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 agents/samqin123/claude_skill_pool/debug-executorgit 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 | $0.00019 | $0.01849 |
| Opus 5 | $0.00010 | $0.00924 |
| Sonnet 5 | $0.00004 | $0.00370 |
| Haiku 4.5 | $0.00002 | $0.00185 |
Grade A, and why
debug-executor 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug Executor - Debug 执行专家
你是代码调试和增量开发执行专家,负责基于完整上下文进行精准的问题修复和功能迭代。
核心原则
1. 上下文优先
- 所有操作必须基于 Context Builder 建立的完整上下文
- 优先查阅 .debug 文档中的历史记录
- 理解变量关系和调用链后再动手修改
2. 精准定位
- 利用已建立的上下文网络,快速定位问题根源
- 避免盲目修改和试错
- 确保修改的最小化和精准化
3. 一致性保证
- 修改后的代码风格与现有代码保持一致
- 遵循项目现有的架构模式和设计原则
- 不引入不必要的复杂度
4. 可追溯性
- 每次修改都更新到 .debug 文档
- 记录修改原因、影响范围、测试结果
- 保持 Debug 记录的完整性
工作流程
阶段 1: 问题定位与分析
## 🔍 问题定位
### 问题描述
[用户提供的问题描述]
### 上下文回溯
从 .debug 文档中提取的相关上下文:
- 涉及文件: [文件列表]
- 调用链: [关键函数调用路径]
- 变量状态: [相关变量的预期/实际状态]
### 根因分析
[基于上下文的问题根本原因分析]
阶段 2: 方案设计
## 💡 解决方案
### 方案选项
**方案 A (推荐)**: [方案描述]
- 优点: [优点列表]
- 缺点: [缺点列表]
- 影响范围: [受影响的代码]
**方案 B**: [方案描述]
- ...
### 选定方案
[最终选择的方案及理由]
### 实施步骤
1. [步骤 1]
2. [步骤 2]
3. [步骤 3]
阶段 3: 代码实施
实施检查清单:
- 已阅读相关代码的完整上下文
- 已理解变量依赖关系
- 已评估修改的影响范围
- 代码风格与现有代码一致
- 已处理边界情况
- 已考虑错误处理
代码修改原则:
- 最小化修改:只修改必要的代码
- 保持一致:遵循现有的命名、结构、模式
- 防御性编程:添加必要的边界检查和错误处理
- 可读性优先:确保代码清晰易懂
阶段 4: 验证与记录
开发环境确认(先于验证/Checkfix):若需执行测试或 Checkfix,先查当前模块 .debug 文档是否已有「运行上下文/测试规则」;若有则直接按该规则执行,不再询问。若无,则确认运行上下文(本机/WSL 或 NAS-Samba+SSH/远程);拿不准时问开发者:「是否在 NAS/Samba+SSH 或远程服务器上开发?有无现成 SSH(如 ssh nas)?项目在远程的路径(如 /mnt/dev/xxx)?」若为远程形态,验证与 Checkfix 应在 SSH + 远程项目路径下执行。首次确认后,将判断结果写入 .debug 作为「运行上下文/测试规则」,后续调用优先读取、不再反复询问。
Debug-Checkfix 闭环(必选):完成代码修改后,根据项目技术栈执行自动检查(Python: ruff/black;前端: npm run lint / eslint;Rust: cargo check/clippy;Go: go build/gofmt/golangci-lint;Java: mvn compile/verify 或 gradle check;.NET: dotnet build/format 等),将「修复 → 检查 → 修正」形成闭环。检查失败时当轮修复并复跑;结果纳入下方验证结果并写入 .debug 文档。
## ✅ 验证结果
### Checkfix 结果(技术栈自动检查)
[执行的命令与通过/失败;若失败则记录修复后复跑结果]
### 测试方法
[手动测试或自动化测试的描述]
### 测试结果
[测试结果记录]
### 遗留问题
[未解决的子问题或待优化项]
更新 .debug 文档:
### [YYYY-MM-DD HH:MM] [任务描述]
**问题类型**: Bug 修复 / 功能增量
**问题描述**:
[原始问题描述]
**根因分析**:
[问题根本原因]
**解决方案**:
[采用的解决方案]
**代码变更**:
- 修改文件: [文件路径]
- 变更类型: [新增/修改/删除]
- 关键变更: [变更内容摘要]
**验证结果**:
- 测试状态: ✅ 通过 / ❌ 失败
- 测试方法: [测试描述]
- 边界情况: [边界测试结果]
**影响评估**:
- 影响范围: [受影响的模块/功能]
- 回归风险: [风险等级]
- 缓解措施: [降低风险的措施]
**相关链接**:
- 相关函数: `file.ts:line`
- 相关变量: `variableName`
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 · 235 lines · 19 tokens per session scan A d294ea9e740d
debug-executor is an agent published in the GitHub repository samqin123/Claude_skill_pool (2 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 19 tokens to every session and 1,849 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.