Debrief
ProductivitydebriefDebrief is an Agent Skill for productivity published in the davepoon/buildwithclaude repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Alias for `/origin:handoff` — symmetric brief/debrief naming. Same behavior: end-of-session ritual that writes session log + project status + granular MCP captures. Invoked as `/debrief`. Use when the user prefers the brief/debrief pair over brief/handoff.
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/davepoon/buildwithclaude/blob/HEAD/plugins/origin/skills/debrief/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/debrief, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
/debrief
Alias for /handoff. Identical behavior — full end-of-session ritual:
git context grab (if repo), narrative session log at
~/.origin/sessions/, project status update, granular MCP captures.
Run the steps in /origin:handoff exactly. Same artifacts, same
guardrails. The only reason this skill exists is the symmetric naming —
/brief (session start) ↔ /debrief (session end). Pick whichever
verb feels natural; both invoke the same flow.
When to use
- User says "wrapping up", "let's call it", "we're done", "debrief".
- Session about to close and useful state would otherwise be lost.
When NOT to use
- Mid-flow capture during work → use
/capture(single memory). - Search / lookup → use
/recall.