Reproduce Chat States
different-ai/openwork
Fires known chat states in the running OpenWork desktop app, such as provider errors, retries and tool steps, so you can check how each renders.
Before picking new work, smoke-test the last "completed" feature.
Install Broken Window Check
$ npx skills add Archive228/loopkit --skill broken-window-check -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Archive228/loopkit broken-window-check --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Archive228/loopkit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/broken-window-check .claude/skills/broken-window-check && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "broken-window-check" agent skill from https://github.com/Archive228/loopkit/tree/main/skills/broken-window-check into .claude/skills/broken-window-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "broken-window-check", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Archive228/loopkit/tree/main/skills/broken-window-checkType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Archive228/loopkit --skill broken-window-check -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Archive228/loopkit broken-window-check --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Archive228/loopkit.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/broken-window-check .agents/skills/broken-window-check && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "broken-window-check" agent skill from https://github.com/Archive228/loopkit/tree/main/skills/broken-window-check into .agents/skills/broken-window-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "broken-window-check", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Archive228/loopkit --skill broken-window-check -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Archive228/loopkit broken-window-check --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Archive228/loopkit.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/broken-window-check .cursor/skills/broken-window-check && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "broken-window-check" agent skill from https://github.com/Archive228/loopkit/tree/main/skills/broken-window-check into .cursor/skills/broken-window-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "broken-window-check", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Archive228/loopkit.git --path skills/broken-window-check--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Archive228/loopkit --skill broken-window-check -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Archive228/loopkit broken-window-check --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Archive228/loopkit.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/broken-window-check .gemini/skills/broken-window-check && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "broken-window-check" agent skill from https://github.com/Archive228/loopkit/tree/main/skills/broken-window-check into .gemini/skills/broken-window-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "broken-window-check", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Archive228/loopkit broken-window-checkInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Archive228/loopkit --skill broken-window-check -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Archive228/loopkit.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/broken-window-check .github/skills/broken-window-check && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "broken-window-check" agent skill from https://github.com/Archive228/loopkit/tree/main/skills/broken-window-check into .github/skills/broken-window-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "broken-window-check", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Archive228/loopkit --skill broken-window-check -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Archive228/loopkit broken-window-check --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Archive228/loopkit.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/broken-window-check .opencode/skills/broken-window-check && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "broken-window-check" agent skill from https://github.com/Archive228/loopkit/tree/main/skills/broken-window-check into .opencode/skills/broken-window-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "broken-window-check", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
broken-window-check- GitHub stars
- 756
- Token cost
- ~899 tokens
- SKILL.md length
- 492 words
- Files
- 1
- Skills in repo
- 43
- Repo updated
- First seen
- Licence
- MIT
At a glance
Before picking new work, smoke-test the last "completed" feature.
- Works in 5 steps: Read the last "done" entry in the shift… → Drive the feature end-to-end using the… → Compare observed behavior to the spec —… → …
- Tasks that involve QA and bug reports
- SKILL.md covers The sequence — run in order,…, What "end-to-end" means, Red flags — the check is not… and Cost, plus 1 more section
- Calls git
What it does
Broken Window Check is an agent skill from Archive228/loopkit. 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.
Its SKILL.md is about 900 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Testing & QA, covering QA and bug reports. The repository describes itself as: 33 battle-tested skills + minimal .claude harness for any coding agent (Claude Code, Cursor, Codex, Gemini CLI). The licence is MIT.
When your agent uses it
- Tasks that involve QA and bug reports
Example prompts
- “completed”
- “looks shipped, isn”
- “/broken-window-check”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Read the last "done" entry in the shift notes / feature list (whichever the project uses).
- Drive the feature end-to-end using the actual runtime path — browser automation, HTTP request, CLI invocation. Not the unit test.
- Compare observed behavior to the spec — the steps field on the feature, or the acceptance criteria in the spec.
- If it works — proceed to normal work selection. Note the check in the shift notes ("verified feature N still green").
- If it fails —
What it can do on your machine
Read from SKILL.md and the folder at commit 5ae033e. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
git
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Broken Window Check loads about 899 tokens when it runs. Until then it costs about 54 tokens; SKILL.md has 492 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from Archive228/loopkit at commit 5ae033e, republished under its MIT licence (© Archive228). 492 words, ~899 tokens.
Download SKILL.mdSave it as
.claude/skills/broken-window-check/SKILL.md (or your agent's skills folder).- name
- broken-window-check
- 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.
- when_to_use
- start of any session in a multi-session project, right after reading progress notes and running init.sh
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
- Read the last "done" entry in the shift notes / feature list (whichever the project uses).
- Drive the feature end-to-end using the actual runtime path — browser automation, HTTP request, CLI invocation. Not the unit test.
- Compare observed behavior to the spec — the
stepsfield on the feature, or the acceptance criteria in the spec. - If it works — proceed to normal work selection. Note the check in the shift notes ("verified feature N still green").
- If it fails —
git revertthe commit that claimed completion (do not force-push).- Set that feature's status back to
not-donein 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 |
Show full SKILL.md (198 more words)Show less
Red flags — the check is not doing its job
- You're reading tests instead of running the feature. Tests can pass while the feature is broken (wrong route, missing CORS, config mismatch). Drive the runtime.
- You add a mock to make the check pass. The mock is the bug. Remove it, watch the failure, that's the real state.
- You "fix" by editing the feature list to match reality ("oh it never supported X"). No. Revert. Re-open. Fix the code or negotiate scope in the spec, not the ledger.
- You skip the check because "it worked yesterday". Yesterday's session doesn't run today's dev server.
Cost
The check is 30-90 seconds per session in a healthy project. In a project that's about to go sideways, it saves hours. The dropout in premature-completion rate is roughly 4x when the check is enforced vs. not (measured in shift-work-style agent runs).
Pairs with
shift-notes— the ledger the check reads and writes.adversarial-verify— run this on the current session's diff before claiming done, so the next session doesn't have to broken-window you.verification-before-completion— the general form of "don't claim without evidence".
If every session enforces the check, the compounding-error mode of shift-work agents stops compounding.
© Archive228, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/broken-window-check of Archive228/loopkit.
Open the folder on GitHubat commit 5ae033e
Compare with similar skills
Broken Window Check next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Broken Window Check this skillArchive228/loopkit | 756 | — | ~899 | Automated safety check: Pass | MIT | |
| Reproduce Chat Statesdifferent-ai/openwork | 24k | — | ~673 | Automated safety check: Pass | Custom licence | |
| Dynamo Jira TicketDynamoDS/Dynamo | 2k | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| Minimal Run And Auditlllllllama/RigorPilot-Skills | 497 | 2 repos | ~691 | Automated safety check: Pass | MIT | |
| Moav E2EMotherofallVPNs/MoaV | 448 | — | ~1.9k | Automated safety check: Notes | MIT | |
| Anchor Reprolynxlangya/techne | 105 | 1 repos | ~1.2k | Automated safety check: Pass | MIT |
Similar skills
Dynamo Jira Ticket
DynamoDS/Dynamo
Create structured Jira tickets for Dynamo from bug reports, failing tests, or feature requests.
Minimal Run And Audit
lllllllama/RigorPilot-Skills
Rigor Run skill for README-first deep learning repo reproduction.
Moav E2E
MotherofallVPNs/MoaV
Run and debug MoaV's end-to-end tests — real protocol connectivity (client-test.sh) and the moav CLI smoke test — against a LIVE server, via the self-hosted e2e workflow or a local test VPS.
Anchor Repro
lynxlangya/techne
Reproduce a behavioral bug before fixing it, record the failing probe, and verify the fix with the same probe.
Creating A Coral Task
Human-Agent-Society/CORAL
Author a new CORAL task — the three pieces that must line up (task.yaml, seed/, a packaged grader/), the coral init → coral validate → smoke-test loop, and how to pick a grader pattern (stdout…
More from Archive228/loopkit
All 43 skills in this repoHitl Escalate
Archive228/loopkit
Escalate blocked runs to a human via configured channel or fallback to BLOCKED.md and exit the loop.
Structured Output
Archive228/loopkit
Get JSON out of the model reliably. An agent skill from Archive228/loopkit.
Using Loopkit
Archive228/loopkit
A skill your agent uses when starting any conversation in a loopkit-enabled project - establishes how to find and use loopkit's 49 skills, requiring skill invocation before ANY response including…
Active Memory Reminder
Archive228/loopkit
Before compaction Loopkit extracts decisions into claude-decisions.json (machine-readable).
Eval Harness
Archive228/loopkit
Build a repeatable eval loop that grades agent output with an LLM judge, so prompt/skill changes get scored against a baseline instead of eyeballed.
Feature List JSON
Archive228/loopkit
Enumerate every end-to-end feature as strict JSON entries with passes:false, editable-passes-only discipline, and priority order.
Related
Categories
Questions about Broken Window Check
What does Broken Window Check do?
Before picking new work, smoke-test the last "completed" feature. Broken Window Check is an agent skill from Archive228/loopkit. Before picking new work, smoke-test the last "completed" feature.
When should I use Broken Window Check?
Broken Window Check fits situations like: tasks that involve QA and bug reports.
How do I install Broken Window Check in Claude Code?
Run `npx skills add Archive228/loopkit --skill broken-window-check -a claude-code`. Or copy the skill folder (skills/broken-window-check in Archive228/loopkit) into .claude/skills/broken-window-check in your project. Claude Code loads it when a task matches its description.
How do I install Broken Window Check in Codex?
Run `npx skills add Archive228/loopkit --skill broken-window-check -a codex`. Or copy the skill folder (skills/broken-window-check in Archive228/loopkit) into .agents/skills/broken-window-check in your project. Codex loads it when a task matches its description.
Can I use Broken Window Check in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Archive228/loopkit --skill broken-window-check -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/broken-window-check, .gemini/skills/broken-window-check, .github/skills/broken-window-check and .opencode/skills/broken-window-check in your project.
What does Broken Window Check need to run?
Going by SKILL.md and its folder, Broken Window Check needs the command-line tools its instructions call (git).
Does Broken Window Check access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Broken Window Check safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Broken Window Check use?
Broken Window Check is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Broken Window Check use?
About 899 tokens (SKILL.md is roughly 3.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Broken Window Check?
Skills that share tags, products or a category with Broken Window Check: Reproduce Chat States (different-ai/openwork, 24k stars), Dynamo Jira Ticket (DynamoDS/Dynamo, 2k stars), Minimal Run And Audit (lllllllama/RigorPilot-Skills, 497 stars) and Moav E2E (MotherofallVPNs/MoaV, 448 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Broken Window Check?
Archive228 (a GitHub user) maintains it in Archive228/loopkit, which has 756 GitHub stars. The repository holds 43 skills in this directory. The repository was last updated on July 14, 2026.
Source: Archive228/loopkit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.