agentleFS
hellocrossmanwildhellocrossmanwild/Claude-skills-tools/skills/access-check/SKILL.md

access-check

Skill0 starsChanged 38 days agoMITView on GitHub

Tests who can see what in an app: visitors, signed-in users and paying members. Use for 'who can see this', 'is my paywall safe', 'check permissions' or 'can people get in free'.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the app and list every page (and important actions, like "download", "watch", "edit").

    line 11
  2. Distinctive:

    Ask (with tap-to-answer options) or infer from their brief, then show the intended rules:

    line 14
  3. Distinctive:

    Use ✓, ✗ or "preview only".

    line 19
  4. Distinctive:

    Run the app (or use the preview link) and open each page while logged out.

    line 22
  5. Distinctive:

    Check the obvious ways around a paywall: opening a paid page's URL directly, direct links to files or videos, thumbnails or links that leak …

    line 23
  6. Distinctive:

    If you can, test as a signed-in free user too.

    line 24

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill 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
SKILL.md

Access check

You're checking that the right people see the right things. The person doesn't code, so report in a table they can read at a glance.

1. List every page and action

Read the app and list every page (and important actions, like "download", "watch", "edit"). Include sign-in and account pages.

2. Say who should see what

Ask (with tap-to-answer options) or infer from their brief, then show the intended rules:

Page / actionVisitor (logged out)Signed in, freePaying memberAdmin

Use ✓, ✗ or "preview only".

3. Test it for real

  • Run the app (or use the preview link) and open each page while logged out. Record what actually happens: shows the content, redirects to sign-in, or shows an error.
  • Check the obvious ways around a paywall: opening a paid page's URL directly, direct links to files or videos, thumbnails or links that leak a paid item's ID, and API routes that return paid content without checking who's asking.
  • If you can, test as a signed-in free user too.
  • If you can't open pages yourself (for example in a normal chat rather than the Code tab), give them a short numbered list of exactly what to click and ask them to report back or send screenshots. Never mark a step passed without seeing the result.

4. Report

Show the table again with what actually happened next to what should happen, and highlight every mismatch in plain English: "A visitor can open /videos/12 directly and watch it without paying." For each problem, explain the fix in one line, and offer to make it on a branch. Don't change anything without a yes.

5. Sign-in sanity

Briefly confirm sign-in itself is handled by a login service (such as Clerk), not home-made password code, and that pages check sign-in on the server, not just by hiding buttons.

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.