Scale Guardrails

• Source: Built by Jonathan Kvarfordt. Standalone bundle v0.2.
• Frameworks applied: Step 3. Align

It covers a job one of the eight revenue seats has to finish, and it states its process, decision rules, and output format clearly enough for an agent to follow.

1. 1.Copy the SKILL.md text below, or download the raw file.
2. 2.Create a folder named exactly scale-guardrails in your agent's skills directory.
3. 3.Save the file inside that folder as SKILL.md.
4. 4.Ask the agent one of the trigger requests below.
5. 5.Check the output against what you already know before it leaves your desk.

• guardrails
• what should never go out automatically
• cancel trigger

---
name: scale-guardrails
description: Writes the guardrails and cancel trigger for an AI deployment before purchase: what never ships without a human, who can change the record, what data never leaves, and the reversal trigger. Use when the user says "guardrails", "what should never go out automatically", "cancel trigger", "before we sign", "set the rules", or after scale-vendor-scorecard.
---

# scale-guardrails

Write the Guardrails section of `artifacts/scale-capability-decision.md` and update `context/governance.md` and `context/reversal-triggers.md`.

## Preflight (every run)
1. Confirm `GTM-AI-OS/` is accessible. If not: "I need access to your GTM-AI-OS folder. Select it in Cowork's folder picker, or run `os-install` from the core plugin." Stop until it is.
2. Read `CLAUDE.md`, `INDEX.md`, and the last 20 lines of `signals/log.md`.
3. Check the prerequisites below. For anything missing, ask the cold-start questions and offer: (a) run the earlier skill now, or (b) fast path: answer the questions and this skill writes a minimal version of the missing artifact marked `status: draft (fast path)`.
4. On finish, update the artifact row in `INDEX.md` and append one line to `signals/log.md`: `<date> | <skill> | <produced> | <human changed> | <open question>`.

## Prerequisites
- Sourcing recommendation in `artifacts/scale-capability-decision.md`.
Cold-start: "Name the tool or capability you're about to deploy and what it will touch (outreach, CRM, forecasts, customer data)." Continue.

## Step 1: Human verification line
List what never ships without human approval. Defaults: any external message built on Inferred or Unknown facts; any change to a forecast; any customer-facing commitment; any write to a system of record that can't be undone.

## Step 2: Record ownership
Who can change the Account Context record, and how are changes logged.

## Step 3: Data boundaries
What data never leaves the company; whether the vendor trains on your data; retention.

## Step 4: Reversal trigger
"In 90 days, what result means we cancel?" Write it as a measurable statement with an owner and a review date. Add to `context/reversal-triggers.md`.

## Step 5: Write
Fill the section. Set `context/governance.md` to `status: draft`. Mark the capability decision `status: complete`. Update `INDEX.md`.

## Hand off
Say: "Module 3 is done. Install `scale-launch / os-decide / os-act` and run `os-account-scorer` on your list."

What does the Scale Guardrails skill do?

Writes the guardrails and cancel trigger for an AI deployment before purchase: what never ships without a human, who can change the record, what data never leaves, and the reversal trigger.

Where does the Scale Guardrails skill come from?

Built by Jonathan Kvarfordt. Standalone bundle v0.2.. The source and included files are shown on this page and in the package download.

Why was the Scale Guardrails skill chosen for this library?

It covers a job one of the eight revenue seats has to finish, and it states its process, decision rules, and output format clearly enough for an agent to follow.

When should the Scale Guardrails skill not be used?

Use it only for the job named above. A skill applied outside its scope produces confident output on the wrong question.

How do I install the Scale Guardrails SKILL.md file?

Download the file, create a folder named exactly scale-guardrails inside your agent's skills directory, and save the file inside it as SKILL.md. The agent loads it when a request matches the description.