agentleFS
leakyhoseleakyhose/resumekit/AGENTS.md

resumekit

AGENTS.md1 starsChanged 3 months agoMITView on GitHub

This workspace maintains a one-page LaTeX resume, with tooling built for agents. The resume content lives in resume/resume.tex; everything else exists to help you edit it safely and judge the result. Anything under .resumekit/ is machinery (scripts, templates, the LaTeX preamble) — you should not need to read or edit it. Use the make commands instead. Read the rules, in order: make check is mechanical truth (does it fit); the rendered png is judgment (does it look right). Use both…

  • 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 32,671 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 repository3 other files it gives its agents.

The file

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

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the rules, in order:

    line 12
  2. Very specific:

    Never edit build/ or anything in .resumekit/

    line 47

≈ “Common” is an estimate: at least 1 in 5 of the 41,581 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

resumekit — agent instructions

This workspace maintains a one-page LaTeX resume, with tooling built for agents. The resume content lives in resume/resume.tex; everything else exists to help you edit it safely and judge the result.

Anything under .resumekit/ is machinery (scripts, templates, the LaTeX preamble) — you should not need to read or edit it. Use the make commands instead.

Before editing anything

Read the rules, in order:

  1. rules/core.md — workflow invariants (required reading)
  2. rules/profile.md — who the candidate is; calibrate to it
  3. rules/style.md — how to write bullet points
  4. rules/my-rules.md — the user's personal overrides; wins on any conflict

Commands

CommandWhat it does
make checkCompile and validate: bullet line spans, overflow, page count. Run after every edit; must end result: PASS
make renderRasterize the pdf to pngs in a temp dir (prints the paths) — view them to judge the layout visually
make limitsPrint the character budget for one-line and two-line bullets
make buildCompile resume/resume.tex to build/resume.pdf
make calibrateRe-measure the character budget; run after changing margins, font, or template
make initList templates / switch template (make init TEMPLATE=jakes)
make setupInstall dependencies (tectonic, poppler)
make syncPull latest tooling from the upstream resumekit repo without touching the resume

The edit loop

make limits  →  edit resume/resume.tex  →  make check  →  make render + view the png

make check is mechanical truth (does it fit); the rendered png is judgment (does it look right). Use both before considering an edit done.

Where things go

  • Content edits → resume/resume.tex
  • Spacing/margin tweaks → resume/settings.tex (then make calibrate && make check)
  • Page count / bullet length limits → \MaxPages and \MaxBulletLines in resume/settings.tex
  • Never edit build/ or anything in .resumekit/

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.