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/samqin123/claude_skill_pool/code-debuggernpx skills add samqin123/Claude_skill_pool --skill code-debuggergit 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 | $0.00063 | $0.02102 |
| Opus 5 | $0.00032 | $0.01051 |
| Sonnet 5 | $0.00013 | $0.00420 |
| Haiku 4.5 | $0.00006 | $0.00210 |
Grade C, and why
code-debugger scanned grade C with 1 finding 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.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
- 若无，则指导用户建立公钥-私钥登录（`ssh-keygen` + 将公钥写入远程 `~/.ssh/authorized_keys`），并确认**项目在远程机器上的实际路径**（如 `/mnt/dev/xxx`、`/home/user/proj`）。 How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Debugger
Overview
在修改代码前先建立完整上下文关系网络，最小化变更并记录可追溯的调试文档，确保修复可验证、可回滚、可复盘。
开发环境与运行上下文（优先确认）
在执行验证、测试或 Checkfix 之前，务必确认项目的「部署-开发」架构，避免在错误环境中跑命令导致死循环或无法推进：
- 常见形态：本机 Windows 开发；WSL 内开发；内网 NAS 或云服务器上代码通过 Samba 挂载到 Windows 盘符，在本地 IDE 编辑，但实际运行/测试需 SSH 登录远程执行。
- 若无法从仓库或路径推断：主动问开发者一句，例如：「项目是否在 NAS/Samba+SSH 或远程服务器上开发？当前是怎么跑测试/构建的？」
- 若是远程/NAS-Samba+SSH 形态：
- 询问是否已有现成的 SSH 登录方式（如
ssh nas、ssh dev等别名或主机配置）。 - 若无，则指导用户建立公钥-私钥登录（
ssh-keygen+ 将公钥写入远程~/.ssh/authorized_keys），并确认项目在远程机器上的实际路径（如/mnt/dev/xxx、/home/user/proj）。 - 后续验证与 Checkfix 的 shell 命令应在该上下文中执行（例如
ssh nas "cd /mnt/dev/xxx && cargo test"），而不是在本地 Samba 映射路径下直接执行，以保障调试流畅、节省成本并防止 AI 反复无效尝试。
- 询问是否已有现成的 SSH 登录方式（如
- 首次与用户确认后，将上述判断结果写入当前模块的 .debug 文档，作为「运行上下文/测试规则」（运行环境类型、SSH 方式、远程项目路径、验证/Checkfix 执行方式等）。后续再调用本命令时，优先从 .debug 读取该规则，不再反复询问。
Workflow
1. 上下文构建
- 解析用户任务，识别涉及模块与边界。
- 使用
rg/文件浏览定位入口与相关模块，梳理调用链、变量依赖和数据流向。 - 检查
.debug/：若已有同模块记录则加载；若模块不同则新建，避免混杂上下文。 - 评估影响范围与潜在回归点，只改必要代码。
2. 问题定位与实施
- 基于上下文网络定位根因，给出 1-2 个方案并评估风险。
- 采用最小改动原则实施修复或增量功能，保持现有架构与风格一致。
- 添加必要的边界检查和错误处理。
3. 验证与记录
- 运行现有测试或提供明确的手动验证步骤。
- Debug-Checkfix 闭环（必选）：完成代码修改后，根据项目技术栈执行相应的自动检查（见下方「技术栈与推荐检查」），将「修复 → 检查 → 修正」形成闭环；检查结果纳入验证并写入
.debug/。 - 更新
.debug/记录：问题、根因、变更、验证（含 checkfix 结果）、影响评估。 - 根据反馈迭代修复与文档。
4. 文档同步与部署约束（必选）
- 前端功能变更：必须同步更新
docs/用户说明书，默认面向零基础用户，步骤写到可直接照做。 - 后端/API/环境变更：必须同步更新开发与部署文档，明确命令、执行顺序、预期输出、失败排查与回滚。
- 每次功能或环境更新后，必须检查既有部署指导是否需要联动修改（如
docs/DEPLOYMENT.md、docs/README.md）。
技术栈与推荐检查（Checkfix 闭环）
读取本 skill 的编程工具应在 debug 完成后自动考虑执行下列检查，减少开发者反复提醒的负担：
| 技术栈/类型 | 推荐检查 | 说明 |
|---|---|---|
| Python | 优先 uv venv + uv sync（或 uv pip install -r requirements.txt），并执行 ruff check .、ruff format --check . 或 black --check . |
部署优先级：uv（非 uvicorn）> 直接部署 > conda |
| 前端 (Node/npm) | npm install（依赖变更时）、npm run lint 或 npx eslint .，可选 npm run build |
依赖与静态检查，优先用 package.json scripts |
| PyTorch (GPU) | uv pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu124（按目标 CUDA 版本调整） |
有 NVIDIA GPU 时优先 CUDA 包，并补充 CPU 回退命令 |
| Rust | cargo check 或 cargo clippy |
编译与 Clippy |
| Go | go build ./...、gofmt -l . 或 golangci-lint run |
编译与格式/静态检查 |
| Java/Kotlin (Maven) | mvn compile 或 mvn verify |
编译与测试 |
| Java/Kotlin (Gradle) | ./gradlew compileJava 或 ./gradlew check |
同上 |
| C# / .NET | dotnet build、dotnet format --verify-no-changes |
编译与格式 |
| 通用 | 项目内已配置的 lint/format/check 脚本（如 make check、invoke lint） |
优先执行项目既有脚本 |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 136 lines · 63 tokens per session scan C b36688c8884c
code-debugger is a skill published in the GitHub repository samqin123/Claude_skill_pool (2 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 63 tokens to every session and 2,102 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…