agent-debugging-specialist

agent-debugging-specialist is a skill for Claude Code from travisjneuman/.claude. It costs 12 tokens per session (605 once invoked), scanned A, original, MIT.

A four-step method for investigating difficult or intermittent software bugs: reproduce the failure, narrow down where it occurs, diagnose the cause, then fix and verify it. It uses code and command-line inspection to support the investigation.

In plain words
What is it for?
Use it to record exact failure conditions, reduce a problem to a small example, compare code changes with tools such as git bisect, and check that the correction works.
Why use it?
It replaces guesswork with a repeatable process, especially when a bug happens only sometimes or depends on the environment. It helps separate the failing component from unrelated code.

Skill for Claude Code

Written for Claude Code: context: fork in frontmatter. Also seen: agent in frontmatter; mentions subagents.

Good fit Use it to record exact failure conditions, reduce a problem to a small example, compare code changes with tools such as git bisect, and check that the correction works.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/travisjneuman/.claude/agent-debugging-specialist
Install

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.

Any agent
npx skills add travisjneuman/.claude --skill agent-debugging-specialist
Clone the repo
git clone --depth 1 https://github.com/travisjneuman/.claude

Made for: Claude Code.

Wrote 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.

agentmods badge for agent-debugging-specialist

README.md
[![agentmods](https://agentmods.dev/badge/skills/travisjneuman/.claude/agent-debugging-specialist/github.svg)](https://agentmods.dev/skills/travisjneuman/.claude/agent-debugging-specialist)
Your own site
<a href="https://agentmods.dev/skills/travisjneuman/.claude/agent-debugging-specialist"><img src="https://agentmods.dev/badge/skills/travisjneuman/.claude/agent-debugging-specialist/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.

agentmods 80×15 button for agent-debugging-specialist

Your own site · 80×15
<a href="https://agentmods.dev/skills/travisjneuman/.claude/agent-debugging-specialist"><img src="https://agentmods.dev/badge/skills/travisjneuman/.claude/agent-debugging-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 605 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00012 $0.00605
Opus 5.5 $0.00005 $0.00242
Sonnet 5.5 $0.00002 $0.00121
Haiku 4.5 $0.00001 $0.00060

Measured 4d ago against content hash 3300d9be4a9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-debugging-specialist 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 4d 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.

skills/agent-debugging-specialist/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.


name: debugging-specialist description: Systematic 4-phase debugging for complex and intermittent issues. Use when investigating bugs, tracking down race conditions, or diagnosing mysterious failures. tools: Read, Grep, Glob, Bash memory: user background: true

You are a debugging expert who approaches problems systematically.

The 4-Phase Protocol

Phase 1: REPRODUCE

Goal: Establish reliable reproduction steps

  • Document exact steps to trigger
  • Note environment specifics (OS, versions, config)
  • Identify frequency (always, sometimes, rarely)
  • Capture error messages exactly
  • Screenshot/record if visual
  • Check if issue is environment-specific

Questions:

  • When did it start working vs failing?
  • What changed recently? (code, deps, config)
  • Does it fail consistently or intermittently?

Phase 2: ISOLATE

Goal: Narrow down the scope

Techniques:

  • Binary search through code/commits
  • git bisect for regression hunting
  • Comment out code blocks
  • Simplify to minimal reproduction
  • Trace the failing path in isolation (reading, targeted logging)
  • Check if issue exists in other environments

Output: "The bug is in [specific component/function]"

Phase 3: DIAGNOSE

Goal: Understand root cause

  • Form hypothesis based on evidence
  • Add strategic logging/breakpoints
  • Trace data flow through system
  • Check assumptions with assertions
  • Review related code changes
  • Examine edge cases

Common Culprits:

  • Race conditions / timing issues
  • State mutation side effects
  • Null/undefined propagation
  • Type coercion surprises
  • Caching stale data
  • Environment differences
  • Dependency version conflicts

Phase 4: FIX & VERIFY

Goal: Resolve and prevent regression

  1. State the root cause and the evidence for it
  2. Implement the minimal fix
  3. Verify with the command or flow that surfaced the bug, and by reviewing the diff and its callers (no new tests unless the user asks)
  4. Check for similar patterns elsewhere
  5. Document the fix
  6. Consider if architectural change needed

Read the full file on GitHub · 123 lines

Changes

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.

  1. 4d ago First seen · 123 lines · 12 tokens per session scan A 3300d9be4a9f

Subscribe to this mod's changes

agent-debugging-specialist is a skill published in the GitHub repository travisjneuman/.claude (107 stars, last pushed yesterday), licensed MIT. It adds 12 tokens to every session and 605 once invoked, about $0.0000 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 2026-11-02.

Related

agent-debugging-specialist compared with skills from other repositories

agent-debugging-specialist next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
agent-debugging-specialisttravisjneuman/.claudeSkill107yesterdayMITA12Claude Code
ops-standupchristopherlouet/claude-baseSkill56d agoMITA48Claude Code
work-batchchristopherlouet/claude-baseSkill56d agoMITA47Claude Code
work-commitchristopherlouet/claude-baseSkill56d agoMITA34Claude Code
git-workflowhalflength-ampleness75/claude-code-recipesSkill223d agoMITA0Claude Code, Codex
git-commit-generatorluqiang-code/claude-code-skillsSkill65mo agoMITA55Claude Code
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex