opencode2-self-management
Skill89 starsChanged todayGPL-3.0View on GitHub
Drive your own opencode2 session from inside an agents-sandbox VM - request a context compaction through the session.compact API, tell the TUI's --port server from the CLI's `serve --service` background service, refresh an edited skill or scope a skill query, or clean up a scratch `opencode2 serve` without killing the session's own daemon. Use when an agent is asked to compact/shrink its own context, when an edited skill "didn't change", when a project skill is missing from the bare /api/skill list, or before `pkill`-ing a scratch server.
In this repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- bare-worktreesSkill
- compacting-contextSkill
- greptile-reviewSkill
- handle-pr-feedbackSkill
- maintainSkill
- opencode2-probeSkill
- prSkill
- rebase-statusSkill
- releaseSkill
- terminal-resetSkill
- upstream-driftSkill
The file
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

