debug

debug is a skill for Claude Code, Codex from SyloRei/claude-godmode. It costs 43 tokens per session (1,450 once invoked), scanned A, original, MIT.

A structured debugging skill for finding the underlying cause of a software failure and then fixing it. It uses the exact error, reproduction steps, and evidence from the code rather than guesses.

In plain words
What is it for?
Use it for bugs, failing tests, unexpected results, and error messages that need to be reproduced, investigated, and fixed.
Why use it?
It helps separate the real cause from the visible symptom, which reduces the risk of applying a fix to the wrong problem. It also handles missing reproduction details by stating the best interpretation for correction.

Skill for Claude CodeCodex

Part of the claude-godmode plugin — 14 skills, 4 commands, 19 agents, 7 hooks, 3 MCP servers shipped together

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/sylorei/claude-godmode/debug
Any agent
npx skills add SyloRei/claude-godmode --skill debug
Clone the repo
git clone --depth 1 https://github.com/SyloRei/claude-godmode

Made for: Claude Code, Codex.

Or install claude-godmode, the plugin that ships this one along with the rest of its 14 skills, 4 commands, 19 agents, 7 hooks, 3 MCP servers.

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 debug

README.md
[![agentmods](https://agentmods.dev/badge/skills/sylorei/claude-godmode/debug.svg)](https://agentmods.dev/skills/sylorei/claude-godmode/debug)
Your own site
<a href="https://agentmods.dev/skills/sylorei/claude-godmode/debug"><img src="https://agentmods.dev/badge/skills/sylorei/claude-godmode/debug.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,450 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 $0.00043 $0.01450
Opus 5 $0.00022 $0.00725
Sonnet 5 $0.00009 $0.00290
Haiku 4.5 $0.00004 $0.00145

Measured 3d ago against content hash d166e6824d20, 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 3d 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 · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Structured Debugging

Find and fix bugs systematically using evidence, never guessing.


Auto Mode

Auto Mode suppresses confirmation prompts and proceed-pauses — not the one clarifying question that can matter here: if the symptom isn't reproducible and the exact error/repro steps aren't given, state your reading of it for the user to override (debugging the wrong symptom wastes the whole effort). Don't ask "what's the repro?" from blank — lead with your best-inferred symptom and repro and invite correction: "I read the failure as X on step Y — correct me if not." This is the clarifying rendering of the recommendation-backed-question convention (godmode:recommend-convention) in rules/godmode-recommend.md. Once you can reproduce, proceed: fix immediately after the root cause is found, surface assumptions inline, and treat course-corrections as normal input. Don't loop on trivia.


The Job

Follow the 4-step protocol strictly. Do NOT skip steps.


Step 1: REPRODUCE

  • Get the exact error message, stack trace, or unexpected behavior
  • Find minimal reproduction steps
  • Identify: when did it last work? What changed since?
  • If the bug is intermittent, identify conditions that trigger it
  • Establish baseline: what is the EXPECTED behavior?

Output: "The bug is [X]. Expected [Y]. Triggered by [Z]."


Step 2: HYPOTHESIZE

  • Form 2-3 hypotheses based on evidence (not intuition)
  • Rank by likelihood
  • For each, state what evidence would confirm or deny it

If stuck gathering evidence: use @researcher agent to search the codebase for related patterns, recent changes, or similar bugs.

Output:

H1 (most likely): [hypothesis] — confirm by [check]
H2: [hypothesis] — confirm by [check]
H3: [hypothesis] — confirm by [check]

Step 3: ISOLATE

  • Test hypotheses one at a time, most likely first
  • Add targeted logging or read code at suspect locations
  • Narrow to the exact line/condition causing the failure
  • DO NOT fix multiple things at once

Read the full file on GitHub · 147 lines

Files

What ships with it

1 file 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.

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. 3d ago First seen · 147 lines · 43 tokens per session scan A d166e6824d20

Subscribe to this mod's changes

debug is a skill published in the GitHub repository SyloRei/claude-godmode (3 stars, last pushed 2mo ago), licensed MIT. It adds 43 tokens to every session and 1,450 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 2026-08-31.

Related

Other skills, from other repositories

erpaval

Workflow for autonomous software development with the Kiro CLI (open Agent Skills standard). Classifiers route scope, complexity, directory state, and spec readiness before committing to Explore / Research / Plan / Act / Validate, then close the loop with a Compound step that persists lessons to .erpaval/solutions/…

theagenticguy/erpaval · 174 tokens

product-discovery

File-first orchestrator for product discovery and spec frameworks. Frames the problem with a Discovery Lead, Product Analyst, or System Architect role. Spawns parallel framework agents (Double Diamond, How Might We, Jobs to Be Done, user stories with INVEST, EARS for AI-coder specs, Gherkin), synthesizes into a PRD or…

theagenticguy/erpaval · 242 tokens

review

Use when DISCOVER or REFRESH has surfaced a proposal staged at -context.proposed/, to inspect it and record sign-off before applying it.

nick-railsback/skill-engine · 33 tokens

status

Use when picking up a contextualizer after a gap, or checking reference freshness and pending review work at a glance — read-only, safe to run anytime.

nick-railsback/skill-engine · 33 tokens

agent-ux-patterns

Agent UX patterns and human-in-the-loop design: Twilio A2H protocol, Levels of Autonomy (L0-L5), inbox pattern, progressive trust, decision journal, gate reviews, autonomous work reports. Six-phase methodology from vague pain point to concrete data model via landscape research and multi-direction brainstorming. Use…

theagenticguy/erpaval · 182 tokens

meta-prompt-optimizer

Audit and rewrite prompts against Claude Opus 4.7 instruction-following best practices. Produces a scored audit plus a rewritten prompt. Use when the user asks to audit, review, critique, rewrite, improve, optimize, tighten, score, fix, migrate, or draft a prompt — including system prompts, CLAUDE.md files, Claude…

theagenticguy/erpaval · 230 tokens