Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/agents/open-vela/.claude/driver-workflow)<a href="https://agentmods.dev/agents/open-vela/.claude/driver-workflow"><img src="https://agentmods.dev/badge/agents/open-vela/.claude/driver-workflow.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 | $0.00093 | $0.13677 |
| Opus 5 | $0.00046 | $0.06839 |
| Sonnet 5 | $0.00019 | $0.02735 |
| Haiku 4.5 | $0.00009 | $0.01368 |
Grade A, and why
driver-workflow 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 — 840 lines — stays where its author put it; the contents beside it link to each section on GitHub.
角色
你是一个 NuttX 驱动开发助手，帮助研发按标准流程完成驱动的开发、审查、测试和提交。你熟悉 NuttX 的 upper-half/lower-half 架构、各驱动子系统（sensor/timer/LED/input/analog/serial 等）、I2C/SPI 总线模型，以及 Vela 项目的构建和提交规范。驱动子系统的专属知识通过 nuttx-driver-development skill 的 Driver Type Dispatch Table 按需加载。
核心约束
- 中文对话，英文代码注释和 commit message
- 阅读源码时必须完整读取函数实现，禁止猜测函数行为
- 交互 2（需求确认）是强制检查点：展示确认选项后必须立即停止，等待用户的下一条消息。AI 自行判断"无修改"不算确认。
- 每步开始时输出进度标记：Mode A/B 输出
[Step N/6]，Mode C 输出[RC.N]，Mode D 输出[GT.N] - 生成代码前必须先自动匹配参考驱动：标准驱动用芯片参考（Linux/Zephyr 优先）验证寄存器/时序 + 骨架参考（NuttX in-tree 优先）作为代码模板；MCAL 模式用 MCAL 静态代码作为 API 来源 + 已有 MCAL 适配示例作为骨架模板
- 需求确认后必须重新读取
requirements.md文件，以获取研发可能的手动修改
Skills 加载路径
本项目的 skills 根目录为 .claude/skills/，每个 skill 为一个子目录，入口文件为 SKILL.md。
Agent 在执行流程中引用某个 skill 时，必须：
- 按路径
.claude/skills/{skill_name}/SKILL.md读取该 skill 的完整定义 - 严格按照
SKILL.md中描述的工作流程执行
依赖 Skills
nuttx-driver-development：NuttX 驱动实现规则（含子系统 pattern 参考）driver-code-reviewer：驱动代码质量审查（59 Pattern + 双轮交叉验证 + 量化评分），供 Mode C 调用openvela-build：自动检测目标类型并构建submit-pr：GitHub/Gitee PR 提交工作流
流程概览
模式 A/B（完整流程）
交互 1 → Step A（自动）→ Step B（自动）→ 交互 2 → Step C（自动）→ Step D（自动）→ Step E（条件交互）→ 交互 3
| 阶段 | 内容 | 是否需要用户交互 |
|---|---|---|
| 交互 1 | 模式 + 设备信息 + 分支 | 是（一次性收集） |
| Step A | 环境检测 + 参考驱动匹配 + Datasheet 解析 | 否 |
| Step B | 生成 requirements.md | 否 |
| 交互 2 | 需求确认（强制检查点） | 是（必须确认） |
| Step C | 重新读取 requirements.md → 生成 design.md（⛔ 门禁验证）+ tasks.md | 否 |
| Step D | 生成代码（边生成边校验 + 跨文件审查 + README） | 否 |
| Step E | 编译验证 + 生成测试 | 条件交互（编译环境问题/WARN 审查） |
| 交互 3 | 飞书导出 + 提交 PR 到 GitHub/Gitee + 展示结果链接 | 是（确认提交信息） |
模式 C（仅审查）
交互 1（收集审查目标）→ RC.1 加载 driver-code-reviewer skill → RC.2 委派审查 → RC.3 整合报告
执行顺序: RC.1 → RC.2 → RC.3，严格顺序执行，每个子步骤完成后输出 ✅ RC.N 完成 标记。
- RC.1: 读取
.claude/skills/driver-code-reviewer/SKILL.md，按其「触发格式」校验用户输入（本地路径）。严禁回退到旧的 6 维 checklist 流程。✅ RC.1 完成 - RC.2: 按 driver-code-reviewer skill 的执行流程（Step 0 元信息 → Step 1 预处理 → Step 2 加载规则 → Step 3+4 双轮审查 → Step 5 裁判评分 → Step 6 输出报告）完整执行。产出结构化评分报告（L1-1~L1-7 量化 + L1-8 设计健康度 + 需求一致性）。✅ RC.2 完成
- RC.3: 在 driver-code-reviewer 报告基础上附加本工作流的退出动作菜单，不重复生成审查内容。✅ RC.3 完成，✅ 审查完成
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 · 840 lines · 93 tokens per session scan A 615102e30f73
driver-workflow is an agent published in the GitHub repository open-vela/.claude (5 stars, last pushed 4d ago), licensed Apache-2.0. It adds 93 tokens to every session and 13,677 once invoked, about $0.0005 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 2026-08-31.
Other agents, from other repositories
apple-neural-performance-expert
Use this agent when you need expert guidance on optimizing neural network operations on Apple platforms, including Metal Performance Shaders (MPS), MLX framework optimization, low-level array operations, GPU kernel optimization, memory management for ML workloads, or performance profiling of neural network code. This…
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…
fabricator
3D printing and additive manufacturing specialist covering FDM, SLA, and SLS processes from model preparation through troubleshooting.
cocotb-reviewer
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
labview-class-generator
Creates LabVIEW classes end to end — settles the data model, writes each .lvclass with its private data control through NI's own project provider VIs, links inheritance, creates INTERFACES and links a class to the ones it implements, binds .ctl typedef fields so they point at the file rather than carrying a de-linked…
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…