agentleFS
Sign inStart free
Devesh-ShirsathDevesh-Shirsath/spotkit/AGENTS.md

spotkit

AGENTS.md82 starsChanged 2 months agoMITView on GitHub

This repository is an illustration skill: it turns a feature description into a minimal SVG product illustration that matches a fixed visual system. 1. Read SPEC.md. It is self-contained — every number, the SVG template, the building blocks, the twelve layouts and a complete example. 2. Adapt, don't invent. Pick the nearest of the twelve layouts (SPEC.md §7), start from its example file in examples/, keep its geometry and change only the content. Invent a composition only if none fits,…

  • 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 31,439 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 repository2 other files it gives its agents.

The file

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

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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. Very specific:

    Read SPEC.md. It is self-contained — every number, the SVG template, the building blocks, the twelve layouts and a complete example.

    line 8
  2. Very specific:

    If you can run Python: copy the layout's L* function from build.py, edit its content, and run python3 check.py your.svg before answering.

    line 14
  3. Distinctive:

    Write SVG code. Never use an image-generation model for this.

    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

Spotkit — notes for AI agents

This repository is an illustration skill: it turns a feature description into a minimal SVG product illustration that matches a fixed visual system.

To make an illustration

  1. Read SPEC.md. It is self-contained — every number, the SVG template, the building blocks, the twelve layouts and a complete example.
  2. Adapt, don't invent. Pick the nearest of the twelve layouts (SPEC.md §7), start from its example file in examples/, keep its geometry and change only the content. Invent a composition only if none fits, and say so.
  3. Take icon paths from references/icons.md. Never draw your own glyph.
  4. If you can run Python: copy the layout's L* function from build.py, edit its content, and run python3 check.py your.svg before answering.
  5. Write SVG code. Never use an image-generation model for this.

Don't read these — large, and not needed to draw

  • site/ — the landing page (its index.html alone is ~190 KB)
  • examples/gallery.html, examples/contact-*.svg, examples/flat/
  • icons.py — the same paths as references/icons.md, in Python

Reading from a link, without cloning

Fetch the raw files, not the GitHub pages around them:

Changing the skill itself

build.py is the source of truth — it generated every example. After changing it or any doc:

python3 build.py && python3 flatten.py && python3 check.py --docs

check.py --docs fails if a doc's numbers, colours or snippets disagree with build.py and assets/illustration.css.

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