Agent use case feed
Specific jobs people hand to AI agents, newest first. Each entry links to the pack that walks through it, so this page only lists them and the full pack stays in the marketplace.
Newest first
Build your own render tool for a brand look with Claude Code
A designer used Claude Code to build a browser tool for liquid 3D shapes, with a WebGL2 path tracer and denoising, that exports 4K loops. The point: designers can now make the tool, not only the image.
Give agents reverse engineering output they can check, not guess
borer is an early open-source reverse engineering engine built for agents. It is one Rust binary that runs as an MCP server, keeps lists paged and capped, and checks decompiled C against the machine code in an emulator so the agent knows what is proven.
Have the agent build a tool that runs without it
After 30 days with an always-on agent, one user's main lesson was that repeated agent steps are fragile and costly, and the better result is a script or small app the agent writes once that then runs on its own.
Judge agent-written libraries with test suites your side did not write
A team built open-source C# libraries with a factory of agents (planner, project manager, orchestrator, engineers, reviewers) and scored each one against public conformance suites such as test262 and html5lib, publishing the failures too.
Keep an app's rules in one data file so the agent can change behavior without touching code
A builder made a 90s-style scrolling cable TV guide for Plex, Jellyfin and Emby with Claude. A written spec came first, all channel and schedule rules live in one JSON file, and later ports used the first app as the reference.
Put Grok Bot in front of a Hermes agent so unattended jobs keep running
A builder wired Grok Bot to a local Hermes Agent API: Grok Bot starts runs, streams events, polls for results and relays approvals, while Hermes handles scheduled jobs that run without a person clicking approve.
Reverse engineer a console kernel with Claude Code so new controllers work on old hardware
Claude Code read the Xbox 360 kernel's USB stack through a Ghidra MCP server, ported an open Linux driver to C and built a boot plugin, so up to four Xbox Series controllers pair wirelessly with a modded 360.
Share one small kanban board with your coding agents through MCP
Kanzo is a tiny self-hosted kanban board with a built-in MCP server. Claude Code or Codex can take the next task, comment on it and move it, and its tool list costs roughly 800 tokens of context.
Tag every decision in your game's log with who made it
Thirteen weeks into a fishing and exploration game, a solo developer keeps a Decisions.md with more than 350 entries, each tagged [USER] or [PROPOSED], so the agent knows which choices are settled and which it may revisit.
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.
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.
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.
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.
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.
Make a 3D product ad with Claude Code and headless Blender on an old GPU
A 15-second, four-shot product spot rendered on a 2016 graphics card. Claude Code wrote the whole Blender scene in Python, Blender rendered it with no window open, and ffmpeg put the shots, music and overlay together. The builder posted the render times and what broke.
Never let a booking agent type the service name itself
A team building booking agents found the model sometimes booked services that did not exist. Their fix: the model never names the service. Code maps the request to a real catalogue id, and free text reaching the booking API is blocked.
Point an agent at the order exceptions, not the routine work
Instead of automating the 90% of orders that already run fine, one operator aimed an agent at the messy exceptions. The agent drafts a fix for each one and a person approves it with one click, which cut the daily exception queue from most of a day to about an hour.
Port a Three.js game to Unity and keep the hand-tuned physics
Moving a browser racing game to Unity for phones, the developer asked Claude Code which Asset Store engine to use. It read the code and advised using neither, then ported the 170 lines of drift physics line by line so the feel stayed the same. The port and a new UI took about two hours.
Render repeatable videos from HTML instead of a video model
A hands-on test of HyperFrames, an open-source tool that turns timed HTML pages into MP4 with headless Chrome and ffmpeg. Same input gives the same video, so changes are code edits instead of another roll of the dice. The tester also wrote down the gotchas.
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.
Turn a folder of raw footage into a finished edit with an agent skill
video-use is an open-source skill from the Browser Use team. You drop raw takes in a folder and ask Claude Code or Codex for an edit. It cuts filler words, grades color, adds subtitles and animated overlays, then checks its own render before showing you.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.