Orchestrate large-scale changes across the codebase using parallel worktree agents. Use when you need to apply similar changes to many files or modules simultaneously.
Scanned 9/10/2026
Install to Claude Code
npx -y skills add keychat-io/keychat-app --skill batch --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Batch?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/keychat-io-batch)More formats (shields.io, HTML) on the badges page.
---
name: batch
description: "Orchestrate large-scale changes across the codebase using parallel worktree agents. Use when you need to apply similar changes to many files or modules simultaneously."
invoke: user
---
# Batch
Research and plan a large-scale change, then execute it in parallel across isolated worktree agents.
## Workflow
### Phase 1: Research & Plan
1. Understand the requested change thoroughly
2. Identify all files and modules that need modification
3. Group changes into independent, parallelizable units (max 10 units)
4. Present the plan to the user for approval before proceeding
### Phase 2: Execute
1. For each unit of work, launch an Agent with `isolation: "worktree"` to make the changes independently
2. Run agents in parallel where possible (up to 5 concurrent agents)
3. Each agent should:
- Make the required changes
- Run relevant tests or lint checks
- Commit changes with a clear message
### Phase 3: Review & Merge
1. Collect results from all agents
2. Report successes and failures
3. For successful changes, present diffs for user review
4. Help merge changes back to the main branch
## Rules
- Always get user approval before executing changes
- Never modify more than what was requested
- If a unit fails, continue with others and report the failure
- Keep the user informed of progress throughout
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling