agentic-qa
This Claude Code plugin runs live, human-in-the-loop QA walkthroughs against finished features by driving a browser, API, and CLI against ticket acceptance criteria and merged PRs, with adversarial critic passes and embedded screenshots in the report. It orchestrates drafter-and-critic agent rounds to extract behaviors and plan verification steps, flags blast-radius risks by reading diffs, and handles both contained test actions and external real-world operations with appropriate escalation.
Install
Source: https://github.com/bobtat/claude-plugins/tree/HEAD/plugins/agentic-qa
What it's made of
1 command · 7 agents · 5 skills · 1 MCP server · 1 hook
- Commands
- 1
- Agents
- 7
- Skills
- 5
- MCP servers
- 1
- Hooks
- 1 · PreToolUse
What it needs & plugs into
- API keys
- none
- Paid services
- none detected
- External tools
nodenpx- Talks to
- nothing external detected
Analyzed . Facts extracted from the plugin's files. Prose generated by claude-haiku-4-5-20251001.
Is this your plugin?
Claim it to keep the card accurate and enter the weekly contest. Requires signing in as the GitHub owner (bobtat).