agentleFS
MoeenNehzatiMoeenNehzati/famulus/skills/setup-interface-manager/SKILL.md

setup-interface-manager

Skill4 starsChanged 4 months agoMITView on GitHub

Use only when a generated managed-setup gate, a Famulus setup-required result, or an exact manager lifecycle route directs the agent here.

The file

We split this skill 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. Very specific:

    Follow only the exact evaluated requirements in root_setup_interface, pending_stack, and current_step.

    line 99
  2. Distinctive:

    Never guess a requirement or retry automatically.

    line 108
  3. Very specific:

    When run-markdown returns terminal_actions, invoke its exact success route after the instructions succeed.

    line 110

≈ “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
<!-- BEGIN BLUEPRINT INTERFACES -->

Generated from blueprint.yaml. Do not edit this block by hand.

Executable Interfaces:

Send the required caller (caller skill), interface, version, and arguments; optional dry_run defaults to false. Compact uses ordered positionals plus an option mapping; ordered raw argv uses positionals: [] plus every argv token in list options. Never mix forms.

  • setup-interface-manager._rtx.interface.authorize — Resume only unmanaged or ready targets and atomically claim every ready managed receipt.
    • Caller: setup-interface-manager
    • Version: 1
    • Security level: 2
    • Alternative: default Arguments JSON (replace labels with actual values). Omit optional positionals and options that are not needed. {"options": {}, "positionals": ["TARGET_INTERFACE", "ORIGINAL_CALLER", "ORIGINAL_INTERFACE", "ORIGINAL_VERSION"], "stdin": null} Required options: []; positional arity: 4..4; stdin: forbidden
  • setup-interface-manager._rtx.interface.begin — Begin exactly one setup or teardown flow for a managed root and redacted continuation.
    • Caller: setup-interface-manager
    • Version: 1
    • Security level: 2
    • Alternative: default Arguments JSON (replace labels with actual values). Omit optional positionals and options that are not needed. {"options": {}, "positionals": ["OPERATION", "ROOT_SETUP", "ORIGINAL_CALLER", "ORIGINAL_INTERFACE", "ORIGINAL_VERSION", "FLOW_ID", "OWNER_HOST", "OWNER_PID", "OWNER_STARTED_AT"], "stdin": null} Required options: []; positional arity: 5..9; stdin: forbidden
  • setup-interface-manager._rtx.interface.invalidate — Invalidate one setup receipt and its live managed dependents only while idle.
    • Caller: setup-interface-manager
    • Version: 1
    • Security level: 2
    • Alternative: default Arguments JSON (replace labels with actual values). Omit optional positionals and options that are not needed. {"options": {}, "positionals": ["SETUP_INTERFACE"], "stdin": null} Required options: []; positional arity: 1..1; stdin: forbidden
  • setup-interface-manager._rtx.interface.recover — Retry by verifying first, or cancel without guessing the current external action's completion.
    • Caller: setup-interface-manager
    • Version: 1
    • Security level: 2
    • Alternative: default Arguments JSON (replace labels with actual values). Omit optional positionals and options that are not needed. {"options": {}, "positionals": ["FLOW_ID", "ACTION"], "stdin": null} Required options: []; positional arity: 2..2; stdin: forbidden
  • setup-interface-manager._rtx.interface.run-markdown — Return only the finite map's exact Markdown instructions and await independent settlement.
    • Caller: setup-interface-manager
    • Version: 1
    • Security level: 2
    • Alternative: default Arguments JSON (replace labels with actual values). Omit optional positionals and options that are not needed. {"options": {}, "positionals": ["FLOW_ID", "INTERFACE"], "stdin": null} Required options: []; positional arity: 2..2; stdin: forbidden
  • setup-interface-manager._rtx.interface.run-python — Run the exact current Python action, its verifier, and the receipt transition in one call.
    • Caller: setup-interface-manager
    • Version: 1
    • Security level: 2
    • Alternative: default Arguments JSON (replace labels with actual values). Omit optional positionals and options that are not needed. {"options": {}, "positionals": ["FLOW_ID", "INTERFACE"], "stdin": null} Required options: []; positional arity: 2..2; stdin: permitted
  • setup-interface-manager._rtx.interface.settle — Independently verify and settle only the exact current Markdown action.
    • Caller: setup-interface-manager
    • Version: 1
    • Security level: 2
    • Alternative: default Arguments JSON (replace labels with actual values). Omit optional positionals and options that are not needed. {"options": {}, "positionals": ["FLOW_ID", "INTERFACE"], "stdin": null} Required options: []; positional arity: 2..2; stdin: forbidden
  • setup-interface-manager._rtx.interface.status — Return unmanaged, ready, setup-required, or setup-busy without mutating claims.
    • Caller: setup-interface-manager
    • Version: 1
    • Security level: 2
    • Alternative: default Arguments JSON (replace labels with actual values). Omit optional positionals and options that are not needed. {"options": {}, "positionals": ["TARGET_INTERFACE"], "stdin": null} Required options: []; positional arity: 1..1; stdin: forbidden
  • setup-interface-manager._rtx.interface.teardown-all — Tear down all valid managed setup receipts in the selected context.
    • Caller: setup-interface-manager
    • Version: 1
    • Security level: 2
    • Alternative: default Arguments JSON (replace labels with actual values). Omit optional positionals and options that are not needed. {"options": {}, "positionals": [], "stdin": null} Required options: []; positional arity: 0..4; stdin: forbidden
<!-- END BLUEPRINT INTERFACES -->

Skill: setup-interface-manager

This hidden workflow controller is entered only from a generated managed-setup gate, a structured Famulus setup result, an explicit status request, or an exact managed setup or teardown invocation. Generic discussion about setup, installation, configuration, readiness, or teardown does not activate it.

Preserve the original caller, interface, version, arguments, and stdin outside the manager. Pass only the non-sensitive continuation identity accepted by the exact manager route. Follow current_step exactly, never substitute an interface or ledger path, and resume the original request only when resume_original is true.

Follow only the exact evaluated requirements in root_setup_interface, pending_stack, and current_step. Treat clues as tentative possibilities, not confirmed causes or instructions. For setup_busy, use only its reported owner and exact recover-busy route; never infer either.

Try recover-busy without force first. If it reports setup.owner_active, force only after the user explicitly confirms interruption. Use ordinary recovery only when a recovery-required result or run-markdown terminal_actions supplies its exact route. Never guess a requirement or retry automatically.

When run-markdown returns terminal_actions, invoke its exact success route after the instructions succeed. Before stopping, reporting failure, asking for input, or otherwise yielding with unfinished instructions, invoke its exact failure_or_abort route instead. If that route returns recovery-required, report the returned recovery state without guessing.

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.