tctinh/executing-plans

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. If concerns: Raise them with your human partner before starting
4. If no concerns: Create a short checklist in todo or your working notes only when the batch has enough moving parts to justify active tracking, then proceed

Step 2: Identify Runnable Tasks

Use hive_status() to get the runnable list — tasks with all dependencies satisfied.

Only done satisfies dependencies (not blocked, failed, partial, cancelled).

When 2+ tasks are runnable:

• Prefer vscode/askQuestions for a structured choice: "Multiple tasks are runnable: [list]. Run in parallel, sequential, or a specific subset?"
• Fall back to asking directly in chat only when vscode/askQuestions is unavailable or a lightweight follow-up is enough
• Record the decision in Copilot memory or current working notes only when future turns need it

When 1 task is runnable: Proceed directly.

Use vscode/memory only for durable execution decisions or blocker history that future turns need.

Step 3: Execute Batch

For each task in the batch:

1. Delegate implementation directly to @forager
2. Make sure the worker reads the approved plan and records progress with hive_task_update
3. Follow each step exactly (plan has bite-sized steps)
4. Run verifications as specified and confirm the task state is updated accurately

Step 4: Report

When batch complete:

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

Step 4.5: Post-Batch Hygienic Review

After the batch report, prefer vscode/askQuestions to ask whether the user wants a Hygienic code review for the batch. Fall back to asking directly in chat only when vscode/askQuestions is unavailable or a lightweight follow-up is enough. If yes, invoke the @hygienic agent via the agent tool to review implementation changes from the latest batch, then apply feedback before starting the next batch.

Step 5: Continue

Based on feedback:

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

Step 6: Complete Development

After all tasks complete and verified:

• Announce: "I'm using the verification-before-completion skill to complete this work."
• REQUIRED SUB-SKILL: Refer to the skill at ../verification-before-completion/SKILL.md
• 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

• 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