debug-methodical

debug-methodical is a skill for Claude Code from TheBeardedBearSAS/claude-craft. It costs 38 tokens per session (1,307 once invoked), scanned A, original, MIT.

A four-phase method for debugging: reproduce the problem, isolate its root cause, fix it, and verify the result. It applies to bugs, regressions, flaky tests, and unexpected behaviour.

In plain words
What is it for?
Use it to investigate bugs, create regression tests, find faulty commits, and verify that a fix actually works.
Why use it?
It replaces guesswork with a repeatable investigation and requires a reliable reproduction before changing code.

Skill for Claude Code

Written for Claude Code: context: fork in frontmatter.

Part of the claude-craft plugin — 56 skills, 94 commands, 47 agents, 5 hooks 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/thebeardedbearsas/claude-craft/debug-methodical
Any agent
npx skills add TheBeardedBearSAS/claude-craft --skill debug-methodical
Clone the repo
git clone --depth 1 https://github.com/TheBeardedBearSAS/claude-craft

Made for: Claude Code.

Or install claude-craft, the plugin that ships this one along with the rest of its 56 skills, 94 commands, 47 agents, 5 hooks.

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-methodical

README.md
[![agentmods](https://agentmods.dev/badge/skills/thebeardedbearsas/claude-craft/debug-methodical.svg)](https://agentmods.dev/skills/thebeardedbearsas/claude-craft/debug-methodical)
Your own site
<a href="https://agentmods.dev/skills/thebeardedbearsas/claude-craft/debug-methodical"><img src="https://agentmods.dev/badge/skills/thebeardedbearsas/claude-craft/debug-methodical.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,307 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 5.1 $0.00038 $0.01307
Opus 5 $0.00019 $0.00654
Sonnet 5 $0.00008 $0.00261
Haiku 4.5 $0.00004 $0.00131

Measured 2d ago against content hash 022350db841f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

debug-methodical 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Reproduire avec `curl` ou client minimal
.claude/skills/debug-methodical/SKILL.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debug-Methodical — Debugging en 4 phases

Skill inspiré de obra/superpowers. Objectif : forcer une méthode rigoureuse au lieu de "try random fixes until it works".

Règle d'or : un bug sans reproduction stable est un bug mal compris. Ne JAMAIS fixer avant de reproduire.

Les 4 phases (strictes, dans l'ordre)

Phase 1 : REPRODUCE

Objectif : exécuter le bug à volonté, dans un environnement contrôlé.

Checklist :

  • Étapes de reproduction documentées (Given/When/Then)
  • Reproduction déterministe (>= 3 runs consécutifs identiques)
  • Environnement isolé (local, container, test env)
  • Inputs minimaux (le moins de données/steps possible)
  • Version/commit exacts identifiés

Sortie : test automatisé qui échoue en exposant le bug (test de régression).

Signal rouge : "ça marche sur ma machine" / "parfois ça fail" → reproduction insuffisante, retour Phase 1.

Phase 2 : ISOLATE

Objectif : identifier la cause racine, pas juste un symptôme.

Techniques :

  • Bisect : git bisect pour trouver le commit fautif
  • Binary search dans le code : commenter la moitié, puis itérer
  • Print-driven debugging : logs aux frontières (entrée/sortie fonctions)
  • Debugger : breakpoints, step-through, variable watch
  • Diff environnements : que diffère-t-il entre "qui marche" et "qui casse" ?
  • Question the premise : l'hypothèse initiale est-elle correcte ?

Checklist :

  • Cause identifiée (ligne / condition / input exact)
  • Explication du pourquoi (pas juste le quoi)
  • Chaîne de causalité documentée (A cause B cause C)
  • Autres manifestations potentielles du même bug identifiées

Signal rouge : "je pense que c'est X" sans preuve → retour isolate avec instrumentation.

Phase 3 : FIX

Objectif : corriger la cause racine avec le minimum de changement.

Checklist :

  • Fix au bon niveau (cause racine, pas symptôme)
  • Changement minimal (KISS, voir rule 05)
  • Pas d'effet de bord sur autres features
  • Pas de fix "au cas où" / spéculatif (voir rule 23 Karpathy)
  • Fix dans le bon layer (domain / infra / UI)

Read the full file on GitHub · 127 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 · 127 lines · 38 tokens per session scan A 022350db841f

Subscribe to this mod's changes

debug-methodical is a skill published in the GitHub repository TheBeardedBearSAS/claude-craft (105 stars, last pushed 3d ago), licensed MIT. It adds 38 tokens to every session and 1,307 once invoked, about $0.0002 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 2026-09-03.

Related

Other skills, from other repositories

debug-systematic

Systematic 4-phase debugging methodology for complex, intermittent, or mysterious issues. Use when investigating bugs, race conditions, or unexplained failures.

travisjneuman/.claude · 33 tokens

extracting-code-structure

Use when listing all methods, functions, or classes in a file, exploring unfamiliar code, getting API overviews, or deciding what to read selectively without loading entire files.

SebastienDegodez/copilot-instructions · 39 tokens

audit-dead-code

Hunt dead code across a whole repository through four labelled lanes of unequal confidence. Knip (TS/JS unused files, exports, types, enum members), vulture (Python symbols), gopls (Go unexported symbols), and a portable grep lane (shell and other symbol languages), then adjudicate every candidate against the…

melodic-software/claude-code-plugins · 254 tokens

analyzing-code-structure

Use when editing code structure with text matching ambiguity, handling "oldstring not unique" problems, or performing formatting-independent pattern matching across function signatures, method calls, and class structures.

SebastienDegodez/copilot-instructions · 42 tokens

fortify

Fortify existing code by splitting large functions, adding edge-case coverage, and backfilling unit tests. Use when user asks to "fortify", "harden", "bulletproof", "make robust", "make solid", "strengthen", "add missing tests", "split functions", or wants to improve reliability of existing code. Don't use for new…

helderberto/agent-skills · 93 tokens

devils-advocate

Stress-test plans and proposals via systematic adversarial review. Assumption extraction, evidence check, failure scenarios, operational gotchas. Before implementation begins. Use when: asked to attack a plan or proposal ('devil's advocate', 'stress test', 'poke holes', 'what could go wrong'), or before implementation…

melodic-software/claude-code-plugins · 139 tokens