Host Compatibility

If you are running this skill in Codex, read ../references/codex-compatibility.md before following host-specific tool instructions. Claude Code should continue to use the Claude-specific tools and command wrappers described here.

Model posture (Soloship)

See the auto-loaded model-mode rule. Standard posture (the default): execute this skill exactly as written. Fable posture (model id contains fable/mythos): every gate this skill names — evidence to produce, verifications to run, dispatches it mandates, user checkpoints — remains binding; its step ordering and procedural scaffolding are method guidance you may adapt when the work is better served. Never skip a step that produces evidence; when ambiguous, treat it as a gate.

Executing Plans

Overview

Load plan, review critically, execute tasks in batches, report for review between batches.

Core principle: Batch execution with checkpoints for architect review.

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

The Process

Step 1: Load and Review Plan

1. Read plan file
2. Review critically - identify any questions or concerns about the plan
3. <!-- concern:component-reuse -->If docs/architecture/COMPONENTS.md exists, read it before creating or specifying UI components — reuse or extend an existing component on purpose match, cite what you found, and apply the rule of three (see references/component-inventory.md). Flag any plan task that creates a component the inventory already covers.
4. If concerns: Raise them with your human partner before starting
5. If no concerns: Create TodoWrite and proceed

Step 2: Execute Batch

Default: First 3 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: Report

When batch complete:

• Show what was implemented
• Show verification output
• Say: "Ready for feedback."

The checkpoint is the product of this skill: a human architect reviews between batches. If no partner is present to respond (an unattended or scripted run), this skill is the wrong tool — use /soloship:subagent-driven-development, which executes continuously without per-batch check-ins. Do not simulate feedback or skip the checkpoint to keep going.

Step 4: Continue

Based on feedback:

• Apply changes if needed
• Execute next batch
• Repeat until complete

Step 5: Complete Development

After all tasks complete and verified:

• Announce: "I'm using the /soloship:finish skill to complete this work."
• REQUIRED SUB-SKILL: Use /soloship:finish (Soloship's rename of Superpowers' finishing-a-development-branch)
• Follow that skill to verify tests, present options, execute choice

When to Stop and Ask for Help

STOP executing immediately when:

• Hit a blocker mid-batch (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

• Never start implementation on main/master without explicit user consent — work in a worktree/branch first
• Review plan critically first
• Follow plan steps exactly
• Don't skip verifications
• Reference skills when plan says to
• Between batches: just report and wait
• Stop when blocked, don't guess