Agent use case packs: real jobs, step by step
A use case pack walks one specific job from blank page to result with an AI agent: the plan, the prompts for each stage, what usually goes wrong and how to check the output.
Build a playable browser game prototype in one evening with an AI agent
A step by step pack for going from a one-paragraph idea to a playable HTML5 game in a single file, then posting it on itch.io for friends to try.
Turn a spreadsheet you run by hand into a small web app
A staged plan and prompts for turning the spreadsheet your team edits by hand into a web app with logins, forms and an import of your existing rows.
Get a weekly metrics report written by an agent from Stripe, analytics and a sheet
Build a scheduled job that pulls revenue, traffic and your own sheet numbers, computes week over week changes in code and has an agent write a short report.
MCP server setup playbook: connect your agent to real tools without handing over the keys
Pick the fewest MCP servers for a job, check them before installing, scope the credentials, configure five clients, test with MCP Inspector and build a small read-only server of your own.
Launch an AI-built browser game: mobile, licensing, leaderboards and the itch.io page
A launch plan for a browser game built with an AI agent: performance budget, device tests, audio and touch fixes, an asset license ledger, leaderboard hardening and the itch.io page.
Move a Custom GPT to a skill before custom GPTs retire on Dec 11, 2026
Inventory your GPTs, export everything, migrate, rewrite the instructions as a SKILL.md that triggers at the right time, replace custom actions and test against the answers your GPT gives today.
Solo-founder agent ops playbook: run your business with agents without losing control
Decide which jobs go to agents, how much power each gets, one house rules file they all follow, a daily brief, a weekly review, cost caps and a runbook for when an agent gets it wrong.
Run a daily signal board for your niche on X with an agent
A read-only agent routine and a small script that rank the last 14 days of posts in your niche by bookmarks, quotes and likes, and show what moved since yesterday.
Have your coding agent run a release gate before App Store submission
An indie developer who builds everything with agents shares the pre-submit checks his agent runs, what they caught, and why Apple still rejected his Codex-built puzzle game.
Make your agent play the game before it says done
One prompt, two agents: Claude Code built a neon racing game far faster, while Grok Bot drove the race with real controls and caught reversed steering a script never touched.
Review agent-written code in layers the way the Claude Code team does
The Claude Code team described how they moved most code reading to automated reviewers, kept humans for risky and directional calls, and still cut the share of reverted pull requests by more than 40% while merges doubled.
Pass a quiz on agent-written code before you push it
Sphinx is a free Git hook that pauses pushes to protected branches and asks you a scenario question about the diff your agent wrote, so you only release code you actually understand.
Improve a generated 3D scene with a screenshot and critic agent loop
A creator built a rainy neon city as a single 52 KB HTML file on WebGPU in about 40 minutes, and credits the quality jump to a loop where Claude screenshots its own render and a fresh critic agent reviews it.
Run a pool of coding agents that only merge fixes proven red then green
A maintainer ran a small office of Claude Code workers against 13 Rust repos for five days and got about 170 pull requests merged, then open sourced the tool as ApolloOffice.
Let AI write the NPCs but keep the rules in code
A one-person studio is building Someone Else's War, a Steam RPG where an AI writes the world, characters and replies to whatever you type, while hand-written rules decide every fight and hold NPCs to the deals they make.
Turn production alerts into diagnosed fix PRs with a cloud agent
A small SaaS team wired its alerts to a Claude Code routine that finds the root cause, explains it in the Slack alert thread and opens a fix PR, and its first serious incident went from alert to merged fix in 13 minutes.
Run a local shop services business with an agent team and five approval gates
A gym teacher and former steamfitter runs BuiltForShops, which builds websites, answers calls and manages reviews for independent shops, on a team of named Grok Bot agents with a short list of things that never happen without his yes.
Audit where your agent team's tokens actually go
A user went through a day of Grok Bot usage step by step and found that bots handing work to each other, not his own chats, ate most of his tokens, with each handoff costing a median of about 977,000 tokens.
Give a coding agent eyes inside the game engine with your own MCP server
A streamer who saw models struggle at game dev on an earlier stream built his own MCP server that hooks Opus 5.5 into the s&box engine, so the agent works inside the editor instead of guessing, and used a swarm of agents to build a game about stopping an AI swarm.
Animate a full music video to the beat with an agent-written engine
A creator had Opus 5.5 write a 22,000-line Python engine that times every one of 4,320 frames to a song, getting exact beat sync for about $187 in total AI costs after a video model kept landing seconds late.
Debug a camera game through an MCP server inside the running app
A webcam watches your monitor while you practice with a laser training pistol, and the game scores each hit. Claude Code wrote all of it over about two weeks, and the trick that made it work was giving the agent live access to the running app.
App Store preview videos drawn frame by frame in code
Instead of recording the simulator, an iOS developer had Claude Code build a renderer that draws each frame of the App Store preview from the app's own screens, adds synthesized music and encodes it with ffmpeg.
Let Claude Code run a sky camera through an MCP server that carries its own rules
An open-source meteor camera that Claude Code operates through an MCP server. The server hands the agent its own how-to skills and enforces the safety rules itself, so the agent cannot talk its way past them.
Run agents as an engineering team where nobody approves their own work
A former head of a 150-person engineering org reports that agents opened 1,363 of 1,575 pull requests over ten weeks. The setup works because the ticket is the spec and the test, and a separate checker signs off every change.
Questions
How is a use case pack different from a prompt pack?
A prompt pack is a toolbox of prompts for many small tasks. A use case pack is one job done end to end, in order, with checkpoints and expected results at each step.
Which agents do the packs work with?
Each pack lists the tools it was written for, usually Claude Code, Cursor, Codex or a general chat model. The prompts avoid tool-specific tricks where possible.