# Broken Window Check

Before picking new work, smoke-test the last "completed" feature.

- Repository: https://github.com/Archive228/loopkit (756 stars)
- Category: Testing
- License: MIT
- Last updated: 2026-07-14
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add Archive228/loopkit --skill broken-window-check -g -a claude-code -y`
Codex: `npx skills add Archive228/loopkit --skill broken-window-check -g -a codex -y`
Cursor: `npx skills add Archive228/loopkit --skill broken-window-check -g -a cursor -y`
Gemini CLI: `npx skills add Archive228/loopkit --skill broken-window-check -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add Archive228/loopkit`

## Description

Before picking new work, smoke-test the last "completed" feature. If it's broken, revert and re-open it before touching anything else. Kills the "looks shipped, isn't shipped" bug across sessions.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Broken-Window Check

Across shift-notes-driven sessions (see `shift-notes`), agents will sometimes mark a feature complete after unit tests pass, even when the feature is end-to-end broken. The next session opens the repo, sees a green git log, and builds on top of a broken foundation. By the time anyone notices, three features are stacked on the crack.

**The check:** before picking new work, exercise the most recently "completed" feature end-to-end. If it fails, treat it as your only job this session.

## The sequence, run in order, no skipping

1. **Read the last "done" entry** in the shift notes / feature list (whichever the project uses).
2. **Drive the feature end-to-end** using the actual runtime path, browser automation, HTTP request, CLI invocation. Not the unit test.
3. **Compare observed behavior to the spec**, the `steps` field on the feature, or the acceptance criteria in the spec.
4. **If it works**, proceed to normal work selection. Note the check in the shift notes ("verified feature N still green").
5. **If it fails**, - `git revert` the commit that claimed completion (do not force-push).
   - Set that feature's status back to `not-done` in the feature list.
   - Note in shift notes: "reverted feature N, cause: <one line>".
   - Fix it. That is your entire session.

Do not pick new work on top of a broken previous feature. Ever.

## What "end-to-end" means

The check must exercise the path the user actually takes. Anything less is theater.

| Feature shape | Valid check | Invalid check |
|---|---|---|
| Web UI button | Puppeteer/Playwright click → observe DOM | `expect(handler).toHaveBeenCalled()` |
| HTTP endpoint | `curl` the route → check status + body | Unit test on the handler function |
| CLI flag | Invoke the binary with the flag → observe output | Import the parser, assert on the AST |
| Background job | Trigger it → wait → assert side effect | Assert the job function returns |

## Red flags, the check is not doing its job

The rest: https://github.com/Archive228/loopkit/blob/HEAD/skills/broken-window-check/SKILL.md