Lecture III: First Steps with an Agent

AI-Assisted Programming for PhD Researchers

Dr. Tobias Vlćek

Helmut Schmidt University, August 2026

Meet Your Agent

What Is OpenCode?

  • An open-source coding agent that lives in your terminal
  • Works with any model provider, no lock-in
  • Switch models or editors later, keep the same workflow
  • Today it is your hands-on tool for the rest of the course

Install It (Together, Now)

Pick the line for your system:

# macOS / Linux
curl -fsSL https://opencode.ai/install | bash
# macOS via Homebrew (alternative)
brew install anomalyco/tap/opencode
# Windows: npm (Node.js required)
npm install -g opencode-ai
# Windows via Chocolatey or Scoop (alternatives)
choco install opencode
scoop install opencode

Then confirm it installed:

opencode --version            # any recent version is fine

Windows: once installed, run opencode itself in Zed’s integrated terminal (or Windows Terminal/PowerShell). Git Bash handles multiline paste poorly for TUI apps like OpenCode. git/uv commands are still fine in Git Bash.

Connect Your Model

opencode auth login
  • Choose Mistral, paste the API key from setup
  • Then select the model: Mistral Medium 3.5 (id mistral/mistral-medium-latest) for our labs

Key stored locally in OpenCode’s config, never committed to git.

Bring Your Own Model (Optional)

The Mistral free tier is the course default. Prefer an account you already pay for? All of these work in OpenCode:

  • A paid Mistral tier: same flow as above, higher rate limits
  • A ChatGPT subscription: opencode auth login → OpenAI (officially supported)
  • A Claude subscription: same flow, choose Anthropic and sign in
  • An Anthropic API key: pay-per-use

The Same Agent in Zed

  • Zed’s agent panel speaks the same protocol (ACP)
  • Open the panel, pick OpenCode (install it from the ACP registry), a separate session from the terminal, same agent
  • Bonus: review each edit as an inline diff in the editor
  • Use whichever surface you prefer today: terminal or Zed

Or: Zed’s Own Agent

  • Zed also ships its own agent in the same panel, and it is genuinely good
  • Runs on your Mistral key (same key, its own slot in Zed) or student-plan credits. Add it in Zed’s agent settings
  • Same core loop you learn today: plan, act, review the diff, undo
  • Everything in the labs works there too: the prompts don’t care which agent runs them
  • The cheatsheet and my demos are OpenCode-flavored; translate UI details yourself

Safety Rails

What May It Do?

  • OpenCode asks permission per action class: editing files, running commands
  • Start restrictive; loosen consciously as trust grows
  • Every permission is configurable in opencode.json
  • The default stance: it proposes, you approve

Your Undo Buttons

  • /undo reverts OpenCode’s last change; /redo puts it back
  • Beneath that: git diff to see it, git restore to revert it
  • Nothing is scary while your working tree is clean
  • Commit before you let an agent loose: a clean tree is your rescue point

Giving Context

The Agent Reads, It Does Not Know

  • Recall the context window: the agent only sees what is in it
  • It reads what you show it, or what it opens itself
  • It does not see your screen, your intent, or yesterday’s session
  • No memory between sessions unless you write it down

Pointing at Things

  • @path/to/file pulls a file into the conversation
  • Paste error messages verbatim: the full traceback
  • Name constraints explicitly: “Python 3.12, pandas only”
@legacy_analysis.py why does this crash on empty input?

AGENTS.md: Standing Instructions

  • A file the agent reads every session, automatically
  • Holds your project’s purpose, commands, and rules
  • Keep it short and current
  • A stale AGENTS.md misleads more than no file at all

What Belongs In It

Keep it to what the agent needs to act:

  • Yes: build/test commands, structure overview, hard constraints
  • Yes: style choices like “snake_case, type hints on public functions”
  • Constraint example: “data/raw is read-only”
  • No: essays, wish lists, secrets or API keys

/init Writes a Draft

  • /init scans your repo and generates a first AGENTS.md
  • Treat it as a draft: read it, cut it down, correct it
  • The agent’s guess about your project is a start, not truth
  • You will do exactly this in Lab 1

Tokens, Cost, and Models

Tokens Are the Meter

  • Everything in and out is counted in tokens (~4 characters each)
  • The whole conversation is resent to the model each turn
  • Long sessions cost more, and the agent degrades as they grow
  • Start a fresh session per task: cheaper and sharper

Context Windows

Each model has a hard limit on tokens it can hold at once:

Text Rough tokens
One page of prose ~500
A 500-line source file ~6,000
Our models’ full window 128k–262k

Plan what you load. Do not pour the whole project in at once.

Picking a Model

  • Mistral Small: fast and cheap, for routine edits and boilerplate
  • Mistral Medium 3.5 (our lab default): harder reasoning, for design and tricky bugs
  • Match the model to the task; skip reasoning you do not need
  • Switching is one command, no restart

When the Free Tier Throttles

  • Free tiers have rate limits: you will hit them eventually
  • Symptoms: 429 errors, stalled or truncated responses
  • Do: wait a moment, shrink your context, or drop to a smaller model
  • Still stuck? Raise your hand. I have backup keys

The Core Loop

Explore → Plan → Implement → Verify

THE workflow of this course, four phases, each with a job:

  • Explore: load the right context; understand before touching
  • Plan: agree on the approach before any edit
  • Implement: make the change, one step at a time
  • Verify: prove it works; skipping explore means the agent guesses

Plan Mode vs Build Mode

  • Tab toggles between the two modes
  • Plan mode reads and suggests but never edits. Use it to explore
  • Build mode acts: it edits files and runs commands
  • Stay in Plan until the plan is right, then switch to Build

Explore First

Good opening prompts cost little and load the right context:

Explain this repository: structure and entry points
How does the humidity parsing work?
What would break if I changed the date format?

Exploring is cheap and fast, and it sets up everything after.

Verify Last, Every Time

  • Run the code: does it actually execute?
  • Read the diff: is that really what changed?
  • Check the claim against the output, not the agent’s summary

Still the Scientist of Record

“The agent said so” is not verification. You are still the scientist of record.

Lab 1

Your Mission

In Lab 1 you meet the inherited script and put the loop to work:

  • Make the agent explain the repository you cloned
  • Write a short AGENTS.md with /init, then trim it
  • Fix the first obvious problem, and verify the fix
  • The Explain-it boxes in the lab are mandatory: answer them before moving on

Continue Your Journey

Next Up