Wreck Trace

Trace wreck-it findings to the source code responsible. It maps the route or API endpoint to its handler, follows stack frames, greps for UI strings, reads the code and writes file, line, snippet, why and confidence onto each finding. Never guesses a line. Use as stage 9 of a wreck-it run, or when the user asks "where is this bug in my code" for a wreck-it finding.

Software Development Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add miyannishar/wreck-it

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add miyannishar/wreck-it --skill wreck-trace
Manual install
git clone --depth 1 https://github.com/miyannishar/wreck-it.git /tmp/wreck-it
mkdir -p ~/.claude/skills
cp -r /tmp/wreck-it/skills/wreck-trace ~/.claude/skills/wreck-trace

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# wreck-trace

`WRECK` means `npx @miyanishar/wreck-it`.

`WRECK run stage trace running`

Work through `WRECK finding list --json`. Trace every **reproduced** finding that has no `source`, in severity order. Trace unreproduced findings too if time allows.

## Method (per finding)

1. **Start from evidence.**
   - **Console stack trace:** take the top frame inside the project, not inside `node_modules`. In dev builds the file paths are usually real. With bundled paths (`/_next/static/chunks/…`), use source maps if they exist (`.next/**/*.map`, `dist/**/*.map`). Otherwise fall back to grep.
   - **Failing request:** match `evidence.network[].url` against `discovery.json` `api[]` (method and path, where `[id]` matches any segment) to get the handler `file`.
   - **Route:** match against `discovery.json` `pages[]` to get the page file, then follow its imports to the components that render the broken element.
2. **Grep for anchors.** Search the source, excluding `node_modules`, `.next`, `dist`, `build`, for:
   - text visible near the bug: button names, labels, headings
   - the `testId`/label values in `steps`
   - API paths
   - error messages from the console

   Example: `grep -rn "Place order" src app components --include=*.tsx`
3. **Read the code** from where the data comes in to where it goes wrong, and find the faulty line. The faulty line is the one that, if changed, fixes the bug, not just the first line you landed on.
   - A wrong total points at the arithmetic.
Read the full skill on GitHub

Details

Skill name
wreck-trace
Path
skills/wreck-trace/SKILL.md
License
MIT
Repo updated
25 October 2026

FAQ

What does the Wreck Trace skill do?

Trace wreck-it findings to the source code responsible. It maps the route or API endpoint to its handler, follows stack frames, greps for UI strings, reads the code and writes file, line, snippet, why and confidence onto each finding. Never guesses a line. Use as stage 9 of a wreck-it run, or when the user asks "where is this bug in my code" for a wreck-it finding.

How do I install the Wreck Trace skill?

Claude Code plugin: /plugin marketplace add miyannishar/wreck-it. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Related skills

Wreck Chaos

miyannishar/wreck-it

Chaos-test a running local web app as the chaos-monkey persona, using a page sweep, an API fuzzer (plus Schemathesis when there's an OpenAPI spec), hostile form inputs, double-submits, back/forward/refresh mid-flow, multiple tabs, offline/slow/500-injected network, expired or tampered sessions, an axe-core scan and keyboard-only navigation. Records reproducible bugs with wreck-it. Use as stage 6 of a wreck-it run, or when the user asks to "break my forms", "chaos test", "try weird inputs", "test offline", or "check accessibility".

Testing & QAIn 1 list

Wreck Explore

miyannishar/wreck-it

Explore a running local web app through Playwright MCP as a normal user (every core flow plus data-integrity checks) and then in character as each persona from .wreck-it/personas.md, recording reproducible bugs with wreck-it. Use as stages 4–5 of a wreck-it run, or when the user asks to "click through my app like a user", "test the happy paths", "try my app as a beginner", or "check my core flows".

Testing & QAIn 1 list

Wreck It

miyannishar/wreck-it

Full wreck-it run against a locally running web app. It tests like normal users, ICP personas, rushed beginners, chaos monkeys and traffic spikes, then writes a scored bug report with source file:line and regression Playwright tests. Use when the user says "wreck my app", "wreck it", "test my app like a user", "find bugs before launch", "is my app ready to ship", or asks for a readiness score. Also for one feature, such as "test the checkout", "just test signup", "check the coupon flow" (a focused run). For a single stage ("just stress test my API", "only check accessibility"), use the matchin

Testing & QAIn 1 list

Explain Codebase

agentkitco/agentkit-dev-skills

Map an unfamiliar repo covering purpose, entry points, how to run it, main modules, data flow and risky areas, with file references. Use when asked to explain or onboard onto a codebase.

Software DevelopmentIn 1 list

Validating Performance Budgets

jeremylongshore/claude-code-plugins-plus-skills

This skill enables Claude to validate application performance against defined budgets. It's useful for identifying performance regressions early in the development lifecycle. The skill is triggered when the user mentions "performance budget", "validate budget", "performance regression", or requests a check against performance metrics like "page load times", "bundle sizes", "API response times", or "Lighthouse scores". The plugin validates against predefined thresholds and alerts on violations. It is especially helpful in CI/CD pipelines to prevent performance degradation in production.

Software Development

Repro First Debugging

agentkitco/agentkit-dev-skills

Debug by reproducing the failure first, then forming and testing hypotheses before editing code. Use when asked to fix a bug, a failing test, a crash or unexpected behavior.

Software DevelopmentIn 1 list

Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.