# Severity Scoring

> Rate failure mode severity 1-10 based on end-effect impact. Follows AIAG-VDA severity scale calibrated for research artifacts.

- Skill: `yogsoth-ai/severity-scoring` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add yogsoth-ai/severity-scoring`
- Raw SKILL.md: https://api.skillmd.com/api/skills/yogsoth-ai/severity-scoring/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Research & Search
- Author: yogsoth-ai (https://skillmd.com/u/yogsoth-ai)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/yogsoth-ai/severity-scoring

---


# Severity Scoring

Rates each failure mode's severity on a 1-10 scale based on end-effect impact.

## Execution

Subagent — spawned via subagent-spawning/spawn-agent.

## Why Subagent

Severity assessment requires consistent calibration across all modes. Isolated context prevents anchoring bias from occurrence or detection considerations.

## Input

- **failure_modes**: Failure mode catalog
- **chains**: Cause-mode-effect chains (for end-effect reference)

## Output

- **scores**: List of (failure_mode_id, severity_score, justification)
- **calibration_notes**: Any scoring edge cases or assumptions

<!-- BEGIN available-tables (generated) -->

## Available SOPs

Optional, no fixed order; the final leaf is always a sop.

| SOP | When to use |
| --- | --- |
| spawn-agent | Spawn a customized CC subagent with full MCP tool access. Used by SOPs that declare execution: subagent. |

<!-- END available-tables (generated) -->