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/today-hbw/claude-code-dev-workflow/grillnpx skills add Today-Hbw/claude-code-dev-workflow --skill grillgit clone --depth 1 https://github.com/Today-Hbw/claude-code-dev-workflowWhat 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 | $0.00019 | $0.01117 |
| Opus 5 | $0.00010 | $0.00558 |
| Sonnet 5 | $0.00004 | $0.00223 |
| Haiku 4.5 | $0.00002 | $0.00112 |
Grade A, and why
grill 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
grill · 提问方法论
你的任务
针对 PRD 需求中模糊、缺失、有歧义的部分，沿着决策树逐条向用户提问，直到所有关键不确定点都对齐。
核心方法：决策树遍历
不要按维度平铺提问，而是把 PRD 看作一棵决策树：
PRD
├── 决策 A：数据存在哪？
│ ├── 决策 A1：用新表还是复用旧表？
│ └── 决策 A2：字段如何设计？
├── 决策 B：接口怎么暴露？
│ ├── 决策 B1：新增接口还是扩展现有接口？
│ └── 决策 B2：参数格式？
└── 决策 C：UI 如何呈现？
└── 决策 C1：字段顺序和默认值？
遍历规则：
- 先识别所有决策分支：读完 PRD 后，列出所有需要做出的决策
- 按依赖关系排序：先解决前置决策（被其他决策依赖的节点）
- 逐个向下走：每次只问一个问题，等用户回答后再问下一个
- 回答可能揭示新分支：用户的回答可能引出新的决策节点，动态加入树中
提问原则
-
先推荐，再确认：每个问题先给出你的推荐答案和理由，再让用户确认或修改
我的建议：用新表 `user_preferences` 存储，理由是... 你觉得这样可以吗？还是有其他考虑？ -
一次只问一个问题：并行抛出多个问题会让用户混乱。问完一个，等回答，再问下一个。
-
先查答案来源，再问用户：能查到答案的问题不要问用户。
- 视觉规格问题先回 PRD 内嵌截图/原型逐元素核对——图里已标注的按图定死。
- 实现问题先用 Glob/Grep/Read 查代码库，查到就直接用。
-
给出判断依据：推荐答案要说明为什么，不要只说"我建议 X"，要说"我建议 X，因为 Y"。
-
标记缺口：仅当 PRD 正文和截图/原型都未给出时才算真缺口——标为「缺口」、说明临时方案、继续推进。
提问维度（辅助参考）
决策树遍历是主方法，以下维度帮助你在遍历中发现遗漏的决策节点：
| 维度 | 典型决策点 |
|---|---|
| 边界条件 | 空值怎么处理？最大/最小值？超限怎么办？ |
| 依赖关系 | 依赖哪个表/接口/其他任务？先后顺序？ |
| 存储结构 | 数据存在哪？新表还是复用？字段设计？ |
| UI 细节 | 字段折进已有列还是独立列？按钮文案？入口挂哪个页签？筛选放哪？字段顺序？默认值？ |
| 异常处理 | 失败怎么提示？重试？回滚？ |
| 性能 | 数据量多大？需要分页？有并发问题？ |
| 兼容性 | 需要兼容旧版本吗？接口变更？ |
提问方式
使用 AskUserQuestion 工具：
问题：<具体决策问题>
选项 A：<你的推荐方案>（附理由）
选项 B：<备选方案 1>
选项 C：<备选方案 2>
提问流程
1. 读完 PRD 后，画出决策树（列出所有决策节点和依赖关系）
↓
2. 从根节点开始（最不依赖其他决策的节点）
↓
3. 每个节点：先推荐 → 问用户 → 记录回答
↓
4. 回答可能揭示新节点 → 动态加入决策树
↓
5. 所有节点遍历完毕 → 检查是否有遗漏维度
↓
完成 → 进入步骤 3（编码）
注意事项
- 如果用户说「你自己判断」，给出你的建议方案并记录，不反复追问
- 不要纠结于小问题，先确保大方向正确
- 如果需求已经足够清晰，可以快速过一遍确认，不需要强行提问
- 用户的回答可能推翻之前的理解，及时调整决策树
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 · 101 lines · 19 tokens per session scan A 749ef9257e0a
grill is a skill published in the GitHub repository Today-Hbw/claude-code-dev-workflow (22 stars, last pushed 22d ago), licensed MIT. It adds 19 tokens to every session and 1,117 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 skills, from other repositories
humanizer
Rewrite AI-sounding text so it reads naturally without changing what it says. Use when editing or reviewing prose for inflated claims, sales language, vague sources, repetitive structure, stock AI words, passive voice, filler, or chatbot artifacts. Based on Wikipedia's "Signs of AI writing.".
metrics-instrumentation
Specification for instrumenting an opik-backend workflow with operational OpenTelemetry metrics — per-stage throughput/latency/error counters and native histograms, dimensioned per-customer (workspace). Use when a pipeline (scoring, ingestion, experiments, jobs) needs per-stage visibility. Covers metric emission only…
apm-issue-autopilot
Use this skill to drive any open microsoft/apm issue (bug, feature, docs, refactor, perf) from raw intake to a mergeable PR with triage as the central, paramount gate. Run the apm-triage-panel rubric per issue first, then present ONE consolidated triage review for the whole batch and escalate to the maintainer BY…
discount-review
Inspect the discount policy fixture with a repeatable review checklist and helper script.
happiness-skill
当用户问「怎么才能更幸福/为什么得到了还不满足/怎么减少焦虑」时调用。 核心理念: 幸福是缺憾感清空的默认状态, 是可训练的技能; 欲望是与自己的契约(得到前不快乐), 同时只留一个重大欲望; 活在当下。 不适用于: 临床抑郁等需要专业治疗的场景(本书方法不能替代医疗)。 Triggers: 幸福/不快乐/欲望/焦虑/知足/活在当下/happiness/desire/anxiety.
apm-usage
Activate when the user asks about APM (Agent Package Manager): installing, configuring, authoring, or troubleshooting AI-agent packages, dependencies, compilation, MCP servers, policy, or any apm CLI command.