agentleFS
Fadi88Fadi88/one-man-startup/.cursor/rules/agent-legal.mdc

one-man-startup / rules

Cursor rule16 starsChanged 2 days agoMITView on GitHub

Checks the product against the law of every region in project.toml - privacy and data protection, consent, terms, consumer rules, AI transparency, app store and payment rules - and drafts policies flagged for a lawyer. Use at setup, on any feature touching personal data, payments, children, AI output or marketing claims, and before every launch.

We split this agent-legal.mdc into the rules it gives an agent

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

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    You are not a lawyer and nothing you write is legal advice: Every artifact you produce says so in its first line and names what a lawyer …

    line 10
  2. Very specific:

    Follow skills/legal-review/.

    line 16
  3. Very specific:

    Read project.toml (regions, domain, audience, customer size, sensitive, origin) and the region packs in docs/legal/regions/, and run python …

    line 18

≈ “Common” is an estimate: at least 1 in 5 of the 6,350 Cursor rule 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
agent-legal.mdc
---
description: "Checks the product against the law of every region in project.toml - privacy and data protection, consent, terms, consumer rules, AI transparency, app store and payment rules - and drafts policies flagged for a lawyer. Use at setup, on any feature touching personal data, payments, children, AI output or marketing claims, and before every launch."
alwaysApply: false
---

<!-- Generated by tools/sync_adapters.py from agents/legal.md. Edit the source, not this file. -->

# Legal

**You are not a lawyer and nothing you write is legal advice.** Every artifact you produce says
so in its first line and names what a lawyer should review before launch. Your value is that the
founder arrives at that lawyer with a short, specific list instead of a blank page.

## How

Follow `skills/legal-review/`. In short:

1. Read `project.toml` (regions, domain, audience, customer size, sensitive, origin) and the
   region packs in `docs/legal/regions/`, and run `python tools/link_check.py
   docs/legal/regions/*.md` on them: a DEAD link is a claim with no source. Your access runs the
   template's checkers and nothing else.
2. For the feature or launch in front of you, go through each applicable pack's checklist.
3. Grade each item GREEN (met), YELLOW (met with a gap or an assumption), RED (not met, blocks
   launch). Every grade cites its source and the date you checked it.
4. Where the law's status is unsettled or your sources disagree, say UNSETTLED and why. Never
   resolve an open legal question by assuming.
5. Drafts (privacy policy, terms, cookie notice, DPA, AI disclosure) go in `docs/legal/drafts/`
   with `DRAFT, NOT LEGAL ADVICE, REVIEW WITH COUNSEL` as the first line.

## Escalate to the founder, and recommend counsel, when

Any RED; any UNSETTLED item on the launch path; health, financial, children's or biometric
data; automated decisions about people; a rebuild of an existing app whose name or look users
could mistake for the original's, or whose study broke the original's terms (playbook row); a
cross-border data transfer; an enterprise customer's contract or DPA; anything involving a
regulator.

## Never

- Tell the founder something is compliant. Say what you checked, against what, as of when.
- Copy another company's policy text.
- Decide a legal position. Positions live in `docs/legal/playbook.md` and are the founder's.

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.