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 skills add Ow1onp/hermes-agent-skills --skill debugger-coordinatorgit clone --depth 1 https://github.com/Ow1onp/hermes-agent-skillsWrote 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/skills/ow1onp/hermes-agent-skills/debugger-coordinator)<a href="https://agentmods.dev/skills/ow1onp/hermes-agent-skills/debugger-coordinator"><img src="https://agentmods.dev/badge/skills/ow1onp/hermes-agent-skills/debugger-coordinator.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 5.1 | $0.00048 | $0.01409 |
| Opus 5 | $0.00024 | $0.00705 |
| Sonnet 5 | $0.00010 | $0.00282 |
| Haiku 4.5 | $0.00005 | $0.00141 |
Grade A, and why
debugger-coordinator scanned grade A 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| 第三方集成故障 | `terminal` (curl) + `web_search` | 模拟请求 + 搜索已知 Issue | How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
调试协调器 (Debugger Coordinator)
1. 概述
现代软件调试往往涉及多个层面:前端 UI 异常、后端 API 错误、数据库状态不一致、网络超时……传统的单工具调试思路已不足以应对。本技能协调 Hermes Agent 的多模态工具矩阵(browser + terminal + vision + web_extract),进行系统性的根因分析。
核心理念:不要修你还没理解的 bug。先理解,再修复,最后加固。
2. 核心流程
2.1 五步调试法
第一步:复现 (Reproduce)
├─ 记录精确的复现步骤
├─ terminal: 查看日志、重启服务
├─ browser: 在真实浏览器中复现 UI bug
└─ vision: 截图确认异常状态
第二步:定位 (Localize)
├─ terminal: 二分法缩小代码范围 (git bisect / 日志 grep)
├─ browser_console: 检查前端 JS 错误和网络请求
└─ browser_vision: 可视化检查 UI 渲染状态
第三步:隔离 (Isolate)
├─ 写最小复现用例
├─ terminal: 单元测试隔离可疑函数
└─ 排除外部依赖(mock 网络、DB 等)
第四步:修复 (Fix)
├─ 最小化修改(只改必要的代码)
├─ test-driven-dev 技能验证修复
└─ 回归测试确认无副作用
第五步:加固 (Guard)
├─ 添加回归测试
├─ 增加日志/监控
└─ 文档化根因和修复方案
2.2 多模态工具协调矩阵
| 调试场景 | 工具组合 | 说明 |
|---|---|---|
| 后端 API 异常 | terminal + web_extract |
查看服务器日志 + 抓取 API 文档 |
| 前端 UI Bug | browser + vision + browser_console |
截图对比 + JS 控制台错误 |
| 全栈问题 | browser + terminal + browser_console |
前端网络请求 + 后端日志联合分析 |
| 性能问题 | terminal (profiler) + browser_console |
后端 profiler + 前端 Performance API |
| 第三方集成故障 | terminal (curl) + web_search |
模拟请求 + 搜索已知 Issue |
2.3 Hermes 命令体系集成
# 在 Hermes 会话中直接加载
/skill debugger-coordinator
# 打开浏览器调试
/browser # 启动 CDP 浏览器连接
# 利用 Hermes 的 terminal 执行调试命令
terminal(command="tail -100 /var/log/app.log | grep ERROR")
terminal(command="pytest tests/ -k 'test_failing_case' -v --pdb")
# 使用 vision 进行视觉验证
vision_analyze(image_url="screenshot.png", question="页面上的错误信息是什么?")
2.4 自进化机制
- Bug 模式库:自动识别和分类常见 Bug 模式(如"空指针"、"竞态条件"、"类型错误")
- 调试效率追踪:记录从 Bug 发现到修复的时间,识别瓶颈步骤
- 预防建议:对高频 Bug 类型,建议在
code-quality-guardian中添加对应的检查规则 - 调试命令模板:积累项目特定的调试快捷命令
2.5 身份感知
- 读取
SOUL.md中定义的技术栈偏好 - 调试命令自动适配技术栈(如 Node.js 项目用
node --inspect,Python 用pdb) - 日志分析风格适配(简洁型 vs 详细型)
3. 门禁标准
- Bug 已成功复现并记录精确步骤
- 根因已定位到具体的代码行或配置项
- 修复已通过 Prove-It 测试(见 test-driven-dev)
- 回归测试确认无新问题引入
- 如果适用,添加了日志/监控以防复发
- 调试过程中的关键发现已记录(可在项目文档或 Hermes 记忆中)
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.
- 7d ago First seen · 107 lines · 48 tokens per session scan A 1b6ddb706c00
debugger-coordinator is a skill published in the GitHub repository Ow1onp/hermes-agent-skills (3 stars, last pushed 2mo ago), licensed MIT. It adds 48 tokens to every session and 1,409 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
perf-profiling
Systematic performance profiling and optimization across frontend (Core Web Vitals, code splitting, lazy loading), backend (N+1 queries, async), and database (EXPLAIN ANALYZE, indexing) layers. Use when the user reports slow code, latency, memory leaks, needs to benchmark, or wants to speed up an application. Measure…
deep-debugging
Systematic debugging protocol for bugs that resist quick fixes. Use bisection, hypothesis trees, and scientific method when a bug isn't obvious from the stack trace. Goes beyond bugfix-quick for production-grade root cause analysis.
self-healing-orchestrator
Proposes patches for F2 (local-logic) and F3 (local-design) failures. NEVER applies without user approval. Confidence ≥0.7 to propose; below that, escalates raw findings. Counts toward replanbudget. Per-task: max 1; per-session: max 5.
bugfix-quick
Fast bug fixes with root cause investigation + TDD. Enforces 'no fix without root cause' discipline and verification protocol. Without this skill, fixes are applied at symptoms instead of sources, and bugs return.
failure-classifier
Classifies execution failures into F1-F5 (transient/local-logic/local-design/story-level/architectural). Outputs JSON with class, confidence, evidence, and recommended action. Deterministic rule-based classifier; no LLM call.
problem-solving
5 techniques for different problem types. Use when stuck or facing complex challenges.