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 commands/awesome-embedded-learning-studio/cfdesktop/next-stepgit clone --depth 1 https://github.com/Awesome-Embedded-Learning-Studio/CFDesktopWrote 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/commands/awesome-embedded-learning-studio/cfdesktop/next-step)<a href="https://agentmods.dev/commands/awesome-embedded-learning-studio/cfdesktop/next-step"><img src="https://agentmods.dev/badge/commands/awesome-embedded-learning-studio/cfdesktop/next-step.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 | $0.00000 | $0.00570 |
| Opus 5 | $0.00000 | $0.00285 |
| Sonnet 5 | $0.00000 | $0.00114 |
| Haiku 4.5 | $0.00000 | $0.00057 |
Grade A, and why
next-step 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 3d 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.
What it actually says
/next-step — 开发指引
根据项目阶段文档和当前进度，推荐下一步开发任务。
触发方式
/next-step— 推荐下一步开发任务- 用户说"下一步开发什么"
工作流程
Step 1: 评估当前状态
- 读取
document/status/current.md（项目进度唯一事实来源）获取当前进度与下一步路线 - 识别哪些 Phase / 模块未完成
Step 2: 映射设计文档
对每个未完成阶段，读取对应的设计文档获取具体任务列表：
| Phase | 设计文档 |
|---|---|
| 1 | document/design_stage/01_phase1_hardware_probe.md |
| 2 | document/design_stage/02_phase2_base_library.md |
| 3 | document/design_stage/03_phase3_input_layer.md |
| 6 | document/design_stage/04_phase6_simulator.md |
| 8 | document/design_stage/05_phase8_testing.md |
Step 3: 优先排序
按以下顺序推荐：
- 阻塞依赖项 — 其他模块依赖此任务才能推进
- 接近完成的模块 (90%+) — 收尾效率最高
- 当前活跃阶段 — 保持开发连续性
- 测试覆盖缺口 — 为已完成的代码补充测试
Step 4: 输出格式 (中文)
对每个推荐任务：
## 推荐任务 N: <任务名称>
**优先级**: 高/中/低
**所属阶段**: Phase X — <阶段名>
### 目标文件
- `path/to/file.h` — 修改说明
- `path/to/file.cpp` — 修改说明
- `path/to/new_file.h` — 新建说明
### 改动要点
1. ...
2. ...
### 风险评估
- **风险等级**: 低/中/高
- **风险说明**: ...
- **缓解措施**: ...
### 依赖关系
- 前置依赖: ...
- 后续可解锁: ...
### 参考文档
- `document/design_stage/XX_phaseX.md` — 具体章节
规则
- 推荐前验证目标文件是否存在（避免推荐已完成的任务）
- 不推荐违反层级依赖规则的任务
- 每次推荐 2-4 个任务，按优先级排序
- 如果有近完成的模块，优先推荐收尾
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.
- 3d ago First seen · 76 lines · 0 tokens per session scan A 0d63208a3982
next-step is a command published in the GitHub repository Awesome-Embedded-Learning-Studio/CFDesktop (10 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 570 tokens. 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 commands, from other repositories
gui-anything
Build a complete GUI harness for any software application.
validate
Validate a GUI harness against HARNESS.md standards and best practices.
refine
Expand and improve an existing GUI harness with additional coverage.
test
Run tests for a GUI harness and update TEST.md with results.
list
List all GUI-Anything harnesses in the current repository.
fix_board
Automatically diagnose and fix PlatformIO board upload/monitor issues.