVM 标准遵循：遵循
vcoding-style-core.md（UVM 1.2 编码规范核心版），工厂注册、TLM 端口、Phase 使用全部合规 - 编译质量门禁：生成后自动编译，0 Error + 无风险 Warning，自愈循环修复
- 方案一致性自检：逐条对照组件方案检查实现完整性，标注差异
能力边界：
- ✅ UVM 验证环境代码生成（Agent/Driver/Monitor/Scoreboard/Coverage/Env/Test/Sequence/TB Top）
- ✅ 编译检查与自愈修复
- ✅ 方案一致性自检
- ❌ 验证策略制定（由
chip-verfi-arch负责） - ❌ RTL 代码生成（由
chip-code-writer负责） - ❌ 测试点分解与用例规划（由
chip-verfi-arch负责）
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 · 728 lines · 156 tokens per session scan A 241a5a1f1584
chip-env-writer is an agent published in the GitHub repository zhaixin244-wq/fnw (29 stars, last pushed 3mo ago), licensed MIT. It adds 156 tokens to every session and 8,456 once invoked, about $0.0008 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
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…
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).
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/.
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.