Standup

When you've got work scattered across multiple branches or PRs and need to figure out how to collapse them into one clean worktree, this runs a structured conversation between branch-specific agents in a shared markdown file. Each branch gets its own Claude instance that reports what changed, then the facilitator walks them through resolving overlaps and picking a merge target. It's read-only by design: the agents decide the plan, you execute it afterward with /do. The workflow is opinionated (YAML front matter, atomic file locks, numbered rounds) but the payoff is a concrete consolidation strategy instead of you manually diffing everything. Best when you've got three or more active branches and the merge order isn't obvious.

skills.sh installs: 3.7K
GitHub stars: 115.5K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add thedotmack/claude-mem --skill standup --agent claude-code

Installs into .claude/skills of the current project.

Files

standup — facilitate a group chat between branch-agents

You're the facilitator. Each of the user's git worktrees (and any PRs they pick) joins a shared markdown chat as its own agent, and the agents reconcile their scattered work into ONE consolidated worktree. You convene the room, run the conversation in rounds, and carry the outcome back — the reconciling happens in the chat, between the agents.

The room is one shared file (default ~/.claude-mem/STANDUP.md): YAML front matter holds the goal + prompt; the body is the transcript. Writes are atomically locked, so agents speak at once. It is read-only — agents decide how the merge should go; nobody commits or merges inside the room. Real git work happens afterward via /do.

1. Fill the room

Two ways, mixable:

By recency (common) — worktrees active in a window:
```
node "${CLAUDE_SKILL_DIR}/standup.mjs" worktrees --since <1h|4h|24h|7d|all> --json
```
Active = a commit or an uncommitted/staged/untracked edit in the window. If the user didn't name a window, offer 1h / 4h / 24h / 7d / all.

SKILL.md on GitHub