One-click install
npx skills add https://github.com/swingerman/disciplined-agentic-engineering --skill plan-swingerman
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: plan
Source: https://github.com/swingerman/disciplined-agentic-engineering/tree/main/engineer/skills/plan
Command: npx skills add https://github.com/swingerman/disciplined-agentic-engineering --skill plan-swingerman

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

It prevents AI agents from rushing into implementation without a validated architecture plan, ensuring engineers remain in charge of design decisions and performance-sensitive tradeoffs.

Core Features & Use Cases

  • Architecture-first planning: Drafts the Architecture section first and iterates only until the human confirms it.
  • Checkpoint gating and pipeline breadcrumb: Runs deterministic handoff, branch hygiene checks, and displays where the plan sits in the DAE pipeline.
  • Charter compliance validation: Produces a structured Charter Check and enforces that any deviations have matching amendment evidence.
  • Spec-driven phasing and test strategy: Creates plan phasing (stages/slices) and a verification approach that incorporates the feature’s validation_method.

Quick Start

Use the engineer plan skill when you have acceptance criteria and specs and want an architecture plan drafted and validated before implementation.

Frequently Asked Questions about plan

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

FAQPage Schema
How do I create an architecture plan with deterministic guardrails before implementation?

To create an architecture plan with deterministic guardrails, draft the Architecture section first and iterate until human-confirmed. The process enforces spec-driven DAE checkpoints, runs handoff and branch hygiene gates, and validates Charter compliance with mandatory amendment ADRs for deviations.

What is spec-driven architecture planning and when do I need it?

Spec-driven architecture planning is the process of drafting a validated design from feature specs before any code is written. You need it when you want to prevent AI agents from rushing into implementation and ensure engineers remain in charge of performance-sensitive tradeoffs.

How do I enforce charter compliance during the architecture planning process?

You enforce charter compliance during architecture planning by running a structured Charter Check against CHARTER.md. This deterministic gate requires matching amendment evidence and ADRs for any deviations found during the checkpoint validation process.

Do I need acceptance criteria and specs before drafting an architecture plan?

Yes, you need acceptance criteria and specs before drafting an architecture plan. The planning process requires feature.md, acs.md, spec.md, and CHARTER.md as inputs to enforce prior checkpoint completeness and generate a validation-method-aware test strategy.

What's the best way to validate architecture checkpoints before handing off to implementation?

The best way to validate architecture checkpoints is by running deterministic dae_handoff.py and dae_branch.py gates. These scripts enforce pipeline breadcrumb completeness and resolve the methodology via dae_resolve.py before generating the final plan.md.

Why does architecture planning require resolving methodology via dae_resolve.py?

Architecture planning requires resolving methodology via dae_resolve.py to ensure deterministic guardrails are properly applied. This gate enforces prior checkpoint completeness and guarantees the generated plan.md aligns with the spec-driven DAE pipeline before implementation begins.