# Start safely Prompt Pack

Prompts for scoping work, protecting secrets, and making the agent stop after one reviewable step.

Pack URL: https://aicodingguild.com/prompts/packs/start-safely
Filtered library URL: https://aicodingguild.com/prompts?path=start-here
Plain-text export: https://aicodingguild.com/prompts/packs/start-safely/txt
Featured prompt: Pre-Flight Secrets Check
Prompt count: 7

## 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. Choose a Tiny First Win
Category: Start Here — Build Safely With AI
Path: Start Here — Build Safely With AI
Lesson: https://aicodingguild.com/learn/start-here/choose-a-tiny-first-win
Prompt page: https://aicodingguild.com/prompts/choose-a-tiny-first-win
Tags: beginners, scope, mvp, first-project
Summary: How to pick a first project that teaches the workflow without dragging you into complex product and engineering problems.

Prompt:
"I need help shrinking this idea into a safe first AI-assisted project.
The big idea is: [describe idea]

Reduce it to the smallest useful version by:
1. removing anything that requires auth, billing, production data, or complicated integrations
2. keeping only one user and one core job to be done
3. telling me what the first screen or flow should be
4. telling me what to deliberately postpone until later

I want a first win, not a platform."

## 4. Don't Lose Your Work — Folders, Git, and Checkpoints
Category: Start Here — Build Safely With AI
Path: Start Here — Build Safely With AI
Lesson: https://aicodingguild.com/learn/start-here/dont-lose-your-work
Prompt page: https://aicodingguild.com/prompts/dont-lose-your-work
Tags: git, beginners, safety, workflow
Summary: The minimum safe setup for total beginners: a real project folder, a Git repo, a remote backup, and repeatable checkpoints.

Prompt:
"I am a beginner and I want the safest possible project setup before I keep building.
Help me:
1. confirm this project has the minimum Git safety setup
2. check that `.env`-style secret files are ignored
3. tell me what files should and should not be committed right now
4. suggest the next safe checkpoint

Do not rewrite history, force push, or delete files unless I explicitly approve it."

## 5. 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."

## 6. Pre-Flight Secrets Check
Category: Secrets Hygiene
Path: Start Here — Build Safely With AI
Lesson: https://aicodingguild.com/learn/start-here/before-you-share-anything
Prompt page: https://aicodingguild.com/prompts/before-you-share-anything
Tags: beginners, safety, sharing, shipping
Summary: Run this before you paste configs, screenshots, or terminal output into an AI tool so you do not leak API keys, connection strings, or internal URLs.

Prompt:
"I am about to share this small app with another person for the first time.
Please give me a beginner-safe pre-share review.

Context:
- project: [describe project]
- who will see it: [friend/coworker/client/internal team]
- main flow: [describe flow]

Review it for:
1. obvious safety problems
2. anything sensitive I should not expose yet
3. the most likely embarrassing failure points
4. the smallest fixes that would make it safer to share
5. the minimum production-readiness checklist before this becomes more than a demo
6. the next milestone I should pursue before adding auth, payments, or more users

Do not suggest major rewrites. I want a practical pre-share checklist."

## 7. 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."