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/techdufus/oh-my-claude/debuggernpx skills add TechDufus/oh-my-claude --skill debuggergit clone --depth 1 https://github.com/TechDufus/oh-my-claudeWrote 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/techdufus/oh-my-claude/debugger)<a href="https://agentmods.dev/skills/techdufus/oh-my-claude/debugger"><img src="https://agentmods.dev/badge/skills/techdufus/oh-my-claude/debugger.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 | $0.00045 | $0.00916 |
| Opus 5 | $0.00023 | $0.00458 |
| Sonnet 5 | $0.00009 | $0.00183 |
| Haiku 4.5 | $0.00005 | $0.00092 |
Grade A, and why
debugger 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debugger Skill
Systematic debugging methodology for diagnosing failures and root cause analysis.
When to Apply This Guidance
- 2+ failed fix attempts on the same issue
- Debugging that's gone in circles
- Complex system behavior you don't understand
- Multi-system integration problems
- Intermittent failures (Heisenbugs)
Structured Analysis Framework
Step 1: Restate the Problem
Before investigating, articulate:
- What is the actual vs expected behavior?
- What assumptions might be wrong?
- What could cause the specific symptoms described?
- Are there hidden dependencies or side effects?
Step 2: Generate Ranked Hypotheses
Always generate multiple hypotheses, ranked by likelihood:
Most Likely:
- Evidence: What supports this theory?
- Test: How to verify quickly?
Possible:
- Evidence: What partially supports this?
- Test: How to confirm or eliminate?
Unlikely but worth checking:
- Evidence: Limited, but possible
- Test: Quick check to rule out
Step 3: Systematic Verification
Test hypotheses in order. For each:
- State what you're testing
- Describe the expected outcome if hypothesis is correct
- Execute the test
- Document actual results
- Update hypothesis ranking based on findings
Reasoning Principles
- Challenge assumptions - The "obvious" cause is often wrong after 2+ failures
- Follow the data - What do logs/errors actually say vs what's assumed?
- Consider timing - Race conditions, async issues, initialization order
- Check boundaries - Module interfaces, API contracts, type conversions
- Question the environment - Config, dependencies, network, state
Decision Framework
When choosing between approaches:
| Factor | Weight | Considerations |
|---|---|---|
| Correctness | Critical | Does it actually solve the problem? |
| Simplicity | High | Prefer boring solutions over clever ones |
| Leverage | High | Use existing patterns/libraries/code |
| Developer Experience | Medium | How hard is it to debug/maintain? |
| Performance | Low* | *Unless performance IS the problem |
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.
- 5d ago First seen · 121 lines · 45 tokens per session scan A 317144127730
debugger is a skill published in the GitHub repository TechDufus/oh-my-claude (176 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 916 once invoked, about $0.0002 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
taiyi-ui-design
TaiyiForge 第 4 阶段 — UI/UX 契约，产出 UI-DESIGN.md。四端通用。.
taiyi-evolve
TaiyiForge 辅助 — 实现后架构与文档同步（architecture-sync）。OpenCode / Claude / Codex / Cursor 通用。.
flow-next-resolve-pr
Resolve PR review feedback. Fetches unresolved threads, triages, fixes, replies and resolves via GraphQL. Use when asked to address review comments.
flow-next-tracker-sync
Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.
taiyi-diagram-c4
TaiyiForge 辅助 — 从代码反推 C4 架构文档（Observed/Inferred 分层 · Mermaid 真源）。OpenCode / Claude / Codex / Cursor 通用。.
writing-style
Use for technical communication - GitHub/GitLab tickets, PR/MR descriptions, issue comments, code review comments, commit messages. Direct, brief style with no AI-speak. NOT for README.md, public docs, or blog posts.