agentleFS
Sign inStart free
F0rger123F0rger123/CLAUDE-DESIGN-GOD-MODE/AGENTS.md

CLAUDE-DESIGN-GOD-MODE

AGENTS.md1 starsChanged 19 days agoMITView on GitHub

Claude Design God Mode is a set of nine design skills for Claude Code and other coding agents. Once installed, the agent can look at any website, CRM, app, landing page or browser game, give the design a score out of 100, choose a look that fits the business, and upgrade the design in place without breaking how it works. It costs nothing and installs nothing except the skills. Ask only what you do not already know: In Claude Code,…

  • Reads credentials
  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,700 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository10 other files it gives its agents.

The file

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

8 rules. About 0 are common, 7 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    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. Distinctive:

    Ask only what you do not already know:

    line 9
  2. Distinctive:

    After a run, show the person the before and after score, the main changes in plain words, and the pages to look at.

    line 37
  3. Very specific:

    Never print, copy or commit secrets (API keys, .env values, tokens) found in the project.

    line 41
  4. Distinctive:

    Never spend money: no paid fonts, paid image services or paid UI kits without a clear yes.

    line 42
  5. Distinctive:

    Never deploy, push to production or change live settings without a clear yes from the person.

    line 43
  6. Distinctive:

    Never break behaviour: keep routes, forms, field names, tests, analytics and SEO tags working.

    line 44
  7. Distinctive:

    Never invent facts on a site: no fake reviews, customer logos, numbers or awards.

    line 45
  8. Distinctive:

    Never replace real photos of the person's work with stock images.

    line 46

≈ “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

AGENTS.md: Claude Design God Mode

1. What this is (say this to the person)

Claude Design God Mode is a set of nine design skills for Claude Code and other coding agents. Once installed, the agent can look at any website, CRM, app, landing page or browser game, give the design a score out of 100, choose a look that fits the business, and upgrade the design in place without breaking how it works. It costs nothing and installs nothing except the skills.

2. Questions to ask the person first

Ask only what you do not already know:

  1. Which project should look better? (a folder on their computer, or a GitHub repo)
  2. Which pages matter most? (for example the home page, the dashboard, the pricing page)
  3. Are there brand colours, fonts or a logo that must stay?
  4. Light refresh (keep the current look, make it sharper) or full redesign (new look, same content)?
  5. Can you run the site locally so you can look at it? (if not, you will work from the code and say so)

3. Set it up

In Claude Code, run:

/plugin marketplace add F0rger123/CLAUDE-DESIGN-GOD-MODE
/plugin install design-god-mode@design-god-mode

In another agent (Codex, Cursor, Gemini CLI, Windsurf, ChatGPT with a repo): copy the skills/ folder of this repo into the target project, for example at .claude/skills/ or .agents/skills/, then read skills/god-mode/SKILL.md and follow it.

Check it worked:

  • Claude Code: /design-god-mode:audit appears when typing /design. Running it on the project returns a score out of 100.
  • Any agent: node skills/audit/scripts/slop-scan.mjs <project-folder> prints a summary that starts with "Design God Mode slop-scan". Node 18 or newer is needed for the scanner only.

4. How to use it

  • Full upgrade: /design-god-mode:god-mode plus what they want, for example "make the landing page feel premium" or "clean up the CRM dashboard".
  • Score only, no changes: /design-god-mode:audit.
  • One area: direction (colours and fonts plan), redesign (restyle existing code safely), landing, app-ui, game-ui, motion, polish.
  • After a run, show the person the before and after score, the main changes in plain words, and the pages to look at.

5. Never do this

  • Never print, copy or commit secrets (API keys, .env values, tokens) found in the project.
  • Never spend money: no paid fonts, paid image services or paid UI kits without a clear yes.
  • Never deploy, push to production or change live settings without a clear yes from the person.
  • Never break behaviour: keep routes, forms, field names, tests, analytics and SEO tags working.
  • Never invent facts on a site: no fake reviews, customer logos, numbers or awards. Use marked placeholders.
  • Never replace real photos of the person's work with stock images.

6. For developers changing this repo

  • Skills live in skills/<name>/SKILL.md with name and description frontmatter. Keep each under ~700 words; put tables in references/.
  • The scanner (skills/audit/scripts/slop-scan.mjs) must stay dependency-free and read-only.
  • Re-take screenshots from examples/ after changing the demo pages.

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