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

bloxkit-ai

CLAUDE.md0 starsChanged 6 months agoMITView on GitHub

Claude Code and Claude Desktop should use the same workflow registry as Codex. Run Bloxkit commands through: Do not recreate command logic in global Claude files. If a command needs to change, edit toolkit-v2/commands/*.yaml, then regenerate surfaces: Generated Claude Code commands live in .claude/commands/. Codex skills live in skills/. Claude Desktop prompt packaging lives in toolkit-v2/claude-desktop/. If tools or paths are broken, run: /fix-myself verifies Node, npm, Rokit, Rojo, StyLua, Wally, Selene, and Lune, then runs safe repairs for the…

  • Installs packages

The file

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

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run Bloxkit commands through:

    line 7
  2. Very specific:

    Do not recreate command logic in global Claude files.

    line 13
  3. Distinctive:

    If tools or paths are broken, run:

    line 30
  4. Distinctive:

    Do not document or recommend prompt-first UI generation for launch.

    line 53
  5. Very specific:

    Never write personal paths, local user names, private emails, tokens, or checked-in dependency folders into repo files.

    line 57

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.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
CLAUDE.md

Bloxkit AI Claude Guide

Claude Code and Claude Desktop should use the same workflow registry as Codex.

Use The Shared Runner

Run Bloxkit commands through:

node toolkit-v2/scripts/command-runner.mjs /command

Do not recreate command logic in global Claude files. If a command needs to change, edit toolkit-v2/commands/*.yaml, then regenerate surfaces:

npm run v2:generate-agent-surfaces

Generated Claude Code commands live in .claude/commands/. Codex skills live in skills/. Claude Desktop prompt packaging lives in toolkit-v2/claude-desktop/.

Setup And Repair

Start with:

npm install
npm run tools:verify

If tools or paths are broken, run:

node toolkit-v2/scripts/command-runner.mjs /fix-myself --dry-run
node toolkit-v2/scripts/command-runner.mjs /fix-myself

/fix-myself verifies Node, npm, Rokit, Rojo, StyLua, Wally, Selene, and Lune, then runs safe repairs for the repo or current generated project.

Public UI Surface

Launch UI support is prefab-first:

  • /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
  • /ui-preview

Do not document or recommend prompt-first UI generation for launch.

Privacy Rule

Never write personal paths, local user names, private emails, tokens, or checked-in dependency folders into repo files. Run npm run security:scan before publishing.

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