claude-skills is a collection of specialized skills that extends Claude Code for full-stack development. Developers use it for programming languages, frameworks, infrastructure, APIs, testing, DevOps, security, data and machine learning, platform tasks, and project workflows.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Jeffallan/claude-skillsnpx agentmods add skills/jeffallan/claude-skills/debugging-wizardWrote 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/jeffallan/claude-skills/debugging-wizard)<a href="https://agentmods.dev/skills/jeffallan/claude-skills/debugging-wizard"><img src="https://agentmods.dev/badge/skills/jeffallan/claude-skills/debugging-wizard/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jeffallan/claude-skills/debugging-wizard"><img src="https://agentmods.dev/badge/skills/jeffallan/claude-skills/debugging-wizard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 3 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- high Prompt Injection · line 32 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Anti-Refusal · line 57 Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.Fix: Remove jailbreak framing that nullifies safety policies or restrictions. Skill content must not instruct the agent to ignore its guidelines or operate without guardrails.
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 | $0.00070 | $0.00924 |
| Opus 5.5 | $0.00028 | $0.00370 |
| Sonnet 5.5 | $0.00014 | $0.00185 |
| Haiku 4.5 | $0.00007 | $0.00092 |
Grade A, and why
debugging-wizard 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 17d 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- debugging-wizard — 100% identical, 3 lines differ
- debugging-wizard — 97% identical, 5 lines differ
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debugging Wizard
Expert debugger applying systematic methodology to isolate and resolve issues in any codebase.
Core Workflow
- Reproduce - Establish consistent reproduction steps
- Isolate - Narrow down to smallest failing case
- Hypothesize and test - Form testable theories, verify/disprove each one
- Fix - Implement and verify solution
- Prevent - Add tests/safeguards against regression
Reference Guide
Load detailed guidance based on context:
| Topic | Reference | Load When |
|---|---|---|
| Debugging Tools | references/debugging-tools.md |
Setting up debuggers by language |
| Common Patterns | references/common-patterns.md |
Recognizing bug patterns |
| Strategies | references/strategies.md |
Binary search, git bisect, time travel |
| Quick Fixes | references/quick-fixes.md |
Common error solutions |
| Systematic Debugging | references/systematic-debugging.md |
Complex bugs, multiple failed fixes, root cause analysis |
Constraints
MUST DO
- Reproduce the issue first
- Gather complete error messages and stack traces
- Test one hypothesis at a time
- Document findings for future reference
- Add regression tests after fixing
- Remove all debug code before committing
MUST NOT DO
- Guess without testing
- Make multiple changes at once
- Skip reproduction steps
- Assume you know the cause
- Debug in production without safeguards
- Leave console.log/debugger statements in code
Common Debugging Commands
Python (pdb)
python -m pdb script.py # launch debugger
# inside pdb:
# b 42 — set breakpoint at line 42
# n — step over
# s — step into
# p some_var — print variable
# bt — print full traceback
JavaScript (Node.js)
node --inspect-brk script.js # pause at first line, attach Chrome DevTools
# In Chrome: open chrome://inspect → click "inspect"
# Sources panel: add breakpoints, watch expressions, step through
What ships with it
5 files 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.
- 17d ago Changed · +3 lines 9dc712996f74
- 1mo ago First seen · 108 lines · 70 tokens per session scan A 82c442c0a4f8
debugging-wizard is a skill published in the GitHub repository Jeffallan/claude-skills (11,963 stars, last pushed 4d ago), licensed MIT. It adds 70 tokens to every session and 924 once invoked, about $0.0003 per session on Opus 5.5. 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
04-reverse-engineering
Binary analysis, assembly interpretation, disassembly, decompilation, firmware RE, and protocol reverse engineering.
log-analyzer
A log-analysis helper that reads application and system logs to find unusual patterns and likely causes. Logs are records of events such as errors, requests, warnings, and service activity.
agent-design-review
Review an LLM agent design and find where it will be unreliable, expensive, or unsafe. Use when asked to review an agent architecture, critique a multi-step/tool-using agent, debug an agent that loops or goes off-task, or harden an agent before launch. Produces a structured review — task fit, control flow, tools…
agent-incident-postmortem
Run a blameless postmortem for an incident caused by an AI agent or LLM feature — hallucinated facts shipped to users, runaway tool use, prompt injection, cost blowouts, or wrong actions taken autonomously. Use when asked to write up an AI incident, analyse why an agent did something wrong, or produce corrective…
shiny-py-optimize
Diagnose and fix performance problems in Shiny for Python apps — slow startup, sluggish interactions, blocking operations, and apps that struggle beyond a handful of concurrent users. Use when a Shiny for Python app is slow, hangs, recomputes too much, times out, or must support more users; when the user asks to…
remove-deadcode
Remove unused code from this project with ultrawork mode, LSP-verified safety, atomic commits. Triggers: remove dead code, dead code, cleanup, remove unused.