checkpoint-approval

Enforce user approval at task checkpoint transitions with flag files.

4|Updated Sep 25, 2025
One-click install
npx skills add https://github.com/cowwoc/styler --skill checkpoint-approval
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: checkpoint-approval
Source: https://github.com/cowwoc/styler/tree/main/.claude/skills/checkpoint-approval
Command: npx skills add https://github.com/cowwoc/styler --skill checkpoint-approval

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Critical transitions in AI workflows (e.g., approving a plan, merging changes) require explicit user consent. Bypassing these checkpoints can lead to unintended consequences. This Skill enforces mandatory user approval, ensuring human oversight and preventing costly errors.

Core Features & Use Cases

  • Clear Presentation: Presents the plan or changes to the user in a clear, structured format, explicitly requesting approval.
  • Indefinite Waiting: Crucially, the skill stops and waits indefinitely for explicit affirmative user input, preventing accidental or silent progression.
  • Approval Flag Creation: Upon receiving explicit approval, it creates a persistent flag file (user-approved-synthesis.flag or user-approved-changes.flag) as an audit trail.
  • State Transition: Transitions the task to the next appropriate state (e.g., IMPLEMENTATION or COMPLETE) only after approval is secured and the flag is created.
  • Use Case: After a complex implementation plan has been synthesized, use this Skill to present the plan to the user for approval. It will wait until the user explicitly says "approved" or "proceed," ensuring the user has full control over the project's direction before any code is written.

Quick Start

After the SYNTHESIS phase completes, invoke the skill for plan approval: TASK_NAME="implement-formatter-api" /workspace/main/.claude/scripts/checkpoint-approval.sh
--task "$TASK_NAME"
--type "plan"
--plan-file "/workspace/tasks/$TASK_NAME/task.md"

Frequently Asked Questions about checkpoint-approval

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I enforce mandatory user approval in AI workflows before critical transitions?

Checkpoint-approval enforces mandatory user approval at critical workflow transitions by presenting plans or changes and waiting indefinitely for explicit consent. It prevents accidental progression by requiring affirmative input like 'approved' or 'proceed' before transitioning the task to the next state.

Can I prevent users from bypassing plan approvals in task workflows?

Yes. Checkpoint-approval blocks progression until explicit user approval is received. It creates an audit trail via flag files and only transitions the task state after approval and flag creation, ensuring human oversight prevents bypass.

How do I present synthesized plans to users for approval before implementation?

After the SYNTHESIS phase, invoke checkpoint-approval with the plan file and task name. It presents the plan in structured format, waits indefinitely for explicit approval, creates a persistent flag upon consent, and transitions to IMPLEMENTATION only after approval is secured.

What's the best way to add human-in-the-loop control to automated workflows?

Checkpoint-approval integrates human-in-the-loop control by halting workflows at critical checkpoints, presenting synthesized output clearly, and requiring explicit user consent before state transitions. This satisfies compliance requirements and prevents unintended consequences from silent progression.

Does checkpoint-approval create audit trails for compliance?

Yes. Upon receiving explicit approval, checkpoint-approval creates persistent flag files (user-approved-synthesis.flag or user-approved-changes.flag) that serve as an audit trail, documenting when and that user approval was granted before state transitions.

When should I use checkpoint-approval versus allowing automatic task progression?

Use checkpoint-approval for high-risk transitions requiring explicit consent—plan approvals, change merges, or compliance checkpoints. Avoid it for low-risk autonomous tasks where user oversight isn't mandatory or where indefinite waiting would block necessary automation.