debug

A debugging workflow that coordinates specialized agents to investigate errors, bugs, crashes, failed tests, and other unexpected behavior. It starts with finding the likely root cause before checking a proposed fix.

In plain words
What is it for?
Use it when you have an error message, stack trace, failing test, crash, or broken behavior, either automatically through trigger words or with the /debug command.
Why use it?
It reduces guesswork and repeated trial-and-error when something fails. Gathering the error details and reproduction steps helps focus the investigation on the actual cause.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/arpitnath/claude-capsule-kit/debug
Any agent
npx skills add arpitnath/claude-capsule-kit --skill debug
Clone the repo
git clone --depth 1 https://github.com/arpitnath/claude-capsule-kit

Made for: Claude Code, Codex.

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,717 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00050 $0.02717
Opus 5 $0.00025 $0.01358
Sonnet 5 $0.00010 $0.00543
Haiku 4.5 $0.00005 $0.00272

Measured 2d ago against content hash 2854df09484c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debug 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 2d 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/debug/SKILL.md · 474 lines

How it starts

The opening of the file, as written. The whole thing — 474 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debug Orchestrator

You are a Debug Orchestrator responsible for systematic error resolution using specialized debugging agents rather than manual trial-and-error.

Purpose

Problem: Errors are often debugged reactively—reading code, guessing causes, trying fixes without understanding root cause.

Solution: RCA-first methodology using error-detective for root cause analysis, debugger for systematic investigation, and code-reviewer for fix verification.

When to Use This Skill

Auto-triggers on keywords:

  • "error", "bug", "broken", "failing", "exception"
  • "stack trace", "test failure", "crash", "doesn't work"
  • "why is this failing", "what's wrong", "fix this"

Error indicators:

  • User reports error message
  • Tests failing unexpectedly
  • Application crash or hang
  • Unexpected behavior

Manual invocation: /debug


The 5-Phase Debug Workflow

Phase 1: CAPTURE

Goal: Gather complete error context

Collect:

  1. Error message (exact text)
  2. Stack trace (full trace if available)
  3. Reproduction steps (how to trigger)
  4. Environment (local, CI, production)
  5. Recent changes (git diff, capsule files)

Commands:

# Git diff (check recent changes)
git diff --stat
git log -5 --oneline

# Search for error message
grep -r "error message text" . --include="*.log"

Deliverable: Complete error report with all context


Phase 2: RCA (Root Cause Analysis)

Goal: Understand WHY the error occurs (not just symptoms)

Launch error-detective agent:

Task(
  subagent_type="error-detective",
  description="Analyze error RCA",
  prompt="""
Perform root cause analysis for this error:

**Error**: [exact error message]

**Stack Trace**:
[full stack trace]

**Context**:
- Environment: [local/CI/prod]
- Recent changes: [git diff summary]
- Reproduction: [steps to trigger]

Provide structured RCA with:
- What Failed
- Root Cause
- Evidence
- Chain of Events
- Suggested Fix
- Confidence Level
"""
)

Read the full file on GitHub · 474 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. 2d ago First seen · 474 lines · 50 tokens per session scan A 2854df09484c

Subscribe to this mod's changes

debug is a skill published in the GitHub repository arpitnath/claude-capsule-kit (88 stars, last pushed 3mo ago), licensed MIT. It adds 50 tokens to every session and 2,717 once invoked, about $0.0003 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.