Plan Executor With Checkpoints skill for Claude and Codex

Plan Executor With Checkpoints as an AI skill. It asks for The plan, Verification command, Starting state and 2 more, then does the rest. Free to install in…

Install it once and Claude or Codex runs it for you. When your request matches, your AI loads the skill, asks for anything it is missing, and works through the template itself. Prefer to fill it in by hand? See the full prompt template.

Download the skill (.zip) · View SKILL.md

When it is used

Use when a written implementation plan is ready to be carried out step by step with verification after each task. Do not use for writing the plan itself or debugging a failure the plan did not anticipate. Related topics: coding, productivity.

What it will ask you for

• The plan (longer free text)
• Verification command (free text, e.g. "The command that runs the tests or checks")
• Starting state (free text, e.g. "Branch name and whether the suite is green now")
• On failure (choose one: Stop and report, Try one fix then stop, Skip and continue)
• Report after each task (choose one: Yes, No)

How it works

1. Run the verification command first and record the baseline result so pre-existing failures are known.
2. For each task, make only the described change, run the check and read the real output before marking it done.
3. On a failed check, apply the chosen failure rule and report the exact output without altering tests to hide it.
4. Stop and describe the problem when a task is wrong or larger than planned, instead of widening the change.
5. Finish with a full check run and a summary of tasks done, skipped and surprising.

What you get

A running log with one line per task showing the check output summary, then a final summary listing completed tasks, skipped tasks and surprises.

What it watches out for

• Marking a task done because the edit was made, not because the check output proved it.
• Weakening a failing test to get a green run, which hides the very defect the check found.
• Carrying on after a failure, so later tasks build on a broken base and the cause gets lost.

How to install

Claude.ai and the Claude desktop app

1. Download the skill .zip.
2. Open Settings, then Capabilities, and find Skills.
3. Choose Upload skill and select the .zip.
4. Ask Claude for help with the task. It loads the skill when your request matches.

Claude Code

1. Download the skill .zip.
2. Unzip it into ~/.claude/skills/ (or .claude/skills/ inside a project).
3. Start a new session. Claude Code loads the skill when your request matches.

Codex

1. Download the skill .zip.
2. Unzip it into ~/.agents/skills/ (or .agents/skills/ inside a project).
3. Codex picks it up on its own. Type $ and the skill name to use it, or just ask for the task.

Cursor

1. Download the Cursor rule (.mdc).
2. Save it in .cursor/rules/ inside your project.
3. Cursor's agent applies the rule when your request matches its description.

AGENTS.md (Codex, Cursor, and other coding agents)

1. Copy the AGENTS.md section.
2. Paste it into AGENTS.md at the root of your repository, creating the file if needed.
3. Coding agents that read AGENTS.md follow it when your request fits.