# PLANS For Fable 5: Rebuilding My /Plan Skill for Mythos Class Models

## Executive summary

This deep-dive devlog details the rebuilding of a comprehensive `/plan` meta skill (`PlanF3`) designed for next-generation Large Language Models (LLMs) like Fable 5 and Mythos class models. The core thesis is that superior engineering results depend on rigorous, upfront planning—a concept termed 'great planning is great engineering.' By investing heavily in structured templates, the speaker creates a meta skill that forces agents to output highly detailed, standardized plans in HTML format, thereby improving performance over speed or cost (the 'trade-off trifecta'). The resulting plan acts as a living artifact for the entire codebase, integrating complex workflows like image generation and agent-to-agent communication.

## Key takeaways

- The Importance of Planning in Agentic Engineering: Planning is identified as the single most critical tool an engineer has. The speaker warns against outsourcing thinking or planning to models, arguing that detailed, structured plans are necessary for end-to-end control and reliable results at scale.
- The PlanF3 Meta Skill Architecture: The new skill is designed to be a 'meta skill'—a prompt that creates other prompts or skills. It mandates structured output in HTML format, which is preferred for its ability to convey rich information and utilize tokens efficiently across the 'trifecta' of users: human engineers, engineering teams, and AI agents.
- Structured Planning as an Artifact: The plan is treated as a living artifact containing mandatory sections like Purpose, Problem, Solution (P/S/R), Relevant Files (existing and new), Implementation Phases (with embedded checklists), Testing Strategy, and detailed Metadata Headers (tracking agent name, session ID, back/forward references).
- Advanced Workflow Integration: The skill is modularized into dedicated workflows: `create plan`, `update plan`, `update references`, `build plan`, and `image generation`. This structure allows for complex, multi-step processes (e.g., running a build cycle that updates status markers in the plan).

## Technical details

- Model and Skill Identifiers: The primary skill developed is `PlanF3` (Plans for Fable 5). The target models are the Mythos class models, with Opus 4.8 used during development.
- Plan Structure and Format: The plan template is structured to include: Purpose, Problem/Solution (P/S/R), Relevant Files (existing/new), Implementation Phases (with embedded checklists), Testing Strategy, and Metadata Header. The use of HTML is emphasized for superior token usage.
- Workflow Management: The skill utilizes a workflow table to manage five core workflows: `create plan`, `update plan`, `update references`, `build plan`, and `image generation`. This allows the agent to execute complex, multi-stage processes.
- Agentic Capabilities: The system integrates advanced features such as GPT Image 2 for image generation and the Iron network protocol for secure agent-to-agent communication, demonstrating a focus on modularity and scalability.

## Practical implications

- Implement a structured, multi-stage planning meta skill to enforce consistency and quality in agentic development cycles.
- Treat your system plans as living artifacts that must track metadata (e.g., commit history, agent name) for full traceability.
- Design workflows with explicit steps (e.g., `build plan`, `update references`) rather than relying on single-shot prompts to manage complex state changes.
- Prioritize structured output formats like HTML over plain text or Markdown when the plan must be consumed by multiple systems (human, CI/CD, other agents).

## Topics

Agentic Engineering, Meta Skills, LLM Prompt Engineering, Build Systems, Workflow Automation, PlanF3 Skill, Anthropic Fable 5 / Mythos Class Models, GPT Image 2

Source: https://www.youtube.com/watch?v=DzbqeO_diOQ