empiricaai/empirica/message-cleanup
Claude Code and agent skill by empiricaai/empirica
- community
Checking that the SKILL.md file is still in the repository.
Daily housekeeping body for the canonical `message-cleanup` loop. Prunes expired git-notes mesh messages so the inbox stays focused on un-read ones. Loaded by the loop scheduler when the cron entry fires (default 03:17 daily) — never invoked directly by a user. Triggers: `<task-notification>` from the message-cleanup loop, "message housekeeping", "expired messages", "prune mesh".
Install
npx vskill@latest install empiricaai/empirica/message-cleanupSKILL.md
Message Cleanup — daily housekeeping body
This is a scheduled-loop body skill, not a user-facing workflow. The message-cleanup canonical loop fires once a day (cron 17 3 * * *) and wakes a session to run this skill. The runtime is short: one CLI verb + a receipt log.
When this fires
The TUI cockpit registers this loop alongside cortex-mailbox-poll when the user toggles L on an instance for the first time, or by explicit empirica loop register --name message-cleanup --kind cron --cron "17 3 * * *". On fire, the AI sees a <task-notification> and loads this skill.
What to do
One command, then close out:
The verb walks refs/notes/empirica/messages/ for any message whose expiry_at is in the past and removes them. JSON output shape:
If removed_count > 0, log a brief finding so the cleanup is visible in the project's audit trail:
If removed_count == 0, no artifact needed — silent success is fine.
Then signal heartbeat and you're done:
What NOT to do
- Don't open an empirica transaction for this — it's a pure CLI
cleanup, no praxic decisions to gate.
- Don't run with
--dry-rununless you're debugging. The loop's
scheduled fire IS the action.
- Don't escalate to user attention unless the verb errors. A scheduled
cleanup is supposed to be invisible.
Source
- Verb:
empirica message-cleanup— handler at
empirica/cli/command_handlers/message_commands.py::handle_message_cleanup_command
- Underlying logic:
empirica/core/canonical/empirica_git/message_store.py::cleanup_expired - Catalog entry:
empirica/core/cockpit/canonical_loops.py(this loop)
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingempirica/plugins/claude-code-integration/skills/message-cleanup/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/empiricaai/empirica/message-cleanup)