# SAM: Human Escalation Criteria

> Define explicit triggers for escalating to human at each stage (not just Discovery). When should agents block and ask vs attempt repair vs fail?

- Skill: `tools-only/sam-human-escalation-criteria` (Agent Skill, multi-file: 3 files)
- Install (CLI): `npx skillmds@latest add tools-only/sam-human-escalation-criteria`
- Raw SKILL.md: https://api.skillmd.com/api/skills/tools-only/sam-human-escalation-criteria/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Product & Planning
- Author: tools-only (https://skillmd.com/u/tools-only)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/tools-only/sam-human-escalation-criteria

---


**Suggested location**: [`stateless-software-engineering-framework.md`](https://github.com/bitflight-devops/stateless-agent-methodology/blob/main/stateless-software-engineering-framework.md) (each Agent Specification section)

**Research first**: How do GSD deviation rules work? How does BMAD-METHOD handle human checkpoints? What escalation patterns exist in agent frameworks?