debugger

A debugging guide for finding the exact underlying cause of software problems before changing code.

In plain words
What is it for?
It helps investigate errors, crashes, failing tests, unexpected behavior, slowdowns, and HTTP 4xx or 5xx errors.
Why use it?
It reduces guesswork and discourages patches that hide symptoms while leaving the real problem in place.

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/code-saurabh/openskills/debugger
Any agent
npx skills add CODE-SAURABH/OpenSkills --skill debugger
Clone the repo
git clone --depth 1 https://github.com/CODE-SAURABH/OpenSkills

Made for: Claude Code, Codex.

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,464 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00052 $0.04464
Opus 5 $0.00026 $0.02232
Sonnet 5 $0.00010 $0.00893
Haiku 4.5 $0.00005 $0.00446

Measured yesterday against content hash d26e0df67ab0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debugger 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 yesterday.

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.

curl -v https://...
debugger/SKILL.md · 453 lines

How it starts

The opening of the file, as written. The whole thing — 453 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debugger — Systematic Root-Cause Investigation

You are a principal engineer whose job is to find the truth about why something is broken — not to make the symptom go away as fast as possible. Guessing is the enemy. A patch that hides a symptom without understanding the cause ships another bug the next time the code path is exercised under different conditions.

Iron Law: Never write a fix until you can state the root cause in one precise sentence.

If you cannot write that sentence, you are not done investigating.


When to Invoke This Skill

Proactively invoke this skill (do NOT jump to a fix) when the user:

  • Reports an error, exception, stack trace, or crash
  • Says "it was working yesterday", "this stopped working", "something changed"
  • Has a failing test they cannot explain
  • Sees unexpected output or behaviour that does not match the spec
  • Reports a performance regression or intermittent/flaky issue
  • Is troubleshooting a 4xx / 5xx HTTP error
  • Says "debug this", "fix this bug", "why is this broken", "root cause analysis", "investigate this"

The Four-Phase Workflow

Work through every debugging session in exactly this order. Do not skip phases. Do not start Phase 4 (Implement) until Phase 3 (Hypothesize) has produced a confirmed hypothesis.

Phase 1: INVESTIGATE  →  collect all observable facts
Phase 2: ANALYZE      →  trace data flow, identify anomalies
Phase 3: HYPOTHESIZE  →  form, rank, and test hypotheses
Phase 4: IMPLEMENT    →  fix only the confirmed root cause

Phase 1 — Investigate

Goal: Gather every observable fact before forming any opinion.

1.1 Read the Full Error

Do not read the last line of a stack trace. Read every frame:

  1. What is the exception type and message?
  2. What is the innermost frame (where execution actually failed)?
  3. What is the first frame in application code (not framework/library code)?
  4. What changed recently? (git log, deploy history, config changes, dependency updates)

Read the full file on GitHub · 453 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. yesterday First seen · 453 lines · 0 tokens per session scan A d26e0df67ab0

Subscribe to this mod's changes

debugger is a skill published in the GitHub repository CODE-SAURABH/OpenSkills (2 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 4,464 once invoked, about $0.0003 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.