Project Tracking
Project Tracking
A system for organizing work, maintaining continuity across AI sessions, and capturing knowledge.
Core Concepts
Initiatives
Multi-session efforts with a clear goal. Can be small (1-2 sessions) or large (weeks of work). Tracked through active → completed lifecycle.
Sessions
One focused work period within an initiative. Captures what happened, decisions made, and what's next.
Ideas
Quick capture for things that could be explored later. Not committed to.
Todos
Concrete tasks that should happen but don't warrant a full initiative.
Workspace Structure
All tracking lives in docs/workspace/:
docs/workspace/
├── initiatives/
│ ├── active/ # Currently being worked on
│ ├── completed/ # Done, archived for reference
│ └── backlog/ # Planned but not started
├── ideas/ # Quick captures, exploratory
└── todos/ # Tasks, not big enough for initiative
Quick Reference
| I want to... | Do this |
|---|---|
| Start working | Check workspace/initiatives/active/ for context |
| End a session | Create session summary, update initiative status |
| Track new effort | Create initiative in active/ or backlog/ |
| Capture quick idea | Add to workspace/ideas/ |
| Note a task | Add to workspace/todos/ |
| Find prior context | Read recent sessions in relevant initiative |
When to Use Each Reference
| Reference | When to Read |
|---|---|
| structure.md | Understanding folder layout, document types, what goes where |
| workflows.md | Starting/ending sessions, managing initiative lifecycle |
| templates/ | Creating new documents |
AI Navigation
Finding Context for Current Work
- List
docs/workspace/initiatives/active/ - Read
INITIATIVE.mdfor relevant initiative - Read recent sessions in
sessions/folder - Check for blockers or open questions
Updating After Work
- Create session summary in initiative's
sessions/folder - Update
INITIATIVE.mdstatus section - Update completion criteria checkboxes
- Note any blockers or next steps
Quick Captures
- Ideas: Create
docs/workspace/ideas/[name].md - Todos: Create
docs/workspace/todos/[name].md
Keep these lightweight - a few sentences is fine.
More from hhopkins95/ai-systems
opencode sdk development
This skill should be used when the user asks to "create an OpenCode tool", "build an OpenCode plugin", "write a custom tool for OpenCode", "use @opencode-ai/sdk", "use @opencode-ai/plugin", "integrate with OpenCode", "create OpenCode hooks", "define tool schema", "use tool.schema", "work with OpenCode sessions", or needs guidance on OpenCode SDK patterns, plugin development, or custom tool creation.
30backend setup
This skill should be used when the user asks to "create an agent runtime server", "set up agent runtime backend", "configure Modal sandbox", "implement PersistenceAdapter", "start WebSocket server", "create REST API for agents", or needs to build a Node.js backend using @hhopkins/agent-runtime.
1agent design
This skill should be used when the user asks to "configure agent profile", "add skills to agent", "set up MCP servers", "configure agent tools", "write system prompt", "create agent workflow", "define agent commands", "add subagents", or needs to define what capabilities an agent has and how to orchestrate complex workflows in the runtime.
1agent design 2
This skill should be used when the user asks to "configure agent profile", "add skills to agent", "set up MCP servers", "configure agent tools", "write system prompt", "create agent workflow", "define agent commands", "add subagents", or needs to define what capabilities an agent has and how to orchestrate complex workflows in the runtime.
1documentation system
Standards for documenting codebases. Use when writing documentation, deciding where docs should go, reviewing doc quality, or updating docs after code changes. Covers folder structure, content guidelines, and maintenance workflows.
1agent runtime overview
This skill should be used when the user asks "what is agent-runtime", "why use agent-runtime", "what does this repo do", "agent runtime architecture", "how does agent-runtime work", or needs to understand the purpose, value proposition, and high-level architecture of the @hhopkins/agent-runtime monorepo.
1