agentleFS
Achref23illiAchref23illi/ui-redesign/AGENTS.md

ui-redesign

AGENTS.md3 starsChanged 16 days agoMITView on GitHub

This repository is a skill for redesigning existing products and their design systems. Claude Code loads SKILL.md automatically. Other agents (Codex, Cursor, Gemini CLI, Windsurf, Aider…) should read SKILL.md before any UI, redesign or design-system work. The short version: Design only: same routes, data, copy and behaviour. Big projects follow references/large-projects.md.

  • 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 31,542 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 repositoryOne other file it gives its agents.

The file

We split this AGENTS.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
  • could be automatic: a setting could enforce it
  1. Distinctive:

    New branch first: Run git status.

    line 9
  2. Distinctive:

    If the tree is dirty, ask the user to commit or stash.

    line 10
  3. Very specific:

    If it's clean, run git switch -c redesign/<scope> and tell the user their app stays untouched.

    line 11
  4. Distinctive:

    Never commit to or merge into their main branch.

    line 12
  5. Very specific:

    Direction: Write DESIGN.md with five decisions: feeling, type, colour, shape, depth.

    line 16

≈ “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

ui-redesign for any coding agent

This repository is a skill for redesigning existing products and their design systems. Claude Code loads SKILL.md automatically. Other agents (Codex, Cursor, Gemini CLI, Windsurf, Aider…) should read SKILL.md before any UI, redesign or design-system work.

The short version:

  1. New branch first. Run git status.
    • If the tree is dirty, ask the user to commit or stash.
    • If it's clean, run git switch -c redesign/<scope> and tell the user their app stays untouched.
    • Never commit to or merge into their main branch.
  2. Capture before. python3 scripts/shots.py <url> <routes…> --out shots/before.
  3. Audit. python3 scripts/audit.py <repo> --out redesign-audit.md --propose redesign-tokens.md.
  4. Ask before merging the design system when the verdict is CONSOLIDATE: give the numbers and the three options (merge / keep tokens / only named screens), then wait.
  5. Direction. Write DESIGN.md with five decisions: feeling, type, colour, shape, depth.
  6. Tokens, then the eight layers, one commit each: type, colour, shape & space, imagery, icons, components & states, data, depth & glass. Details are in references/layers.md.
  7. Verify on renders. python3 scripts/shots.py --compare shots/before shots/after-<layer> --out shots/compare. Check contrast, focus, 44-pt targets, 360 and 1440 widths.
  8. Hand off. Report the branch, one line per layer, what is left, and UX suggestions not built.

Design only: same routes, data, copy and behaviour. Big projects follow references/large-projects.md.

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.