claude

debrief

Debriefs of completed agent work

36 on GitHubv0.1.6updated 2 days ago
/

Plugin debrief from marketplace alignment-hive in Crazytieguy/alignment-hive. Commands read from the repo's manifest — yesterday.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (1)

  • debrief

    This skill should be used when the user asks for a debrief, review or report of what was done in this session, or for another round of an earlier debrief. Also offer it when a long stretch of work the user wasn't watching is finished. Not for reviewing code this session did not write.

Hooks (1)

  • SessionStart

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/session-start.sh"

View source on GitHub alignment-hive.com

More from Crazytieguy/alignment-hive

All 17 plugins →

Non-Claude models (GPT, Grok, Muse) as native Claude Code subagents via a local routing gateway

2 skills · 10 agents

36

hive

claude

Tooling recommendations and session sharing for alignment researchers

3 skills · 1 command · 1 agent · hooks

36

autopilot

claude

Deprecated: superseded by Claude Code's built-in auto mode. Autonomous operation with permission management.

2 skills · hooks

36

Literature review pipeline (arXiv, Semantic Scholar, LessWrong)

1 skill · 1 agent

36

Cloud GPU instances with Jupyter kernels for AI/ML workloads

1 skill · 1 MCP server

36

Deprecated: no longer maintained. Set up Claude Code GitHub Action for autonomous issue and PR handling.

1 skill

36

Maintain debrief?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins17 plugins