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.
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
- Distinctive: line 12
Read the rules, in order:
- Very specific: line 47
Never edit build/ or anything in .resumekit/
≈ “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.
Files
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:
rules/core.md— workflow invariants (required reading)rules/profile.md— who the candidate is; calibrate to itrules/style.md— how to write bullet pointsrules/my-rules.md— the user's personal overrides; wins on any conflict
Commands
| Command | What it does |
make check | Compile and validate: bullet line spans, overflow, page count. Run after every edit; must end result: PASS |
make render | Rasterize the pdf to pngs in a temp dir (prints the paths) — view them to judge the layout visually |
make limits | Print the character budget for one-line and two-line bullets |
make build | Compile resume/resume.tex to build/resume.pdf |
make calibrate | Re-measure the character budget; run after changing margins, font, or template |
make init | List templates / switch template (make init TEMPLATE=jakes) |
make setup | Install dependencies (tectonic, poppler) |
make sync | Pull 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 pngmake 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(thenmake calibrate && make check) - Page count / bullet length limits →
\MaxPagesand\MaxBulletLinesinresume/settings.tex - Never edit
build/or anything in.resumekit/
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
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.

