# aSPARK

> Gated AI product team for Claude Code — An agile AI product team for Claude Code that gates every feature through spec, plan, build, review and QA.

- Page: https://tesign.com/en/item/aspark/
- JSON: https://tesign.com/en/item/aspark/index.json
- Korean Markdown: https://tesign.com/item/aspark/index.md
- Generated: 2026-09-23 04:12 UTC

## Numbers

- 22 stars — checked on GitHub 2026-09-22 07:32 UTC
- no 7-day star increase observed (GH Archive) (as of 2026-09-22 23:00 UTC)
- 1 Show HN points — observed 2026-09-22 08:42 UTC
- Star total = the value last checked on GitHub (stars_checked_at) + increases observed via GH Archive since. The 24h · 7d · 30d gains are GH Archive hourly events summed to the reference time (as_of). No score of ours.

## AT A GLANCE

- LICENSE: MIT (permissive) — https://spdx.org/licenses/MIT.html
- USAGE: Use, change and redistribute, commercially too. Keep the notice.
- OPEN SOURCE: YES
- LANGUAGE: [unconfirmed]
- PLATFORM: cli
- CATEGORY: DEV TOOLS · AI
- Tags: ai 코딩 · claude code · 품질 관리 · 오픈소스
- How to start: Install to use
- SOURCES: Show HN https://github.com/a-lottes/aSPARK
- INSTALL: https://aspark.lottes.dev/

## ACTIVITY

- Last commit: 2026-09-22 05:18 UTC
- Latest release: [unconfirmed]
- Contributors: [unconfirmed]
- Open issues (incl. PRs): [unconfirmed]
- Made by: [unconfirmed]
- Checked on GitHub: 2026-09-22 07:32 UTC

## Signals and evidence

- NEW · 2h OLD WHEN SEEN

## TESIGN TAKE

Plenty of tools claim AI-assisted development; requiring a human gate five separate times, with a reviewable paper trail, is what's different here.

## WHY IT MATTERS

Hand a whole feature to an AI and scope creeps, or nothing gets verified. aSPARK splits the work across a Product Owner, Designer, Engineering Manager, Developer, Reviewer, QA Tester and Release Manager, and won't let a feature move to the next phase without your explicit gate approval.

## BUILD FROM THIS

- No service, no account — it installs into a project as Markdown. Running /spark drives the whole loop and leaves spec.md, plan.md, review.md, qa.md and a release log in .spark/; the QA phase opens a real browser and clicks through the running app.

## WHO IT'S FOR

- Solo developers and small teams building with Claude Code who want AI work checked at every phase, not just at the end.

## START IN 5 MINUTES

```
# Inside a Claude Code session, run /plugin marketplace add a-lottes/aSPARK then /plugin install aspark@aspark; on a new project, start with /charter.
```

## CAVEATS

- Requires Claude Code and Git; the browser QA phase (/demo-day) needs a browser integration such as Claude in Chrome or a Playwright MCP server. Newly released, with 24 stars so far.

## RECEIPT

- FIRST SEEN BY TESIGN: 2026-09-22 07:01 UTC
- AT SOURCE: 2026-09-22 04:14 UTC
- KEPT: 2026-09-23 02:05 UTC
- Published on TESIGN: 2026-09-23 02:05 UTC
- Text last updated: 2026-09-23 02:05 UTC

## How to read this

- This file was produced by the same build, from the same data, as the tesign.com item page. The text is editorial; the numbers are stored observations.
- null in the JSON means not observed — never zero. The Markdown writes [unconfirmed] for it.
- Star total = the value last checked on GitHub (stars_checked_at) + increases observed via GH Archive since. The 24h · 7d · 30d gains are GH Archive hourly events summed to the reference time (as_of). No score of ours.
- A summary, not legal advice.

[Image] https://tesign.com/img/aspark-23216f9ee6.png