agentleFS
adymireadymire/CraftLayer/skills/super-admin-panel/SKILL.md

super-admin-panel

Skill0 starsChanged 3 days agoMITView on GitHub

Design privileged platform-operator tools with strict authorization, auditability, safeguards, and operational clarity.

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:

    Use only for explicitly privileged, platform-wide operational interfaces that can affect tenants, security, billing, or availability.

    line 10
  2. Distinctive:

    Do not use for ordinary organization administration or to create an unaudited shortcut around product permissions.

    line 15
  3. Distinctive:

    Add reason capture, preview, scoped confirmation, and approval or dual-control for high-impact changes as policy requires.

    line 31
  4. Distinctive:

    Never display secrets or unrelated tenant data to simplify operations.

    line 41
  5. Distinctive:

    Prefer reversible actions.

    line 42
  6. Distinctive:

    Do not treat hidden navigation or client flags as access control.

    line 44

≈ “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

Super-admin Panel

When to use

Use only for explicitly privileged, platform-wide operational interfaces that can affect tenants, security, billing, or availability.

When not to use

Do not use for ordinary organization administration or to create an unaudited shortcut around product permissions.

Inputs and assumptions

Confirm operator roles, authorization policy, tenant boundaries, incident procedures, approval requirements, sensitive data policy, and audit retention.

Workflow

  1. Define the minimum operator tasks and least-privilege permission for each.
  2. Require strong server-side authorization and appropriate re-authentication for sensitive operations.
  3. Display tenant, environment, and target identity on every consequential action.
  4. Add reason capture, preview, scoped confirmation, and approval or dual-control for high-impact changes as policy requires.
  5. Log actor, reason, target, request ID, before/after state where safe, and result; protect logs from tampering.
  6. Prevent cross-tenant exposure in search, exports, and detail routes.
  7. Provide safe failure, rollback, and incident-response paths.

Decision rules

  • Privilege is explicit, narrow, time-bounded where feasible, and reviewed.
  • Never display secrets or unrelated tenant data to simplify operations.
  • Prefer reversible actions; require additional checks for irreversible operations.
  • Do not treat hidden navigation or client flags as access control.

Example

A tenant suspension flow should explain user impact, verify the selected tenant and environment, capture the operator reason, enforce authorization on the server, and create an audit event.

Common failures

  • “God mode” access without scoped roles or traceability.
  • Cross-tenant search results leaking data.
  • Confirmation dialogs that do not identify the target or consequences.

Validation

Review threat scenarios, authorization tests, tenant isolation, audit completeness, re-authentication, failure recovery, and permission review.

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.