St4ck Lite Marketplace
- Updated July 14, 2026
- edo-ceder/st4ck-lite
st4ck-lite is a Claude Code plugin that pairs st4ck browse recording skills with deterministic markdown replay so agents can author and rerun UI tests without ongoing LLM calls.
About
st4ck-lite-marketplace is the free Claude Code plugin for the st4ck browser testing runner. Your agent records flows through a stable IPC vocabulary, saves markdown tests you can commit, and replays them with Playwright-grade waits without paying per rerun. Pick it when you want agent-assisted E2E authoring that stays deterministic in CI, without the paid st4ck platform connection.
- Manifest promises agent-authored tests with deterministic markdown replay
- st4ck browse --record writes traces replayable with zero LLM cost
- Compact IPC vocabulary and locator-priority ladder for self-heal tier one
- Bundled PRD authoring skills and three reviewer agents in the lite repo
St4ck Lite Marketplace by the numbers
- Data as of Jul 15, 2026 (Skillselion catalog sync)
/plugin marketplace add edo-ceder/st4ck-liteAdd your badge
Show developers this marketplace is listed on Skillselion. Paste this into your README.
| Last updated | July 14, 2026 |
|---|---|
| Repository | edo-ceder/st4ck-lite ↗ |
How do you turn agent-driven browser walks into committed tests that replay fast and cheaply when selectors drift?
Record browser flows with your agent into markdown tests and replay them deterministically in CI without further LLM calls.
Who is it for?
Teams adopting st4ck-runner who want lite marketplace skills for record-and-replay E2E without app.st4ck.io connectivity.
Skip if: Groups needing Tier-2 LLM self-heal, TRIAD attestation, or multi-project orchestration reserved for paid st4ck.
What you get
Markdown test files, deterministic Playwright replays, and optional PRD review outputs from bundled authoring agents.
Plugins in this marketplace
1 plugin - install individually after you add the marketplace.
Recommended Marketplaces
FAQ
What does the marketplace manifest emphasize?
It states the plugin lets your AI agent author tests and replay them deterministically.
How is replay different from ad-hoc browser MCP tools?
README says recorded markdown reruns use pure Playwright with zero LLM calls, unlike intent-retranslation each run.
What requires the paid platform?
Tier-2 LLM self-heal, cross-project knowledge base, TRIAD attestation, and several orchestration features are paid-only per README table.