Build and validate a bounded, evidence-linked implementation plan without editing source or executing commands. Use when the user explicitly invokes /aet-plan or asks AET for an evidence-guided code plan.
At a glance
This skill is for Coding and helps you build an implementation plan, validate a code plan, and create an evidence-linked implementation strategy.
git clone --depth 1 https://github.com/AdvancingTitans/agent-engineering-toolkit
cp -r agent-engineering-toolkit/skills/aet-plan ~/.claude/skills/aet-plan
Setup, runtime and requirements describe AdvancingTitans/agent-engineering-toolkit, the repo this skill ships in.
AetplanningCode StrategyValidationimplementationNo Execution
Also in AdvancingTitans/agent-engineering-toolkit
View the repoRun a bounded AET check of Agent instructions, Skills, verification contracts, and dangerous authority. Use only when the user explicitly in...
Deterministically check whether an AET proof still applies to the current workspace. Use only for an explicit /aet-fresh request.
Create a bounded, read-only investigation from normalized Codex or Claude Code Run Records, optionally inspect explicit AET Proof and Freshn...
Execute one explicit verification command and record a minimal hash-bound AET proof receipt. Use only when the user explicitly invokes /aet-...
Investigate whether an AI coding change matches the user's task and whether cross-module changes are necessary. Use only for an explicit /ae...
Compatibility entrypoint for AET Quick and advanced AET Lab workflows. Prefer the four dedicated Quick Skills for daily work; use this Skill...
Other Coding skills
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make...
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI be...
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-design...
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model...
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS,...
Create a detailed refactor plan with tiny commits via user interview, then file it as a GitHub issue. Use when user wants to plan a refactor...