Standing Instructions¶
The Problem You're About to Feel¶
Remember that AI is stateless — every conversation starts from a blank slate. In practice, this means every time you open your AI coding assistant, you're working with a delegate who:
- Doesn't know what your project does
- Doesn't know your conventions or patterns
- Doesn't know what you've already built
You could re-explain all of this at the start of every conversation. But you're going to have a lot of conversations today. There's a better way.
Project Context Files¶
A project context file is a file in your project that your AI coding assistant reads automatically at the start of every conversation. Think of it as an onboarding document for a new team member — except this team member shows up fresh every single time.
The file is called CLAUDE.md. Claude Code reads it automatically when it starts a conversation. Place it in your project's root directory.
The file is called AGENTS.md. Codex reads it automatically when it starts. Place it in your project's root directory.
The file is called AGENTS.md. pi.dev reads it automatically when it starts. Place it in your project's root directory.
Whatever tool you're using, the purpose is the same: persistent instructions that survive across conversations, solving the statelessness problem at the project level.
The Bootstrap Pattern¶
Your project context file should be an index, not an encyclopedia. Point AI to where the information lives rather than copying it all in.
What goes in: - What the project does and what its main parts are (one paragraph) - Key technology choices and conventions - What data sources the project uses and where the data comes from - Domain rules that should always be followed (e.g., "always use the official North American Avalanche Danger Scale colors — green, yellow, orange, red, and black — for danger levels 1 through 5") - Rules for how the AI assistant should behave (e.g., "push back when I don't provide clear acceptance criteria") - Where to find important documentation
What doesn't go in: - Entire codebases or documentation dumps - Information that changes frequently (point to the source instead) - Step-by-step procedures — keep it at the "need to know" level
Remember the oxygen tank: everything in your context file uses up space in every conversation. Keep it focused. A concise file that points to detailed docs beats a bloated file that crowds out the actual work.
Team Activity: Bootstrap Your Project¶
Format: Mob Session Time: ~4 minutes Setup: One person drives, everyone else navigates. Make sure your AI coding assistant is open and running.
Your team's about to build an Avalanche Observation Network. Before you write your first story, give your AI coding assistant its onboarding document.
Ask your AI coding assistant:
Read through this project and create a project context file for it. The file should describe what's already set up and include a section for our project: an Avalanche Observation Network for the Wasatch Range. The platform serves two user types — backcountry skiers who submit field observations (snowpack, avalanche sightings, weather, red flags) and avalanche forecasters who review those observations to produce daily danger ratings. Keep it short — point to documentation rather than duplicating it.
This creates a CLAUDE.md file in your project root. Every new Claude Code conversation will read it automatically.
This creates an AGENTS.md file in your project root. Every new Codex conversation will read it automatically.
This creates an AGENTS.md file in your project root. Every new pi.dev conversation will read it automatically.
After it's created, save your progress:
Save my progress and sync it.
Why this matters: When you "save and sync," your AI assistant uses Git — a version control tool that records every change (who changed what, when, and why) — and then pushes your work to GitLab, a safe location outside of Coder. Your Coder workspace is a cloud computer, and like any computer, things can occasionally go wrong. If they do and you haven't synced, your recent work could be lost. Once you've synced, your work is safely stored even if your workspace restarts. Build this habit: every time you finish something that works, tell your AI assistant to save and sync.
Discuss: How is this different from just telling AI about your project at the start of every conversation? What happens as your project evolves — does this file need to change too?
Key Insight¶
The best delegation starts before the conversation. A project context file means AI shows up already knowing your project, your conventions, and your constraints. Instead of re-explaining every session, you start with: "Here's what I need built next." That's the shift from using AI to delegating to it.