Executing Plans

Executing Plans

Overview

Load plan, review critically, execute all tasks, report when complete.

Announce at start: "I'm using the executing-plans skill to implement this plan."

Note: If the harness has subagents, running one task per subagent keeps each context clean and is usually the better way to execute a long plan. When that applies is project doctrine, not this skill's call — see "When to launch a subagent" in the project's AGENTS.md.

The Process

Step 1: Load and Review Plan

1. Ensure you are on a feature branch, never straight on main/master
2. Read plan file
3. Review critically - identify any questions or concerns about the plan
4. If concerns: Raise them with your human partner before starting
5. If no concerns: Create todos for the plan items and proceed

Step 2: Execute Tasks

For each task:

1. Mark as in_progress
2. Follow each step exactly (plan has bite-sized steps)
3. Run verifications as specified
4. Mark as completed

Step 3: Complete Development

After all tasks complete and verified:

• REQUIRED SUB-SKILL: call the Skill tool with "verification-before-completion" — run the suite now and read the output; do not report the plan done from memory
• Then call the Skill tool with "code-review", plus "security-review" if the change touched the sensitive surface listed in the project's SECURITY.md

When to Stop and Ask for Help

STOP executing immediately when:

• Hit a blocker (missing dependency, test fails, instruction unclear)
• Plan has critical gaps preventing starting
• You don't understand an instruction
• Verification fails repeatedly

Ask for clarification rather than guessing.

When to Revisit Earlier Steps

Return to Review (Step 1) when:

• Partner updates the plan based on your feedback
• Fundamental approach needs rethinking

Don't force through blockers - stop and ask.

Remember

• Review plan critically first
• Follow plan steps exactly
• Don't skip verifications
• Reference skills when plan says to
• Stop when blocked, don't guess
• Never start implementation on main/master branch without explicit user consent