skills.rest
Brite-Nites
Brite-NitesOFFICIAL
Explore all skills by this author →
WebsiteGitHub

executing-plans

Execute structured plans by delegating each task to a fresh subagent.

Updated Jan 14, 2026
Search Tags:#checkpointing#subagent#workflow-automation#plan-execution#two-stage-review#parallel-tasks#tdd-enforcement
One-click install
npx skills add https://github.com/Brite-Nites/brite-claude-plugins --skill executing-plans-brite-nites
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: executing-plans
Source: https://github.com/Brite-Nites/brite-claude-plugins/tree/main/plugins/workflows/skills/executing-plans
Command: npx skills add https://github.com/Brite-Nites/brite-claude-plugins --skill executing-plans-brite-nites

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill orchestrates the execution of an approved plan by delegating each task to a fresh subagent, ensuring isolated context per task and preventing cross-task information leakage.

Core Features & Use Cases

  • Subagent-per-task execution: Launch a dedicated agent for each task in the plan, with task-only context.
  • Enforced TDD: Red-green-refactor cycle for per-task work, including two-stage reviews.
  • Checkpointing and drift control: Verify task outputs and progress between tasks with automatic validation.
  • Parallel task support: Run independent tasks concurrently while avoiding conflicts.

Quick Start

Start an approved plan from docs/plans and let the system spawn per-task subagents.

Frequently Asked Questions about executing-plans

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

FAQPage Schema
How do I execute a structured plan with isolated context per task?▼

Plan execution delegates each approved task to a fresh subagent, ensuring isolated context per task and preventing cross-task information leakage. Each subagent receives task-only context to run independently.

Can I run independent tasks concurrently during plan execution?▼

Yes, plan execution supports running independent tasks concurrently while avoiding conflicts. The system manages parallel task support alongside enforced TDD cycles and staged reviews.

How does TDD enforcement work within a multi-task workflow?▼

TDD enforcement applies a strict red-green-refactor cycle to per-task work executed by subagents. Each task undergoes two-stage reviews to validate outputs before checkpointing progress.

What is the best way to prevent context drift when running multi-task workflows?▼

Preventing context drift requires checkpointing and drift control between tasks. The system verifies task outputs and progress with automatic validation, ensuring each subagent operates with reduced, task-specific context.

When do I need two-stage reviews and checkpointing in plan execution?▼

Two-stage reviews and checkpointing are needed for multi-task workflows requiring strict context isolation and TDD enforcement. They validate task outputs automatically between tasks to control drift and verify progress.

Does plan execution work with tasks that require strict context isolation?▼

Yes, plan execution is designed for workflows where plan scope includes independent tasks requiring strict context isolation. It implements per-task context reduction and subagent-per-task prompts to maintain boundaries.

Related Skills

Explore More Software Engineering Skills→
zzafergokzzafergok
1

writing-plans

Draft executable implementation plans enumerating files, code changes, tests, docs, and verification steps.

Community
Intermediate
lagz0nelagz0ne
2

subagent-driven-development

Dispatch fresh subagents per task with two-stage spec and code reviews.

Community
Advanced
obraobra
269.6k

writing-skills

Apply RED-GREEN-REFACTOR cycles to create and test AI skills.

Community
Advanced
BryceRoberts13BryceRoberts13

subagent-driven-development

Dispatch subagents for isolated tasks with two-stage spec and code reviews.

Community
Advanced