agentleFS
Sign inStart free
PlayUGCAIPlayUGCAI/bloxkit-ai/AGENTS.md

bloxkit-ai

AGENTS.md0 starsChanged 6 months agoMITView on GitHub

These instructions apply to the bloxkit-ai template repo and to generated Bloxkit projects. Run these before normal development: If setup fails, run: /fix-myself checks Node, npm, Rokit, Rojo, StyLua, Wally, Selene, and Lune. It runs safe install and validation steps, then reports any manual Studio or Rojo work that remains. Before handing off template changes, run: For a generated project, run: Agents can prepare projects and build .rbxl files. A human still needs to open Roblox Studio, connect Rojo, press…

  • Installs packages

The file

We split this AGENTS.md into the rules it gives an agent

9 rules. About 1 is common, 4 are distinctive, and 4 are very specific to this project.

  • ≈1

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Very specific:

    Prefer the shared workflow runner: node toolkit-v2/scripts/command-runner.mjs /command.

    line 8
  2. Very specific:

    Keep Codex, Claude Code, and Claude Desktop behavior aligned by updating toolkit-v2/commands/ first, then running npm run …

    line 9
  3. Distinctive:

    Do not edit generated project output by hand unless you are debugging the generator.

    line 10
  4. Very specific:

    Treat generated-project/, reports/, builds/, node_modules/, .rokit/, and .bloxkit/cache/ as generated or local runtime output.

    line 11
  5. Common:

    Never commit personal paths, local machine names, private emails, API keys, tokens, or generated dependency folders.

    line 12
  6. Distinctive:

    Run these before normal development:

    line 16
  7. Distinctive:

    If setup fails, run:

    line 23
  8. Very specific:

    Add prefab UI: /ui-add-shop, /ui-add-inventory, /ui-add-upgrade-menu, /ui-add-settings, /ui-add-daily-rewards, /ui-add-quest-log, …

    line 40
  9. Distinctive:

    Before handing off template changes, run:

    line 45

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

Bloxkit AI Agent Guide

These instructions apply to the bloxkit-ai template repo and to generated Bloxkit projects.

Core Rules

  • Work from the current repo root. Do not use hard-coded absolute paths.
  • Prefer the shared workflow runner: node toolkit-v2/scripts/command-runner.mjs /command.
  • Keep Codex, Claude Code, and Claude Desktop behavior aligned by updating toolkit-v2/commands/ first, then running npm run v2:generate-agent-surfaces.
  • Do not edit generated project output by hand unless you are debugging the generator. Change specs, overrides, or toolkit scripts, then rebuild.
  • Treat generated-project/, reports/, builds/, node_modules/, .rokit/, and .bloxkit/cache/ as generated or local runtime output.
  • Never commit personal paths, local machine names, private emails, API keys, tokens, or generated dependency folders.

Standard Setup

Run these before normal development:

npm install
npm run tools:verify

If setup fails, run:

npm run fix-myself -- --dry-run
npm run fix-myself

/fix-myself checks Node, npm, Rokit, Rojo, StyLua, Wally, Selene, and Lune. It runs safe install and validation steps, then reports any manual Studio or Rojo work that remains.

Main Workflows

  • New standalone game: /new-game "Game Name"
  • Existing Rojo repo: /adopt-project --repo-root ../your-existing-game
  • Existing Bloxkit project setup: /setup
  • Validate a project: /doctor, /test, /runtime
  • Build a project: /build
  • Serve to Studio: /serve
  • Add prefab UI: /ui-add-shop, /ui-add-inventory, /ui-add-upgrade-menu, /ui-add-settings, /ui-add-daily-rewards, /ui-add-quest-log, /ui-add-hud, /ui-add-popup
  • Preview UI: /ui-preview [Screen.Shop]

Validation

Before handing off template changes, run:

npm run tools:verify
npm run v2:generate-agent-surfaces
npm run v2:test:workflow-surface
npm run v2:list-commands
npm run security:scan

For a generated project, run:

npm run setup
npm run build
npm run doctor

Studio Handoff

Agents can prepare projects and build .rbxl files. A human still needs to open Roblox Studio, connect Rojo, press Play, and verify visual or gameplay behavior unless a Studio MCP session is available.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free