agentleFS
Sign inStart free
buddyhbuddyh/agent-skills/branch-session/skill.md

branch-session

Skill5 starsChanged 8 months agoMITView on GitHub

Branch the current Claude Code or Codex session into a new tmux session. Creates a parallel conversation that can diverge independently. Use when you want to explore an alternative approach without losing your current context.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create a "branch" of the current conversation by spawning a new tmux session that continues from the same session.

    line 10
  2. Distinctive:

    Create a unique session name:

    line 42
  3. Distinctive:

    Run the branch script:

    line 51
  4. Distinctive:

    Test something risky without losing progress

    line 80

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
skill.md

Branch Session

Overview

Create a "branch" of the current conversation by spawning a new tmux session that continues from the same session. Both sessions can then diverge independently. The original session remains untouched.

Platform Support

  • Claude Code: Uses claude --continue <session-id> to resume from the same session
  • Codex: Uses codex resume <session-id> to resume from the same session

Workflow

Step 1: Get Current Session ID

Claude Code:

  1. Get current working directory
  2. Convert to Claude project path format:
    # /home/user/projects/myapp -> -home-user-projects-myapp
PROJECT_PATH=$(echo "$PWD" | sed 's|/|-|g' | sed 's|^-||')
  3. Find most recently modified session file:
    SESSION_FILE=$(ls -t ~/.claude/projects/$PROJECT_PATH/*.jsonl 2>/dev/null | head -1)
SESSION_ID=$(basename "$SESSION_FILE" .jsonl)

Codex:

# Find recent session files
ls -t ~/.codex/sessions/$(date +%Y/%m/%d)/*.jsonl 2>/dev/null | head -5

Step 2: Generate Branch Name

Create a unique session name:

SHORT_ID=$(echo "$SESSION_ID" | cut -c1-5)
TIMESTAMP=$(date +%H%M)
BRANCH_NAME="branch-${SHORT_ID}-${TIMESTAMP}"

Step 3: Execute Branch

Run the branch script:

~/.claude/skills/branch-session/scripts/branch_session.sh "$PWD" "$SESSION_ID" "$BRANCH_NAME"

The script creates a new tmux session and launches the agent with session context:

  • Claude Code: claude --continue $SESSION_ID
  • Codex: codex resume $SESSION_ID

Step 4: Confirm

Report to user:

Branched session: branch-a1b2c-1508
Directory: /home/user/projects/myapp
Resuming: a1b2c3d4-da03-4ece-8625-582be89f6dff

To attach: tmux attach -t branch-a1b2c-1508

Quick Reference

Invocation: /branch

Session naming: branch-<first-5-chars-of-id>-<HHMM>

Use cases:

  • Explore alternative implementation approaches
  • Test something risky without losing progress
  • Split work into parallel tracks

Setup

Make the script executable (one-time):

chmod +x ~/.claude/skills/branch-session/scripts/*.sh

Requirements

  • tmux installed and running
  • Claude Code CLI (claude) or Codex CLI (codex)
  • Active session to branch from

Resources

scripts/

  • branch_session.sh - Creates tmux session and continues from current session

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free