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 skills add zhaixin244-wq/fnw --skill chip-arbiter-selectorgit 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-arbiter-selector)<a href="https://agentmods.dev/skills/zhaixin244-wq/fnw/chip-arbiter-selector"><img src="https://agentmods.dev/badge/skills/zhaixin244-wq/fnw/chip-arbiter-selector/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/skills/zhaixin244-wq/fnw/chip-arbiter-selector"><img src="https://agentmods.dev/badge/skills/zhaixin244-wq/fnw/chip-arbiter-selector.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 | $0.00084 | $0.01814 |
| Opus 5 | $0.00042 | $0.00907 |
| Sonnet 5 | $0.00017 | $0.00363 |
| Haiku 4.5 | $0.00008 | $0.00181 |
Grade A, and why
chip-arbiter-selector 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
仲裁策略选择器
基于公平性需求和饥饿风险评估，选择合适的仲裁策略。chip-code-writer 在 RTL 编码阶段调用。
输入
| 参数 | 类型 | 必需 | 说明 |
|---|---|---|---|
| scenario | string | 是 | 仲裁场景描述 |
| channel_count | int | 是 | 仲裁通道数 |
| request_pattern | string | 是 | 请求模式：continuous（持续流）/ bursty（突发流）/ mixed（混合） |
| qos_requirements | object[] | 否 | 各通道 QoS 要求（带宽/延迟） |
| protocol_priority | string | 否 | 协议规定的优先级（如有） |
输出
| 参数 | 类型 | 说明 |
|---|---|---|
| strategy | string | fixed_priority / round_robin / weighted_rr |
| starvation_risk | string | high / medium / low |
| reason | string | 选择理由 |
| implementation_notes | string | RTL 实现要点 |
策略选择规则
固定优先级（Fixed Priority）适用条件（需全部满足）
- 无并发饥饿：高优先级请求不会持续阻塞低优先级
- 请求模式：请求到达是突发性的，非持续流
- 协议要求：上游协议明确规定优先级
Round-Robin 适用条件（任一满足）
- 公平性要求：各通道需平等带宽
- 持续流场景：请求持续到达，可能造成饥饿
- 多通道竞争：3+ 通道同时竞争共享资源
Weighted Round-Robin 适用条件
- 差异化 QoS：各通道有不同带宽要求
- 非均匀负载：通道间负载差异 > 2x
饥饿风险评估矩阵
| 风险等级 | 请求模式 | 优先级策略 | QoS 要求 | 推荐策略 |
|---|---|---|---|---|
| 高风险 | 持续流 | 固定优先级 | 低优先级通道有 QoS | 必须用 RR |
| 中风险 | 突发流 | 固定优先级 | 低优先级通道有延迟要求 | 建议用 RR |
| 低风险 | 突发流 | 固定优先级 | 无 QoS 要求 | 可用固定优先级 |
| 无风险 | 突发流 | - | 无并发 | 可用固定优先级 |
执行步骤
分析请求模式 → 评估饥饿风险 → 检查 QoS 要求 → 选择策略 → 输出实现要点
输出格式
## 仲裁策略选择报告
**场景**：{scenario}
**通道数**：{channel_count}
**请求模式**：{request_pattern}
### 饥饿风险评估
| 评估项 | 结果 |
|--------|------|
| 请求模式 | {continuous/bursty/mixed} |
| 优先级策略 | {固定/无} |
| QoS 要求 | {有/无} |
| 风险等级 | {high/medium/low} |
### 策略选择
**推荐策略**：{fixed_priority / round_robin / weighted_rr}
**理由**：{reason}
### RTL 实现要点
{implementation_notes}
实战案例
| 场景 | 请求模式 | 通道数 | QoS | 风险 | 策略 | 原因 |
|---|---|---|---|---|---|---|
| 4ch RAM 请求仲裁 | 持续流 | 4 | 无 | 高 | RR | 各通道平等，需防饥饿 |
| pending 通道选择 | 持续流 | 4 | 无 | 高 | RR | 多通道竞争，公平性重要 |
| debubble buffer 输出 | 突发流 | 2 | 无 | 低 | 固定优先级 | 不会同时满足，无饥饿风险 |
| output_if_mod ready_q_push | 突发流 | N | 无 | 低 | 固定优先级 | node 动态分配，近似 FIFO |
| W1/W2 SRAM 写冲突 | 突发流 | 2 | 协议规定 | 低 | 固定优先级 (W2优先) | 协议要求，W2 是返回数据 |
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 · 169 lines · 84 tokens per session scan A d5fcfb117c43
chip-arbiter-selector is a skill published in the GitHub repository zhaixin244-wq/fnw (29 stars, last pushed 3mo ago), licensed MIT. It adds 84 tokens to every session and 1,814 once invoked, about $0.0004 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.