- Home
- Skills
- Testing & Debugging
- bug-finder
Works with the AI Agents you already use
Bug Finder
One command runs four parallel QA agents that scan your codebase, auto-fix safe issues, commit them, and report everything else.
$6.99
bug-finder
Example session with this skill installed
/bug-finder
- Read your context and instructions
- Compiled the bug-finder
BUG FINDER REPORT — AUTO-FIXED (3): X-scroll overflow → globals.css; missing rel on external link → src/app/page.tsx:87; console.log removed → src/lib/api.ts:34. NEEDS YOUR ATTENTION (2): hardcoded API key → src/lib/client.ts:5; missing aria-expanded on hamburger menu → src/components/Nav.tsx:23. SUMMARY: 42 files scanned, 5 issues, 3 auto-fixed, 2 manual, commit a3f92bc.
Connects securely to your tools. The creator never sees your data.
About this skill
Run a full automated bug sweep on the current project. Detect project type, launch four parallel review agents, announce and apply all auto-fixable bugs, commit the fixes, and produce a detailed final report.
Read package.json (or pubspec.yaml for Flutter, *.csproj for .NET) to identify the stack. Also scan the file tree to understand scope: number of pages/routes, animation libraries (Framer Motion, GSAP, AOS), image handling strategy, form/interactive elements, and whether there is a backend API.
| Stack | Agents to run |
|---|---|
| Next.js / React | All 4 agents |
| Node / Express API | Agent 1 (functional), Agent 4 (perf/security) |
| Plain HTML/CSS/JS | Agents 1, 2, 4 — skip TypeScript checks in Agent 3 |
| React Native | All 4 agents — Agent 2 uses mobile-specific checks |
| Electron | Agents 1, 3, 4 |
| Full-stack | All 4 agents |
| Unknown / mixed | All 4 agents — skip checks that don't apply |
Announce the detected project type and which agents will run before starting.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Testing & Debugging.
Not a linter or CVE scanner (not a replacement for Snyk or Semgrep), and it cannot judge UX feel or copy quality. Auto-fixes are limited to safe changes; anything needing design or business-logic decisions is reported, not changed.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 1 day ago
- Software
Git
Python 3
- Optional
- A web, Node, React NativeorElectron project (for code scan)A website you ownorare authorised to test (for live testing)PlaywrightorGoogle Chrome
Live testing contacts only the website you name and confirm you are authorised to test, same host only, about one request per second. The bundled scripts read no environment variables, run no shell commands, and send nothing to any other server. Without a browser tool, live testing runs in a limited
Permissions
File Scopes
Auto-commits only the files it fixed. No network access required.