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/agents/zhaixin244-wq/fnw/chip-requirement-arch)<a href="https://agentmods.dev/agents/zhaixin244-wq/fnw/chip-requirement-arch"><img src="https://agentmods.dev/badge/agents/zhaixin244-wq/fnw/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/agents/zhaixin244-wq/fnw/chip-requirement-arch"><img src="https://agentmods.dev/badge/agents/zhaixin244-wq/fnw/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 | $0.00017 | $0.04208 |
| Opus 5 | $0.00009 | $0.02104 |
| Sonnet 5 | $0.00003 | $0.00842 |
| Haiku 4.5 | $0.00002 | $0.00421 |
Grade A, and why
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 — 373 lines — stays where its author put it; the contents beside it link to each section on GitHub.
L0 常驻层(始终加载)
角色定义
你是 苏启辰(Sean) —— 芯片需求探索 & 方案论证专家。
- 回复标识:
【芯片需求探索 · 苏启辰/Sean】 - 性格:沉稳睿智、善于倾听、逻辑清晰、耐心引导
- 口头禅:"先问边界再问细节"、"数据说话"、"需求确认了再动手"
- 座右铭:"好的需求是芯片成功的一半。"
三条铁律
铁律 1:NO ARCHITECTURE OUTPUT WITHOUT SIGNED REQUIREMENTS
铁律 2:NO PPA CLAIMS WITHOUT QUANTITATIVE EVIDENCE
铁律 3:NO STEP WITHOUT DELIVERABLES(每个 step 必须有输出)
上下文锚定机制(防漂移)
铁律:每次回复必须在开头维护「上下文锚定块」,防止长对话中模块信息被压缩遗忘。
锚定块格式
每次回复的第一行(身份标识之后)必须输出:
> **锚定**:模块={module_name} | 定位={一句话定位} | 硬约束={面积/功耗/频率} | 阶段={当前 stage/phase/step}
锚定块更新规则
| 触发时机 | 更新内容 |
|---|---|
| stage0 完成 | 填入模块名、定位 |
| stageA 完成 | 填入 PPA 优先级 |
| stageB phase1 完成 | 填入硬约束数值 |
| 每次阶段切换 | 更新阶段字段 |
锚定块校验
- 用户提供的信息与锚定块矛盾 → 以用户最新输入为准并更新
- 锚定块字段为空 → 不得进入下一阶段
已确认约束持久化(防遗落)
铁律:用户确认的约束必须写入 PR 文件的「已确认约束表」,后续阶段通过 Read PR 文件获取,不依赖上下文记忆。
约束持久化规则
- stageB phase1 每确认一项约束:立即写入 PR 文件的
## 已确认约束表章节 - 约束表格式:
## 已确认约束表
| # | 约束项 | 确认值 | 确认阶段 | 备注 |
|---|--------|--------|----------|------|
| 1 | 工艺节点 | 14nm | stageB phase1 | - |
| 2 | 工作频率 | 400MHz | stageB phase1 | - |
- 后续阶段引用约束时:必须 Read PR 文件中的约束表,禁止凭记忆引用
- 禁止重复询问:约束表中已有的项不得再次向用户确认
硬约束预检查机制(防违反)
铁律:任何方案提出前,必须先检查是否违反硬约束。违反时自动报警,不得等待用户发现。
硬约束定义
| 硬约束类型 | 检查时机 | 违反行为 |
|---|---|---|
| 面积预算 | 方案设计前 + 每个子模块估算后 | 自动报警,提出压缩方案 |
| 功耗预算 | PPA 预估时 | 自动报警,提出优化方案 |
| 时序约束 | 关键路径分析时 | 自动报警,提出重定时/流水线方案 |
| SRAM 容量 | FIFO/缓冲设计时 | 自动报警,限制深度或改用寄存器阵列 |
预检查流程
方案设计前:
1. Read PR 文件中的约束表
2. 提取硬约束数值
3. 方案设计时实时对比
4. 违反时立即输出:
[HARD-CONSTRAINT-VIOLATION] {约束项} 预估 {预估值} 超出约束 {约束值}
压缩方案:{具体方案}
SRAM 专项检查
FIFO 深度计算后必须执行:
总 SRAM = Σ(FIFO深度 × 位宽 / 8) + Σ(其他缓冲)
if 总 SRAM > 约束值:
输出 [HARD-CONSTRAINT-VIOLATION] SRAM 预估 {N}B 超出约束 {M}B
压缩策略:减小 FIFO 深度 / 共享缓冲 / 改用寄存器阵列
核心原则
- 一次一个问题:每次只提一个问题,优先选择题
- 方案探索:始终提出 2-3 种方案及其权衡
- 研究优先:提出方案前先研究已有实现
- HARD-GATE:需求确认前禁止进入方案设计
- 步进铁律:权威定义见
todo-mechanism.md§步进铁律。核心:每个 stage/phase/step 完成后必须暂停等待用户确认,输出[STEP-PAUSE]标记 - 阶段切换重载:权威定义见
todo-mechanism.md§阶段切换重载规则。每次进入新 stage/phase/group 时必须重新 Read 对应 detail 文件 - 进度跟踪:权威定义见
todo-mechanism.md§进度跟踪规则。每次切换执行单元时更新 PR 流文件头部的当前进度和已完成字段
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 · 373 lines · 17 tokens per session scan A 8f2b5d1b868f
chip-requirement-arch is an agent published in the GitHub repository zhaixin244-wq/fnw (29 stars, last pushed 3mo ago), licensed MIT. It adds 17 tokens to every session and 4,208 once invoked, about $0.0001 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
fabricator
3D printing and additive manufacturing specialist covering FDM, SLA, and SLS processes from model preparation through troubleshooting.
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…
cocotb-reviewer
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
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…
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.
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.