agentleFS
Sign inStart free
paulmil11paulmil11/decks/AGENTS.md

decks

AGENTS.md106 starsChanged 26 days agoMITView on GitHub

This folder is Decks: HTML slide decks reviewed in the browser, where the user comments under each slide and you edit the deck file and reply on the slide. For any deck work ("process changes", "read my feedback", a pasted "Ask Claude" prompt from a deck, a new deck, a PDF), read and follow .claude/skills/decks/SKILL.md. It has the round procedure, the sb commands, how a deck file is organized, and the slide style rules. Every slide follows the method in…

  • 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 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, 1 is distinctive, and 4 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.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every slide follows the method in that file: action titles, vertical and horizontal flow, the five- and ten-second tests, and charts that …

    line 11
  2. Very specific:

    If a pasted prompt says "Import … into Decks", follow Importing a deck in that file: BRIEF.md in the deck folder has the steps, and …

    line 14
  3. Very specific:

    If the user says "watch my decks", follow Watch mode in that file: ./sb watch in the background (every deck), a round for the deck it names …

    line 18
  4. Very specific:

    Start the server if it isn't running: python3 server.py (port 8790 unless config.json or SB_PORT says otherwise).

    line 23
  5. Very specific:

    Check a change by starting the server on a spare port with a scratch decks folder, SB_PORT=8799 SB_DECKS_DIR=/tmp/sb-test python3 …

    line 36

≈ “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

Decks: instructions for coding agents

This folder is Decks: HTML slide decks reviewed in the browser, where the user comments under each slide and you edit the deck file and reply on the slide.

For any deck work ("process changes", "read my feedback", a pasted "Ask Claude" prompt from a deck, a new deck, a PDF), read and follow .claude/skills/decks/SKILL.md. It has the round procedure, the sb commands, how a deck file is organized, and the slide style rules.

Every slide follows the method in that file: action titles, vertical and horizontal flow, the five- and ten-second tests, and charts that prove the title.

If a pasted prompt says "Import … into Decks", follow Importing a deck in that file: BRIEF.md in the deck folder has the steps, and tools/importdeck.py does the conversion. Ask before installing its Python packages.

If the user says "watch my decks", follow Watch mode in that file: ./sb watch in the background (every deck), a round for the deck it names each time it returns, then watch again.

Quick reference:

  • Start the server if it isn't running: python3 server.py (port 8790 unless config.json or SB_PORT says otherwise).
  • ./sb decks, ./sb comments <deck>, ./sb edits <deck>: what to act on.
  • ./sb proposals <deck> [--bake | --fix-placement]: decisions on proposed slides (prop:true, replaces:'id'), after a line for any proposal that won't show where its original shows; --fix-placement files those right after their original, --bake writes the decisions into the deck file. sb audit names misfiled proposals too, and sb round refuses while one exists (--force records it anyway).
  • ./sb reply <deck> <slide> done|question|skipped "<text>": answer on the slide.
  • ./sb shot, ./sb audit, ./sb export, ./sb round, ./sb commit: check and finish.

Working on Decks itself (not a deck):

  • server.py and sb use only the Python standard library. Keep it that way.
  • tools/browser.mjs needs playwright-core (./setup.sh installs it).
  • tools/importdeck.py and tools/pptx2native.py (Import a deck) need python-pptx, lxml, Pillow, and PyMuPDF. The server never imports them.
  • Check a change by starting the server on a spare port with a scratch decks folder, SB_PORT=8799 SB_DECKS_DIR=/tmp/sb-test python3 server.py, then sb new a deck from each template and run sb audit and sb export on it.

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