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 agentmods add skills/zhaixin244-wq/fnw/chip-impl-parallel-devnpx skills add zhaixin244-wq/fnw --skill chip-impl-parallel-devgit 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-impl-parallel-dev)<a href="https://agentmods.dev/skills/zhaixin244-wq/fnw/chip-impl-parallel-dev"><img src="https://agentmods.dev/badge/skills/zhaixin244-wq/fnw/chip-impl-parallel-dev.svg" alt="Measured on agentmods" 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 | $0.01578 |
| Opus 5 | $0.00034 | $0.00789 |
| Sonnet 5 | $0.00014 | $0.00316 |
| Haiku 4.5 | $0.00007 | $0.00158 |
Grade A, and why
chip-impl-parallel-dev 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 6d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
并行开发 Skill
任务
多模块并行开发流程:分析→调度→集成→确认。
流程
Phase 1: Plan Mode 分析
- 用
Glob搜索{module}_work/ds/rtl/*.v获取子模块 RTL 文件列表。若文件不存在,暂停并提示用户 - 确认输入:PR/FS/UA 文档
- RAG 检索 CBB 依赖
- 划分模块,评估依赖关系
- 确定并行组(无依赖模块可并行)
输出格式:
### 模块开发清单
| 模块名 | 依赖 | 复杂度 | 预估工时 | 并行组 |
|--------|------|--------|----------|--------|
| buf_mgr | sync_fifo | 中 | 2h | Group-A |
| ctrl_fsm | 无 | 高 | 3h | Group-A |
| top_int | buf_mgr, ctrl_fsm | 低 | 1h | Group-B |
Phase 2: 并行 Subagent 开发
为每个可并行模块启动独立 subagent:
Agent({
description: "RTL 开发 - {模块名}",
subagent_type: "chip-code-writer",
prompt: "开发 {module_name} 模块 RTL..."
})
调度规则:
| 规则 | 说明 |
|---|---|
| 依赖优先 | 有依赖的模块必须等待依赖完成 |
| 无依赖并行 | 无依赖模块可同时启动 |
| 独立工作目录 | 每个模块使用独立 {module}_work/ |
| 独立检查 | 每个模块独立执行 Lint + 综合 |
Phase 3: 顶层集成
所有子模块完成后:
- 顶层 Lint 检查(ALL PASS)
- 顶层综合检查(ALL PASS + 面积达标)
- 检查模块间接口一致性
Phase 4: PR/FS/UA 确认
| 确认维度 | 检查方法 |
|---|---|
| 功能覆盖 | 对照 FS §4 功能列表 |
| 接口一致 | 对照 FS §6 接口定义 |
| PPA 达标 | 对照 FS §8 PPA 规格 |
| 需求追溯 | 对照 RTM(FS §14) |
冲突检测
监控路径
| 文件类型 | 路径模式 | 冲突级别 |
|---|---|---|
| 顶层 RTL | {module}_work/rtl/{top_module}.v |
Critical |
| CBB 清单 | {module}_work/ds/doc/*_cbb_list.md |
Major |
| SDC 约束 | {module}_work/syn/{top_module}.sdc |
Major |
| 子模块 RTL | {module}_work/rtl/{submodule}.v |
Info(独立目录不冲突) |
文件锁机制(跨平台)
Linux/macOS — flock 原子锁:
lock_file="{module}_work/.lock.{file_type}"
exec 200>"$lock_file"
if ! flock -n 200; then
echo "[CONFLICT] $lock_file held by $(cat $lock_file)"
exit 1
fi
echo "{agent_id}:$(date +%s)" >&200
# ... 执行 ...
exec 200>&- # 释放
Windows — PowerShell Mutex:
$mutex = New-Object System.Threading.Mutex($false, "Global\{module}_{file_type}")
if (-not $mutex.WaitOne(0)) {
Write-Error "[CONFLICT] Mutex held by another process"
exit 1
}
# ... 执行 ...
$mutex.ReleaseMutex()
$mutex.Dispose()
平台检测逻辑:
if command -v flock >/dev/null 2>&1; then
# Linux/macOS: 使用 flock
...
elif command -v powershell >/dev/null 2>&1; then
# Windows: 调用 PowerShell mutex
powershell -File lock.ps1 ...
else
# fallback: 文件存在性检查(有竞态风险,仅用于开发环境)
...
fi
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.
- 6d ago First seen · 157 lines · 68 tokens per session scan A 651d01662e7a
chip-impl-parallel-dev is a skill published in the GitHub repository zhaixin244-wq/fnw (28 stars, last pushed 3mo ago), licensed MIT. It adds 68 tokens to every session and 1,578 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 2026-08-30.
Other skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
doca-socket-relay
Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
hsb-flash
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.