crush-session
Skill0 starsChanged 3 months agoMITView on GitHub
Manage Crush sessions - rename, list, inspect, and delete conversations. Use when organizing or navigating Crush session history.
In this repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- agentSkill
- agents-md-syncSkill
- aur-pkg-analysisSkill
- commitSkill
- gen-agentSkill
- git-aware-mvSkill
- tg-notifySkill
- tg-notipySkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 31
All actions are routed through a single script.
- Very specific: line 47
All actions support --json for machine-readable output.
- Very specific: line 69
If the title is null, the session has not been renamed yet.
- Distinctive: line 121
Run the script with no arguments for usage help.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Initialize todos for crush-session operation:
{
"todos": [
{"content": "Initialize crush-session operation", "status": "in_progress", "active_form": "Initializing crush-session operation"},
{"content": "Detect requested action and execute", "status": "pending", "active_form": "Detecting action and executing"},
{"content": "Complete crush-session operation", "status": "pending", "active_form": "Completing crush-session operation"}
]
}Update todos: mark "Initialize crush-session operation" as completed, mark "Detect requested action and execute" as in_progress.
Crush Session Management
Manage Crush CLI sessions: get the current session ID, rename, list, show details, or delete sessions.
Entry Point
All actions are routed through a single script. Grant execute permission once:
python3 scripts/crush-session.pyActions
Detect the user's intent and execute the matching action:
current- show the current session ID and titlerename- rename the current or a specific sessionlist- list all sessionsshow- show details of a specific sessiondelete- delete a session by ID
All actions support --json for machine-readable output.
BEGIN EXECUTION IMMEDIATELY. Do not ask the user what they want to do. Start with step 1:
- Detect the action from the user's request.
Update todos: mark "Detect requested action and execute" as in_progress.
- Execute the corresponding workflow below.
Update todos: mark "Complete crush-session operation" as in_progress.
- Report the result.
Update todos: mark "Complete crush-session operation" as completed. Clear todos with
todos([]).
Workflow: Get Current Session
scripts/crush-session.py currentIf the title is null, the session has not been renamed yet.
scripts/crush-session.py current --jsonWorkflow: Rename Session
# Rename current session
scripts/crush-session.py rename "New Title"
# Rename a specific session by ID
scripts/crush-session.py rename <id> "New Title"
# Machine-readable output
scripts/crush-session.py rename <id> "New Title" --jsonWorkflow: List Sessions
# Human-readable list
scripts/crush-session.py list
# Machine-readable JSON
scripts/crush-session.py list --jsonWorkflow: Show Session Details
# Show current session
scripts/crush-session.py show
# Show specific session
scripts/crush-session.py show <id>
# Machine-readable output
scripts/crush-session.py show <id> --jsonWorkflow: Delete Session
scripts/crush-session.py delete <id>Confirm the session ID before deleting. If the user wants to delete the current session, warn them first.
Tips
- Run the script with no arguments for usage help.
- Session IDs accept a UUID, full hash, or hash prefix (e.g.,
96fd792644642c54). - The
$CRUSH_SESSION_IDenv var is only available from within the Crush TUI.
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.

