agentleFS
Sign inStart free
Jeff-KazzeeJeff-Kazzee/career-coach/AGENTS.md

career-coach

AGENTS.md4 starsChanged 5 months agoMITView on GitHub

This repository is a public, reusable career-coaching agent skill. Keep private user career data out of the repo. Plan the verification gate before editing. For this repo, the default gate is: Use the platform equivalent of NUL when not on Windows. Do not commit: Use examples with synthetic data only.

  • 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 repositoryOne other file it gives its agents.

The file

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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Use short-lived feature branches off dev only for larger blocks of work.

    line 9
  2. Very specific:

    Use the platform equivalent of NUL when not on Windows.

    line 21
  3. Distinctive:

    Use examples with synthetic data only.

    line 33
  4. Distinctive:

    Prefer concrete deliverables over vague advice.

    line 38
  5. Distinctive:

    Do not weaken the legal, tax, medical, immigration, benefits, discrimination, crisis, privacy, scam, or truthfulness boundaries.

    line 39
  6. Very specific:

    When adding a new mode, add a reference file, update SKILL.md, and add at least one trigger or regression example.

    line 40

≈ “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

Career Coach Agent Instructions

This repository is a public, reusable career-coaching agent skill. Keep private user career data out of the repo.

Branches

  • prod is the public stable branch.
  • dev is active development.
  • Use short-lived feature branches off dev only for larger blocks of work.

Tests

Plan the verification gate before editing. For this repo, the default gate is:

python -m json.tool tests/eval_queries.json > NUL
python -m py_compile scripts/scorecard.py tests/test_scorecard.py
python -m unittest discover -s tests -v

Use the platform equivalent of NUL when not on Windows.

Privacy

Do not commit:

  • Personal career logs
  • Resumes with private contact details
  • Employer, client, legal, tax, immigration, medical, benefits, or compensation records
  • Job applications, recruiter messages, or interview notes tied to real people
  • Secrets or private links

Use examples with synthetic data only.

Editing Principles

  • Preserve the evidence-first coaching stance.
  • Prefer concrete deliverables over vague advice.
  • Do not weaken the legal, tax, medical, immigration, benefits, discrimination, crisis, privacy, scam, or truthfulness boundaries.
  • When adding a new mode, add a reference file, update SKILL.md, and add at least one trigger or regression example.

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