debugging-systematically

A step-by-step method for finding and fixing software bugs. It starts by reproducing the problem and ends by checking that the fix works.

In plain words
What is it for?
Use it to reproduce bugs, narrow them to a file or function, test possible causes, and confirm fixes.
Why use it?
It prevents guesswork by using evidence from errors, tests, and controlled checks. This makes it easier to locate the actual cause instead of treating symptoms.

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/porcupine-md/jonggrang/debugging-systematically
Any agent
npx skills add porcupine-md/jonggrang --skill debugging-systematically
Clone the repo
git clone --depth 1 https://github.com/porcupine-md/jonggrang

Made for: Claude Code, Codex.

Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 746 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 $0.00026 $0.00746
Opus 5 $0.00013 $0.00373
Sonnet 5 $0.00005 $0.00149
Haiku 4.5 $0.00003 $0.00075

Measured 2d ago against content hash e35911443ba4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debugging-systematically 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.

skills/library/backend/debugging-systematically/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The 6-Step Debugging Protocol

Step 1: Reproduce Reliably

Before anything else, make the bug reproducible.

# Write a failing test that reproduces the bug
it('reproduces bug #123', async () => {
  // The exact scenario that causes the bug
  const result = await service.doThing(buggyInput);
  expect(result).toBe(expectedValue); // This fails currently
});

If you can't write a reproducible test, you don't understand the bug yet.

Step 2: Read the Error

Read the FULL error message + stack trace. Most bugs tell you exactly where they are.

Checklist:

  • What file and line number?
  • What was the actual value vs expected?
  • Is there an inner error wrapped in the outer one?

Step 3: Narrow the Scope (Binary Search)

Full system broken?
  → Is it the database connection or the business logic?
    → Is it in the controller or the service?
      → Is it in the query or the parsing?

Add console.log / breakpoints to establish:

  • What inputs enter the broken function?
  • What does the function actually return?

Step 4: Form a Hypothesis

State your hypothesis explicitly:

"I believe the bug is caused by [X] because [evidence Y]."

Common hypotheses:

  • Off-by-one error
  • Async/await missing (uncaught promise)
  • Null/undefined not handled
  • Type coercion (== vs ===)
  • Race condition
  • Stale cache/state

Step 5: Verify (Don't Fix Yet)

Prove your hypothesis is correct BEFORE fixing:

// Add assertion to confirm hypothesis
console.assert(typeof userId === 'string', `userId is ${typeof userId}`);

If the hypothesis is wrong, go back to Step 3.

Step 6: Fix and Confirm

  1. Apply the minimal fix
  2. Run the reproduction test — it should now pass
  3. Run the full test suite — nothing should break
  4. Write a regression test if one didn't exist

Common Bug Patterns

Async bugs:

// BUG: forgot await
const user = getUser(id); // returns Promise, not User
user.name; // undefined

// FIX:
const user = await getUser(id);

Read the full file on GitHub · 122 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 · 122 lines · 26 tokens per session scan A e35911443ba4

Subscribe to this mod's changes

debugging-systematically is a skill published in the GitHub repository porcupine-md/jonggrang (11 stars, last pushed 6d ago), licensed MIT. It adds 26 tokens to every session and 746 once invoked, about $0.0001 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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 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