testing-debugging

A guide for finding bugs in deployed applications and writing tests that reproduce them. It covers unit tests, browser-console checks, and repeatable bug investigation.

In plain words
What is it for?
Use it to investigate reported bugs, create a failing test, fix the code, and check related behavior with additional tests.
Why use it?
It replaces repeated manual checking in a browser with a test that reliably shows the failure and confirms the fix. Unit tests are small automated checks that can run quickly during development.

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/qaml-ai/camelai/testing-debugging
Any agent
npx skills add qaml-ai/camelAI --skill testing-debugging
Clone the repo
git clone --depth 1 https://github.com/qaml-ai/camelAI

Made for: Claude Code, Codex.

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,428 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 $0.00048 $0.02428
Opus 5 $0.00024 $0.01214
Sonnet 5 $0.00010 $0.00486
Haiku 4.5 $0.00005 $0.00243

Measured 2d ago against content hash a49905367353, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

testing-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.

sandbox/skills/testing-debugging/SKILL.md · 332 lines

How it starts

The opening of the file, as written. The whole thing — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Testing and Debugging

This skill guides debugging deployed applications and writing tests for rapid iteration. The key insight: unit tests are the fastest way to reproduce and fix bugs.

The Unit Test Debugging Workflow

This is the most effective debugging workflow. Instead of repeatedly deploying and manually testing in the browser, write a unit test that reproduces the bug:

Why Unit Tests for Debugging?

Approach Cycle Time Reliability
Deploy → Browser → Manual test 30-60 seconds Variable
Run unit test 1-2 seconds Consistent

A 30x speedup means you can iterate 30 times faster. This compounds: what takes an hour with manual testing takes 2 minutes with unit tests.

The Workflow

  1. Understand the bug - Read the user report, check console errors, understand expected vs actual behavior

  2. Write a failing test - Create a test that reproduces the exact failure

    // Example: User reports "discount not applied to cart total"
    test('applies discount code to cart total', () => {
      const cart = createCart([
        { name: 'Widget', price: 100 },
        { name: 'Gadget', price: 50 }
      ]);
    
      cart.applyDiscount('SAVE20'); // 20% off
    
      expect(cart.total).toBe(120); // Was returning 150
    });
    
  3. Run the test to confirm it fails - Verify you've reproduced the bug

    bun test
    
  4. Fix the code - Make changes to fix the failing test

  5. Run the test again - Confirm the fix works

    bun test
    
  6. Deploy - Once tests pass, publish through the mediated project tool (not a package-manager or Wrangler deploy command)

    await tools.deploy_project({ project: "<project-name>" });
    

Test File Location

Place test files next to the code they test:

src/
  cart.ts
  cart.test.ts      # Tests for cart.ts
  utils/
    discount.ts
    discount.test.ts

Or use a __tests__ directory:

Read the full file on GitHub · 332 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 · 332 lines · 48 tokens per session scan A a49905367353

Subscribe to this mod's changes

testing-debugging is a skill published in the GitHub repository qaml-ai/camelAI (357 stars, last pushed 3d ago), licensed MIT. It adds 48 tokens to every session and 2,428 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.