# Run your first Claude or agent session Prompt Pack

Prompts for a first Claude Code, Codex, or Cursor session so the agent sets a goal, explains scope, justifies tools or loops, verifies the result, and stops after one safe first move.

Pack URL: https://aicodingguild.com/prompts/packs/first-agent-session
Filtered library URL: https://aicodingguild.com/prompts?q=agent&path=start-here
Plain-text export: https://aicodingguild.com/prompts/packs/first-agent-session/txt
Featured prompt: Safe Agent Loop
Prompt count: 4

## 1. What You're Actually Doing When You Build With AI Agents
Category: Start Here — Build Safely With AI
Path: Start Here — Build Safely With AI
Lesson: https://aicodingguild.com/learn/start-here/what-you-are-actually-doing
Prompt page: https://aicodingguild.com/prompts/what-you-are-actually-doing
Tags: vibe-coding, beginners, mindset, AI
Summary: A plain-English explanation of the job: modern AI agents can plan, edit, run tools, and loop, but you still choose scope, inspect output, and own the result.

Prompt:
"I am completely new to AI-assisted building and I want to build one very small thing safely.
The problem is: [describe the problem]
The user is: [describe the user]
The smallest useful version would do only: [describe the tiny outcome]

Before writing any code:
1. tell me if this is a realistic first project
2. reduce the scope if it is still too big
3. explain the main risks and assumptions
4. propose one measurable stop condition
5. tell me what I must review myself
6. stop before auth, payments, production data, deployment, or destructive changes unless I explicitly approve them"

## 2. Safe Agent Loop
Category: Safety
Path: Start Here — Build Safely With AI
Lesson: https://aicodingguild.com/learn/start-here/the-safe-vibe-coding-loop
Prompt page: https://aicodingguild.com/prompts/the-safe-vibe-coding-loop
Tags: vibe-coding, workflow, beginners, safety
Summary: Use this before implementation work when you want the agent to set one goal, explain the plan, verify the result, and stop after one reviewable change.

Prompt:
"I want to work in a safe beginner loop.
Please do only this one task: [describe one tiny change].

Goal:
- outcome: [what should be true]
- scope: [files, pages, or systems in scope]
- proof: [test command, browser check, or manual check]
- stop condition: [when to stop]
- do not touch: [auth, payments, database, deployment, packages, secrets, etc.]

Before making changes:
1. explain your plan in plain English
2. list the files, commands, and tools you expect to use
3. tell me if this needs a stronger model, deeper planning, a subagent, MCP, or a loop -- and why
4. do not add packages or change config unless absolutely necessary

After making changes:
5. tell me exactly what changed
6. tell me how to test it in one minute
7. run only the verification command or browser check we agreed on
8. stop so I can review before the next step"

## 3. Your First Agent Session
Category: Start Here — Build Safely With AI
Path: Start Here — Build Safely With AI
Lesson: https://aicodingguild.com/learn/start-here/your-first-agent-session
Prompt page: https://aicodingguild.com/prompts/your-first-agent-session
Tags: AI-tools, beginners, agent-workflow, hands-on
Summary: How to run your first Claude Code or AI-agent build session without letting it spiral into a mystery code dump.

Prompt:
"I am on my first real AI-agent coding session.
Project: [describe project]
Current goal: [describe one small feature]
Tooling available: [Claude Code / Cursor / Codex / editor agent / terminal agent / browser preview / database / deployment]
Model available: [current model if known]

Before changing code:
1. explain the safest approach in plain English
2. list the files you expect to change
3. tell me if this request is still too big
4. define the exact stopping point for this session
5. tell me whether this needs a goal, deeper planning, a stronger model, a loop, MCP, a subagent, or browser control -- and justify any yes

Then implement only that one small feature.

Afterward:
6. tell me exactly what changed
7. tell me how to test it in under two minutes
8. run only the agreed verification
9. tell me what you deliberately did not touch
10. stop so I can review before the next step

Do not add auth, deployment, payments, or unrelated cleanup."

## 4. The First Production Stack — Domains, Auth, Data, Logs, and Payments
Category: Start Here — Build Safely With AI
Path: Start Here — Build Safely With AI
Lesson: https://aicodingguild.com/learn/start-here/first-production-stack
Prompt page: https://aicodingguild.com/prompts/first-production-stack
Tags: production, dns, vercel, supabase, clerk, stripe, sentry, github, security
Summary: The practical baseline for turning an AI-built demo into a real software product: DNS, hosting, database, auth, observability, GitHub, durable notes, subscriptions, and security sweeps.

Prompt:
"I have an AI-built demo and I want to understand the path to production.
Do not write code yet.

Product context:
- what the app does: [describe it]
- who will use it first: [describe first testers]
- current stack: [list tools if known]
- business model: [free, subscription, internal, commerce-backed, not sure]

Please produce:
1. the missing production stack checklist across domain, DNS, hosting, database, auth, payments, logs, GitHub, notes, and security
2. the safest recommended vendors for each missing layer, prioritizing strong APIs and clean handoffs to agents
3. the smallest production milestone I should target before inviting more than three testers
4. the subscription or entitlement model I should use if early testers are free but need full paid access
5. the business-value hypothesis: why this could become recurring software revenue, what would prove retention, and how any existing sales channel could help validate it

Be practical and skeptical. Separate table stakes from nice-to-have features."