batch-plan-execute

Name: batch-plan-execute Review
Item: batch-plan-execute
Rating: 2.8
Author: Aaron Matthews

Skill Productivity Usable

Works inClaude Code

Usable Scanned — metadata only

Gives Claude a structured batch planning capability — plan multiple tasks, then execute them sequentially with progress tracking.

An Agent Skill that has coding agents write plan documents in parallel from a task list using subagents, then execute those plans in parallel. It analyzes task dependencies automatically, supports free-form human review, saves original and revised plan versions to disk, and produces a checklist.md for acceptance review. Works with Claude Code, Codex, and OpenCode; distributed as part of the micooz/skills collection.

Plan multi-file changes before executing any edits
Break large refactors into ordered batches for safe execution
Review the full change plan before Claude starts writing code

11 starsMIT (commercial OK)FreeQuick setup

Usable rating — This tool is functional but has notable gaps. Review the evaluation notes below before deploying.

Why it matters

Gives Claude a structured batch planning capability — plan multiple tasks, then execute them sequentially with progress tracking. Prevents the 'do everything at once' failure mode.

Best for

Developers working on multi-file refactors or feature implementations who need Claude to plan before acting.

Works in

Claude Code Claude Cowork Claude Chat

Source

https://github.com/micooz/skills

By micooz

How to Get It

Option 1: Claude Desktop App (Code Mode)Click the + button next to the prompt box → Plugins → Add plugin. Search and click Install. Skills work in Claude Code only.

Option 2: Paste into Claude CodeCopy the command below and paste it into your conversation. Claude will install it.

Command

npx skills add micooz/skills --skill batch-plan-execute

Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.

First thing to try

After installing, paste this into Claude:

Help me plan multi-file changes before executing any edits

PrerequisitesA coding agent that supports subagents; the author recommends an AI model good at long-horizon tasks.CostFree

Trust Signals Auto-scanned

Stars11Contributors1Last updated2026-04-08LicenseMIT (OK for commercial use)Known CVEsNone foundSources: GitHub Advisory Database + OSV.dev · Scanned 2026-08-17 · scanner v1

Reviewer notes

Auto-scanned review. These are observations, not a security certification.

catalog_hygiene stale-eval refresh: Scored from trust signals (evidence-eval-v1): 11 GitHub stars; 1 contributors; last commit 89d ago; license MIT.

Things to check

Requires careful prompt design to avoid over-planning scope; agent may struggle if task dependencies are implicit or if mid-execution corrections are needed. No built-in rollback if later tasks in the batch fail.
Single maintainer. Consider the risk if this person stops maintaining the project.

How to evaluate tools before deploying →

Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.

Evaluation Scores

Evaluation

Ease of Use

3/5

Versatility

2/5

Reliability

3/5

Security

3/5

Overall score2.75 / 5.00 UsableEvaluatedJul 2026

catalog_hygiene stale-eval refresh: Scored from trust signals (evidence-eval-v1): 11 GitHub stars; 1 contributors; last commit 89d ago; license MIT.

← Back to the Claude Observatory