coagent8-session
Skill2 starsChanged 11 days agoMITView on GitHub
List CoAgent8 sessions, read a session's history, close a session or cancel its running turn through the CoAgent8 session and cancel tools. Use when the user wants to continue an earlier consult or review, see what another agent answered, stop a long-running call, or clean up sessions.
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- coagent8-workflowSkill
- pr-mergeSkill
- coagent8-consultSkill
- coagent8-delegateSkill
- coagent8-doctorSkill
- coagent8-issueSkill
- coagent8-loopSkill
- coagent8-reviewSkill
The file
Files
CoAgent8 sessions
- List: call
sessionwithaction: list. - History: call
sessionwithaction: historyand thesession_handle, oraction: messagesto skip tool events; page withcursorandlimit. Eventsequenceis the stored log position; public history combines or filters events, so sequence gaps do not mean lost events. - Continue: call consult or review again with the same
session_handle. That keeps the other agent's context; a call without it starts from nothing. - Cancel: call
cancelwith thesession_handleto stop the running turn. The session is not closed. With aroot_handleinstead it stops every delegated agent of that root and no new one starts in it. - Root: call
sessionwithaction: rootand theroot_handleto see the limits, what they used and the state of each delegated task. - Close: call
sessionwithaction: closewhen the conversation is finished.delete_history: truealso deletes its history; ask the user before deleting.
The handle is in the footer of every consult or review result. Pass
workspace_path only when the session belongs to a different repository than
the current workspace.
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.

