debugging

A methodical workflow for finding the root cause of software bugs. It reproduces the failure, narrows it down, tests one hypothesis at a time, fixes the underlying problem, and adds a regression test.

In plain words
What is it for?
Use it to reproduce errors, isolate failing inputs or code paths, inspect stack traces, verify a diagnosis, implement a root fix, and prove the bug stays fixed.
Why use it?
It reduces guesswork and helps ensure that a fix addresses the actual failure rather than only hiding its visible symptom.

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/duyet/oma/debugging
Any agent
npx skills add duyet/oma --skill debugging
Clone the repo
git clone --depth 1 https://github.com/duyet/oma

Made for: Claude Code, Codex.

Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 902 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 $0.00088 $0.00902
Opus 5 $0.00044 $0.00451
Sonnet 5 $0.00018 $0.00180
Haiku 4.5 $0.00009 $0.00090

Measured yesterday against content hash a6c625d01189, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debugging 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 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.

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.

examples/skills/debugging/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

debugging

A bug you can't reproduce is a bug you can't fix — you'll just be guessing and calling it done. Work the loop: reproduce → isolate → hypothesize → verify → fix at the root → prove it stays fixed.

1. Reproduce before anything else

  • Get the exact repro steps, input, and environment. "It sometimes fails" is not a repro — find what makes it deterministic (specific input, ordering, timing, state).
  • Confirm you're looking at the real failure: run it yourself, read the actual error/stack trace/logs, don't work from a paraphrase of the symptom.
  • If it won't reproduce locally, get closer to production: same data shape, same config, same concurrency — the gap is usually the cause.

2. Isolate the failure

  • Bisect. Binary-search over commits (git bisect), inputs (halve the dataset until it still fails), or code paths (comment out / short-circuit sections) to shrink the failure to the smallest thing that still reproduces it.
  • Read the stack trace bottom-up for exceptions — the throw site, not just where it surfaced. For wrong-output bugs, trace the value backwards from where it's wrong to where it was last known-correct.
  • Separate "where it manifests" from "where it's caused" — a null-pointer three calls deep is usually a bad value passed in much earlier.

3. Form one hypothesis at a time

  • State the hypothesis explicitly ("I think X because Y") before changing code. A hypothesis you can't state, you can't falsify.
  • Test it with the smallest possible check — a log line, a debugger breakpoint, an assertion, a one-line repro script — not a speculative fix.
  • If the check disproves the hypothesis, say so and move to the next one. Don't quietly keep the disproven assumption baked into later reasoning.

4. Instrument, don't guess

  • Prefer a debugger or targeted logging at the exact point of divergence over scattering print/console.log everywhere. Each instrumentation point should answer a specific question.
  • Log actual values, not just "got here" — "reached line 42" tells you nothing a stack trace didn't already.
  • Remove debug instrumentation before calling the bug fixed; don't leave print-driven debugging in the shipped diff.

Read the full file on GitHub · 79 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 · 79 lines · 88 tokens per session scan A a6c625d01189

Subscribe to this mod's changes

debugging is a skill published in the GitHub repository duyet/oma (5 stars, last pushed 12d ago), licensed Apache-2.0. It adds 88 tokens to every session and 902 once invoked, about $0.0004 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

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

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 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