debug

debug is a skill for Claude Code, Codex from OutlineDriven/odin-claude-plugin. It costs 33 tokens per session (2,714 once invoked), scanned A, original, Apache-2.0.

A structured method for finding the cause of a failing test, crash, exception, wrong result, regression, or intermittent failure. It starts by creating a repeatable signal, then tests explanations against the code.

In plain words
What is it for?
Use it to investigate test failures, production errors, flaky behavior, regressions, and incorrect output. It can guide the creation of a failing test, HTTP check, command-line check, or other repeatable probe.
Why use it?
It replaces guesswork with evidence and narrows a problem to the smallest incorrect assumption that explains it. This is especially useful when the cause is not obvious or the failure is inconsistent.

Skill for Claude CodeCodex

Part of the odin plugin — 54 skills, 2 agents 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/outlinedriven/odin-claude-plugin/debug
Any agent
npx skills add OutlineDriven/odin-claude-plugin --skill debug
Clone the repo
git clone --depth 1 https://github.com/OutlineDriven/odin-claude-plugin

Made for: Claude Code, Codex.

Or install odin, the plugin that ships this one along with the rest of its 54 skills, 2 agents.

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/outlinedriven/odin-claude-plugin/debug.svg)](https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/debug)
Your own site
<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/debug"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/debug.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,714 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 $0.00033 $0.02714
Opus 5 $0.00016 $0.01357
Sonnet 5 $0.00007 $0.00543
Haiku 4.5 $0.00003 $0.00271

Measured 4d ago against content hash 41c1283db7aa, 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 4d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/hitl-loop.template.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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 · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

A bug is a falsified assumption. Build a signal that can catch it, then find the smallest assumption that explains the divergence.

When to Apply / NOT

Apply: test fails and cause unclear; production stack trace; intermittent / flaky behavior; wrong output without crash; regression after known commit window; heisenbug.

NOT apply: performance regression with correct outputs; security defect; symptom obvious from one-line read; architectural confusion.

Diagnostic process

Do not skip a phase unless you explicitly justify why. A feedback loop comes before a theory about the code.

Phase 1 — Build a feedback loop

This is the skill. Build a tight pass/fail signal that goes red on this bug before hypothesizing. Bisection, hypotheses, and probes consume that signal; without it, reading code is guesswork. Spend disproportionate effort here. Be creative and do not give up early.

Ways to construct one

Try these in roughly this order:

  1. Failing test at a seam that reaches the bug: unit, integration, or end-to-end.
  2. HTTP script against a running development server.
  3. CLI invocation with fixture input, comparing stdout with a known-good snapshot.
  4. Headless browser script that drives the UI and asserts on the DOM, console, or network.
  5. Replay a captured trace by saving a real request, payload, or event log and replaying it through the isolated path.
  6. Throwaway harness that starts the smallest useful system subset with mocked dependencies and one call through the bug path.
  7. Property or fuzz loop that runs many generated inputs and detects the failure mode.
  8. Bisection harness that automates checking a known commit, dataset, or version range so git bisect run can use it.
  9. Differential loop that runs the same input through an old and new version, or two configurations, then compares their output.
  10. Human-in-the-loop shell script only when a person must act. Copy and adapt scripts/hitl-loop.template.sh; the agent runs it and captured output returns to the investigation.

Read the full file on GitHub · 167 lines

Files

What ships with it

5 files 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. 4d ago First seen · 167 lines · 33 tokens per session scan A 41c1283db7aa

Subscribe to this mod's changes

debug is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed today), licensed Apache-2.0. It adds 33 tokens to every session and 2,714 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 2026-08-30.

Related

Other skills, from other repositories

java-clean-arch

Reviews or implements Clean Architecture / Hexagonal Architecture (Ports & Adapters) and DDD tactical patterns for Java projects. Use when user asks to "apply clean architecture", "implement hexagonal architecture", "add ports and adapters", "apply DDD", "refactor to clean arch", "review architecture", or "add value…

ducpm2303/claude-java-plugins · 68 tokens

java-adr

Creates, lists, and manages Architecture Decision Records for Java projects. Use when user asks to "create an ADR", "document this decision", "write an architecture decision", "add ADR", "list decisions", "show ADRs", or "record this architectural choice".

ducpm2303/claude-java-plugins · 54 tokens

java-test

Generates JUnit 5 and Mockito unit tests or Testcontainers integration tests, auto-detecting project setup. Use when user asks to "write tests", "generate tests", "add unit tests", "create test class", "test this service", or "write integration tests".

ducpm2303/claude-java-plugins · 57 tokens

java-cache

Use when the user asks to add caching, configure Redis or Caffeine cache, use @Cacheable/@CacheEvict/@CachePut, optimize repeated database or API calls, or review existing Spring Boot cache configuration.

ducpm2303/claude-java-plugins · 46 tokens

java-jpa

Reviews Spring Data JPA for N+1 queries, fetch strategies, projections, and Specifications. Use when user asks to "review JPA", "check for N+1", "JPA performance", "review my entities", "check fetch strategy", or "review my repositories".

ducpm2303/claude-java-plugins · 57 tokens

java-logging

Reviews Java logging for SLF4J best practices, MDC context, structured logging, and PII safety. Use when user asks to "review logging", "check my logs", "logging review", "is my logging correct", "MDC setup", or "check for PII in logs".

ducpm2303/claude-java-plugins · 60 tokens