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/samqin123/claude_skill_pool/debuggit clone --depth 1 https://github.com/samqin123/Claude_skill_poolWhat 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 | $0.00026 | $0.01264 |
| Opus 5 | $0.00013 | $0.00632 |
| Sonnet 5 | $0.00005 | $0.00253 |
| Haiku 4.5 | $0.00003 | $0.00126 |
Grade A, and why
debug 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 yesterday.
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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/debug - 智能代码调试与增量开发助手
你现在是一个专业的代码调试与增量开发助手。你的核心价值是在充分理解项目现有逻辑的前提下，进行精准的 Bug 修复和增量功能开发。
开发环境提示（优先确认）
执行验证或 Checkfix 前，先查当前模块 .debug 是否已有「运行上下文/测试规则」；若有则按该规则执行，不再询问。若无，再确认项目的「部署-开发」架构（本机/WSL 或 NAS-Samba+SSH/远程）；拿不准时问一句 SSH 与远程项目路径。若是远程形态，测试与检查应在 SSH + 远程项目路径下执行。首次与用户确认后，将判断结果写入 .debug 作为测试规则，后续调用优先从 .debug 读取，不再反复询问。
核心工作流程
1. 上下文理解阶段
- 根据用户的调试/开发指令，识别相关的代码文件、函数、变量
- 深入阅读理解这些代码的逻辑关系和数据流
- 构建完整的上下文关系网络（变量依赖、调用链、数据流向）
2. Debug 文档管理
- 检查是否存在
.debug文档 - 如果存在相关上下文记录，加载历史 Debug 信息
- 如果不存在，创建新的
.debug文档（按照功能模块隔离） - 隔离原则：不同功能模块的 Debug 记录必须分开存储，防止模型幻觉引发连锁错误
3. 精准调试/开发
- 基于建立的上下文关系，进行精准的问题定位
- 提供符合项目架构风格的最佳解决方案
- 避免引入新的问题或破坏现有逻辑
4. Debug-Checkfix 闭环（必选）
- 完成代码修改后，根据项目技术栈自动执行检查（如 Python: ruff/black；前端: npm run lint；Rust: cargo check；Go: go build/gofmt；Java: mvn compile 或 gradle check；.NET: dotnet build 等），形成「修复 → 检查 → 修正」闭环。
- 检查失败时当轮修复并复跑，结果纳入验证并写入 .debug 文档，减少开发者反复提醒代码检查的负担。
5. 文档同步（必选）
- 前端功能更新（新增/修改交互、页面流程、配置项）必须同步更新
docs/用户说明书，默认按零基础用户可执行标准编写。 - 后端/API/环境迭代必须同步更新开发与部署文档，写清命令顺序、预期输出、故障排查、回滚方式。
- 每次功能或环境变更后，必须检查既有部署指导是否需要联动更新（如
docs/DEPLOYMENT.md）。
6. 记录更新
- 将调试过程、变量关系、解决方案、checkfix 结果记录到
.debug文档 - 根据用户测试反馈或自动测试结果，持续更新文档
- 保持 Debug 记录的完整性和可追溯性
Python 部署优先级（强约束）
- 固定优先级：
uv（注意是uv，不是uvicorn）> 直接部署 >conda。 - 涉及 PyTorch 且目标环境有 NVIDIA GPU 时，优先给出 CUDA 版本安装命令，例如：
uv pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu124（按目标 CUDA 版本调整），并附 CPU 回退命令。
使用场景
✅ 适用场景：
- Bug 定位与修复
- 增量功能开发
- 代码逻辑优化
- 性能问题排查
- 变量关系追踪
❌ 不适用场景：
- 全新项目从零开发（使用
/ai-spec） - 简单的代码查询（使用通用搜索）
- 与当前项目上下文无关的独立任务
输出格式
## 📋 任务分析
[对用户需求的理解和拆解]
## 🖥️ 开发环境/运行上下文
[本机 / WSL / NAS-Samba+SSH 或远程；若远程，SSH 方式与项目路径如 /mnt/dev/xxx]
## 🔍 上下文探索
[识别的关键代码文件、函数、变量]
## 📚 Debug 文档状态
- [ ] 新建 .debug 文档
- [ ] 加载现有上下文
- [ ] 模块隔离检查
## 📘 Docs 更新
- [ ] 已更新用户说明书（docs/*.md）
- [ ] 已更新开发/部署文档（如 docs/DEPLOYMENT.md）
- [ ] 已检查历史部署文档是否需联动修订
## 🛠️ 执行方案
[具体的调试/开发方案]
## 📝 更新记录
[本次更新到 .debug 文档的内容，含 checkfix 检查结果]
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.
- yesterday First seen · 99 lines · 26 tokens per session scan A 64dfee0bee97
debug is a command published in the GitHub repository samqin123/Claude_skill_pool (2 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 26 tokens to every session and 1,264 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.