πŸ—ΊοΈ The Journey

Your Learning Path

Eleven lessons, three parts, one repeatable system. Follow it top to bottom, or jump to what you need.

🧠
Lesson 100:05:44 β†’ 00:30:30

Escape the Token Ceiling

Offload heavy thinking to a browser so you never burn your Codex quota again.

  • Route huge, read-heavy codebase questions to a browser ChatGPT session instead of burning Codex quota
  • Bundle dense repo context with PackX and hand it off via Oracle + an MCP/browser automation bridge
  • Drive a plan β†’ implement β†’ verify loop with Oracle on a separate high-context session
πŸŽ›οΈ
Lesson 200:30:26 β†’ 00:53:29

Command Your Terminal Like an Orchestra

Run a manager agent that spins up worker panes from plain English.

  • Adopt an agent-first mindset and the manager-worker topology
  • Drive CMUX terminal layouts with natural language
  • Set up AFK automation loops that keep working while you don't
πŸ—‚οΈ
Lesson 300:53:29 β†’ 01:10:09

Give Your Agents a Memory

Agent-managed folders, gitignore partitioning, and living check-back files.

  • Create agent-managed notes/goals folders the harness can read and write
  • Partition context by globally gitignoring those agent-managed folders
  • Track progress with a live, auto-refreshing Markdown side pane as a visual checklist
πŸ“
Lesson 401:20:25 β†’ 01:38:20

Source of Truth Over Stale Memory

Trust the code, snapshot a million tokens, and capture design in design.md.

  • Tell the difference between basic memory and dangerous stale memory
  • Treat code as the source of truth with million-token snapshot contexts
  • Capture a design.md standard and generate multi-route structural variants
πŸ’
Lesson 501:38:20 β†’ 02:00:36

The 100 Monkeys & Perspective Prompting

Throw many cheap attempts at a problem and inspect them like a pro.

  • Use perspective-based prompting and discardable QA files for non-obvious user paths
  • Apply the 100 Monkeys technique and use CMUX state for context-aware shortcuts
  • Extract implementation intent from narrated screen recordings into Gemini
🎨
Lesson 602:00:36 β†’ 02:27:33

Design With Images & Video

Generate a look, hand it to an agent, and let video carry your intent.

  • Run CMUX as a primary orchestrator with token-efficient flash models
  • Use image generation as a design reference and hand off image-to-design
  • Prompt with video and navigate the MCP-vs-CLI boundary
πŸͺ
Lesson 703:10:22 β†’ 03:33:48

Hooks, Skills & the Ralph Loop

Intercept the agent's lifecycle and encode reusable expertise.

  • Manage context with compaction and conversation forking
  • Wire user-prompt, tool-use, and stop hooks into your workflow
  • Choose between skills and plugins and run a Ralph loop
♻️
Lesson 803:33:48 β†’ 03:57:36

Self-Improving Loops & Deterministic Gates

Let agents read their own logs, fix themselves, and pass hard gates.

  • Extract terminal pane text in CMUX as machine-readable context
  • Build self-improvement error loops behind log-based deterministic gates
  • Define natural-language contract boundaries and prune context
πŸ€–
Lesson 903:57:36 β†’ 04:22:29

Background Daemons & Agent Swarms

Spin up self-aware scripts and swarms that run while you sleep.

  • Run focused background daemons that update a human-readable HTML dashboard
  • Use low-reasoning iteration with a deliberately small-context strategy
  • Coordinate SDK multi-agent graphs with a multimodal verification loop
πŸŒ™
Lesson 1004:22:29 β†’ 04:50:54

Codex Daemons & Overnight Crons

The context triad, agent archetypes, and work that happens overnight.

  • Bundle the context triad β€” intent, implementation, and live output β€” for diagnosis
  • Run specialized Codex daemons as overnight emulated crons
  • Coordinate agents through natural-language loose coupling
πŸ“œ
Lesson 1104:50:54 β†’ 05:18:21

Code as a Throwaway Artifact

Natural-language contracts, video-as-requirements, and living guardrails.

  • Write natural-language contracts and use video as requirements
  • Treat code as a throwaway artifact behind a state machine + modules
  • Maintain living guardrails while treating generated code as disposable and ideas as durable