debugging

A step-by-step method for finding the underlying cause of technical problems, such as errors, failed commands, or unexpected behaviour. It checks the error details, saved project state, configuration, and environment before changing code.

In plain words
What is it for?
Use it to reproduce failures, narrow them to a file or line, compare possible causes, inspect persistent state, and verify that the final fix solves the original problem.
Why use it?
It reduces guesswork and prevents fixes that only hide the visible symptom. It also helps when a problem comes from stale files, cached data, lock files, or invalid settings.

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

Made for: Claude Code, Codex.

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 944 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 $0.00047 $0.00944
Opus 5 $0.00023 $0.00472
Sonnet 5 $0.00009 $0.00189
Haiku 4.5 $0.00005 $0.00094

Measured 2d ago against content hash a7618ade945f, 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 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.

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.

.agents/skills/debugging/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debugging

Read [[principles/fix-root-causes]] before starting. Every debugging session follows that principle: trace to root cause, never paper over symptoms.

Process

  1. Reproduce. Get the exact error. Run the failing command, read the full output. If you can't reproduce, you can't verify your fix.

  2. Read the error. The error message, stack trace, and line numbers are data. Read all of it before forming hypotheses. Most bugs tell you exactly where they are.

  3. Suspect state before code. Before debugging code, check persistent state — especially on restart bugs or environment drift. See [[principles/fix-root-causes]].

    • Noodle state: .noodle/orders.json (stale items?), .noodle/sessions/ (orphaned?), .noodle.toml (valid?)
    • Environment: tmux sessions (tmux ls), lock files, cached artifacts
    • Config: .noodle.toml validation (noodle start reports diagnostics), skill frontmatter parse errors
    • Persistent files: brain/ notes, plan files, todos — check for corruption or stale references
  4. Isolate. Narrow the scope. Which file? Which function? Which line? Use binary search: comment out half, see if it still fails, repeat.

  5. Find root cause. The first "fix" that comes to mind is usually a symptom fix. Ask "why?" until you hit the actual cause:

    • Test fails → mock is wrong → interface changed → type doesn't match runtime shape → fix the type
    • Build fails → import error → circular dependency → restructure the modules
    • Runtime crash → undefined value → missing null check → data source returns null on empty → handle empty case at the source
  6. Fix and verify. Fix the root cause, not the symptom. Then verify: run the test, run the build, exercise the feature path. "It compiles" is not verification.

  7. Check for the pattern. If the bug existed in one place, grep for the same pattern elsewhere. Fix all instances, or make it structurally impossible.

Noodle-Specific Diagnostics

Read the full file on GitHub · 65 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 · 65 lines · 47 tokens per session scan A a7618ade945f

Subscribe to this mod's changes

debugging is a skill published in the GitHub repository poteto/noodle (263 stars, last pushed 5mo ago), licensed MIT. It adds 47 tokens to every session and 944 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

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