← Browse
agent-recap
rogermas05 ★ 0
This Claude Code plugin hooks into agent turns to catch when an agent finishes without reporting test failures—it sends the agent back once to fix the issue or explicitly acknowledge the failure. It checks for outdated test claims, unrun validations, and missing failure disclosures by analyzing shell command history and test-runner output.
Install
> /plugin marketplace add rogermas05/agent-recap
> /plugin install agent-recap
What it's made of
1 hook
- Commands
- 0
- Agents
- 0
- Skills
- 0
- MCP servers
- 0
- Hooks
- 1 · Stop
What it needs & plugs into
- API keys
- none
- Paid services
- none detected
- External tools
node- 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 (rogermas05).