bug-investigation

bug-investigation is a skill for Claude Code, Codex from Arroyo-Gonzalo/codex-devkit. It costs 44 tokens per session (830 once invoked), scanned A, original, MIT.

A process for finding the root cause of bugs, exceptions, failing tests, incorrect behavior, regressions, or intermittent failures before changing code.

In plain words
What is it for?
Use it to reproduce failures, inspect logs and tests, trace validation and business logic, examine persistence and integrations, and then apply the smallest safe fix.
Why use it?
It prevents fixes based on guesses and narrows the problem through evidence, reproduction, and tracing the path from input to failure.

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/arroyo-gonzalo/codex-devkit/bug-investigation
Any agent
npx skills add Arroyo-Gonzalo/codex-devkit --skill bug-investigation
Clone the repo
git clone --depth 1 https://github.com/Arroyo-Gonzalo/codex-devkit

Made for: Claude Code, Codex.

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 bug-investigation

README.md
[![agentmods](https://agentmods.dev/badge/skills/arroyo-gonzalo/codex-devkit/bug-investigation.svg)](https://agentmods.dev/skills/arroyo-gonzalo/codex-devkit/bug-investigation)
Your own site
<a href="https://agentmods.dev/skills/arroyo-gonzalo/codex-devkit/bug-investigation"><img src="https://agentmods.dev/badge/skills/arroyo-gonzalo/codex-devkit/bug-investigation.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 830 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 5.1 $0.00044 $0.00830
Opus 5 $0.00022 $0.00415
Sonnet 5 $0.00009 $0.00166
Haiku 4.5 $0.00004 $0.00083

Measured 5d ago against content hash 79793d196db7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

bug-investigation 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 5d 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/bug-investigation/SKILL.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bug Investigation

Purpose

Identify the root cause of a defect and correct it with the smallest safe change.

Do not begin by modifying code based only on assumptions.

Investigation workflow

1. Establish the problem

Determine:

  • expected behavior;
  • actual behavior;
  • affected environment;
  • reproduction conditions;
  • frequency;
  • error messages, logs, or stack traces;
  • whether the issue is new or previously existed.

When information is incomplete, inspect available evidence before requesting additional details.

2. Reproduce the failure

Attempt to reproduce the issue using the narrowest practical scenario.

Prefer:

  • a focused failing test;
  • a minimal request;
  • a specific command;
  • a small data fixture;
  • an isolated execution path.

Do not perform broad changes merely to reproduce the problem.

If reproduction is not possible, clearly state the limitation and continue using available evidence.

3. Trace the execution path

Inspect the relevant path from input to failure.

Identify:

  • entry point;
  • validation;
  • transformations;
  • business logic;
  • persistence operations;
  • external integrations;
  • error handling;
  • response generation.

Read only the files necessary to understand that path.

4. Gather evidence

Use evidence from:

  • error messages;
  • stack traces;
  • logs;
  • failing tests;
  • configuration;
  • recent changes;
  • version history when relevant;
  • database state;
  • network requests;
  • runtime behavior.

Distinguish observed facts from assumptions.

5. Form hypotheses

Create a short list of plausible causes.

Prioritize hypotheses using:

  • available evidence;
  • proximity to the failure;
  • recent changes;
  • likelihood;
  • ability to verify safely.

Do not present speculation as a confirmed cause.

6. Verify the most likely cause

Test the highest-confidence hypothesis before changing production code.

Verification may include:

  • adding a focused test;
  • inspecting values at the failure boundary;
  • running a narrow command;
  • comparing expected and actual data;
  • checking configuration;
  • reviewing a recent diff.

Read the full file on GitHub · 177 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. 5d ago First seen · 177 lines · 44 tokens per session scan A 79793d196db7

Subscribe to this mod's changes

bug-investigation is a skill published in the GitHub repository Arroyo-Gonzalo/codex-devkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 830 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens