20-ai-agent-compliance-runbook

name	20-ai-agent-compliance-runbook
description	Use when producing or updating AI-agent compliance operations runbook for control testing, evidence collection, drills, audit-window operations, and remediation. Use agent-runbook for the neighbouring concern; this skill owns the named document contract and its acceptance evidence.
metadata	{"portable":true,"compatible_with":["claude-code","codex"]}

AI Agent Compliance Runbook Skill

Use When

• Produce or update AI-agent compliance operations runbook from approved project evidence.
• Resolve decisions about control testing, evidence collection, drills, audit-window operations, and remediation.
• Prepare a reviewable handoff for Compliance, control owners, and auditors.

Do Not Use When

• The task is primarily owned by agent-runbook; route there and use this skill only for its named output.
• Required project evidence or decision authority is unavailable and the requester expects a pass, release, certification, or production change.

Required Inputs

Artefact	Source/provider	Required?	Behaviour when absent
Project _context/, approved requirements, and relevant architecture	Project owner and upstream phase skills	Required	Stop at a gap register; do not invent scope, thresholds, integrations, or owners.
Existing artefact, implementation, configuration, and evidence named below	Repository, delivery team, or service owner	Required when updating or assessing	Mark inaccessible items ; do not treat them as passed.