agentleFS
Sign inStart free
letitbkletitbk/claude-academic-setup/AGENTS.md

claude-academic-setup

AGENTS.md48 starsChanged 7 days agoMITView on GitHub

Precedence: system/developer constraints > explicit user request > project AGENTS.md > this file. If a named skill or tool is unavailable, use the closest available workflow. When starting a new task, check for clearly relevant skills and use them first. Key triggers: - Session start -> napkin - New data -> datacheck - Plots -> viz - Prose -> plain-writing. Default for docs and general-audience prose. For expert or academic writing, keep field terms and stay concise. - Creative work…

  • 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 31,774 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 repository9 other files it gives its agents.

The file

Show its rules and text

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

15 rules. About 0 are common, 12 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈12

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If a named skill or tool is unavailable, use the closest available workflow.

    line 4
  2. Distinctive:

    When starting a new task, check for clearly relevant skills and use them first.

    line 8
  3. Very specific:

    Use request_user_input for structured questions when that tool is available.

    line 15
  4. Distinctive:

    If a simpler approach exists, say so.

    line 22
  5. Distinctive:

    No features, abstractions, or error handling beyond what's needed.

    line 26
  6. Distinctive:

    Prefer concise solutions. If it looks overcomplicated, simplify.

    line 27
  7. Distinctive:

    Don't improve, refactor, or reformat code you weren't asked to change.

    line 31
  8. Distinctive:

    Remove only orphans created by your own changes.

    line 33
  9. Distinctive:

    When running substantive analysis, not one-liners or sanity checks:

    line 38
  10. Very specific:

    Keep logs/ in .gitignore. Never commit logs.

    line 40
  11. Distinctive:

    Never report results without evidence the code actually ran, such as a log, notebook output, or test report.

    line 41
  12. Distinctive:

    Do not discard work you did not create.

    line 46
  13. Very specific:

    Never include Co-Authored-By in commit messages.

    line 47
  14. Distinctive:

    Never hard-wrap prose. Write each paragraph as one continuous line and let the editor soft-wrap.

    line 51
  15. Distinctive:

    When editing an existing prose file that is hard-wrapped and the user asks for content changes, don't silently reflow it.

    line 54

≈ “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

Precedence: system/developer constraints > explicit user request > project AGENTS.md > this file. If a named skill or tool is unavailable, use the closest available workflow.

1. Use Skills When Relevant

When starting a new task, check for clearly relevant skills and use them first. Key triggers:

  • Session start -> napkin
  • New data -> datacheck
  • Plots -> viz
  • Prose -> plain-writing. Default for docs and general-audience prose. For expert or academic writing, keep field terms and stay concise.
  • Creative work -> brainstorming

Use request_user_input for structured questions when that tool is available. Fall back to concise plain-text questions otherwise.

2. Think Before Coding

  • State assumptions.
  • If uncertain, ask.
  • Multiple interpretations -> present them, don't pick silently.
  • If a simpler approach exists, say so.

3. Simplicity First

  • No features, abstractions, or error handling beyond what's needed.
  • Prefer concise solutions. If it looks overcomplicated, simplify.

4. Surgical Changes

  • Don't improve, refactor, or reformat code you weren't asked to change.
  • Match existing style. Assume the worktree may be dirty.
  • Remove only orphans created by your own changes.
  • Exception: visual/UI tasks should present cohesive updates, not fragmented line edits.

5. Reproducible Evidence

When running substantive analysis, not one-liners or sanity checks:

  • Capture output via tee to logs/YYYY-MM-DD_HH-MM-SS_<description>.log.
  • Keep logs/ in .gitignore. Never commit logs.
  • Never report results without evidence the code actually ran, such as a log, notebook output, or test report.

6. Git

  • Inspect status and diffs before changing or committing files.
  • Do not discard work you did not create.
  • Never include Co-Authored-By in commit messages.

7. Prose & Markdown Line Breaks

  • Never hard-wrap prose. Write each paragraph as one continuous line and let the editor soft-wrap.
  • Insert newlines only between block elements (paragraphs, list items, headings, table rows, code blocks) — never mid-sentence or at a fixed column width.
  • Applies to all .md, .txt, and general prose output. Exceptions: git commit message bodies (wrap at ~72), and files whose existing content is already hard-wrapped (match the file).
  • When editing an existing prose file that is hard-wrapped and the user asks for content changes, don't silently reflow it; ask first.

8. Independent Review

  • For important plans or results, get a review from a different model with $claude or $agy.
  • Present the findings and wait for approval before changing files.

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