agentleFS
runxhqrunxhq/runx/skills/governed-outbound/SKILL.md

governed-outbound

Skill97 starsChanged 33 days agoApache-2.0View on GitHub

Fetch one allowlisted source, scrub personal data, and deliver the exact safe payload through a configured provider with approval and independent readback; use plan explicitly for a handoff only.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Default delivery inputs are url, allowlist, channel, principal, and a tenant-owned connector containing only provider and exact target.

    line 45

≈ “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

Governed Outbound

Deliver exact scrubbed outbound content in this order:

  1. web-fetch performs the bounded provider read and returns source readback.
  2. redact-pii detects semantic identifiers, deterministically scrubs the content, and withholds residual content unless its final verdict is ready.
  3. The exact scrubbed content and digest pass directly to send-as; the caller selects only the provider and bounded target, never provider request grammar.
  4. send-as#send plans principal and audience, derives the provider request and idempotency key, requests exact approval for the consequential send, performs it once, and requires independent provider readback.

The provider's connector remains separately configured and tenant-agnostic. A missing connector instance blocks before delivery; a plan or accepted request is never reported as sent. Select the explicit plan runner when a provider-neutral handoff is the requested outcome.

Composes

<!-- Generated from the native execution closure; run pnpm core-skills:composes:generate. -->
  • redact-pii#redact-pii
  • send-as#plan
  • send-as#send
  • web-fetch#web-fetch

Stop conditions

  • Missing or disallowed fetch inputs stop in web-fetch.
  • needs_review or blocked redaction skips planning and delivery.
  • The plan runner never asks for performative approval; approval belongs to the exact live send in send-as#send.
  • A send plan whose principal, audience, or digest differs from the approved redaction fails deterministic finalization.
  • Provider execution and readback must occur in the selected downstream adapter before any caller reports delivery.

Output

outbound_plan records completion: plan_only, provider_delivery: not_executed, source and redaction digests, the bounded send plan, and the selected provider actions. The scrubbed content remains available only in the redaction step output for the authorized downstream adapter.

Default delivery inputs are url, allowlist, channel, principal, and a tenant-owned connector containing only provider and exact target. operator_context is optional. The explicit plan runner omits connector.

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.