agentleFS
Sign inStart free
varunmoka7varunmoka7/resume-hypergraph/AGENTS.md

resume-hypergraph

AGENTS.md0 starsChanged 44 days agoMITView on GitHub

This repository turns a resume into an interactive graph page. Any agent that can read files and run node can do it. Codex, Gemini CLI, Cursor and others read this file; Claude Code uses the plugin in .claude-plugin/. Read skills/resume-graph/SKILL.md and follow it from start to finish. ROOT, as that file uses the word, is this repository's folder. Work in a folder called resume-graph/ inside the person's current directory, not inside this repository. The skill names two helper agents, company-profiler…

  • 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 repository6 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, 0 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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. Very specific:

    Read skills/resume-graph/SKILL.md and follow it from start to finish.

    line 7
  2. Very specific:

    After changing view/, run python3 scripts/serve.py 8131 and browser-harness < scripts/check-layout.py (every sample, four screen sizes, no …

    line 23
  3. Very specific:

    After changing scripts/profile.mjs or the data format, run node --test scripts/ (it also checks each file in view/data/).

    line 24

≈ “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

resume-hypergraph: instructions for AI agents

This repository turns a resume into an interactive graph page. Any agent that can read files and run node can do it. Codex, Gemini CLI, Cursor and others read this file; Claude Code uses the plugin in .claude-plugin/.

When someone asks for a graph of their resume

Read skills/resume-graph/SKILL.md and follow it from start to finish. ROOT, as that file uses the word, is this repository's folder. Work in a folder called resume-graph/ inside the person's current directory, not inside this repository.

The skill names two helper agents, company-profiler and checker. If your tool has subagents, use them the way the skill describes; their instructions are in agents/. If it has none, do those parts yourself in order. Everything else is plain files and four commands:

node ROOT/scripts/profile.mjs check resume-graph/profile.json resume-graph/resume.txt
node ROOT/scripts/profile.mjs links resume-graph/profile.json
node ROOT/scripts/profile.mjs logos resume-graph/profile.json
node ROOT/scripts/profile.mjs build resume-graph/profile.json resume-graph/index.html resume-graph/resume.txt

Three rules hold throughout: nothing about the person is invented, facts about organisations come from a page you opened, and private details stay out. The skill spells them out.

To try it on a made-up resume: examples/lena-hoffmann-resume.txt.

When working on this repository itself

  • view/ is the published page: plain HTML, CSS and JavaScript, no libraries and no build step. Keep it that way.
  • After changing view/, run python3 scripts/serve.py 8131 and browser-harness < scripts/check-layout.py (every sample, four screen sizes, no overlapping labels).
  • After changing scripts/profile.mjs or the data format, run node --test scripts/ (it also checks each file in view/data/).
  • The data format is defined once, in skills/resume-graph/PROFILE-FORMAT.md.
  • Sample people and companies are made up. Do not add a real person's resume to the repository. The picture in docs/ is the author's own graph, by his choice; its data file stays out of the repository.

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