# Detection Scoring

> Rate detectability 1-10 (inverted: 10 = hardest to detect). Estimates how likely current controls would catch the failure before impact.

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

---


# Detection Scoring

Rates each failure mode's detectability on an inverted 1-10 scale (10 = hardest to detect).

## Execution

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

## Why Subagent

Detection assessment requires reasoning about observability and monitoring independent of severity/occurrence. Isolated context ensures unbiased evaluation.

## Input

- **failure_modes**: Failure mode catalog
- **chains**: Effect chains (to assess where detection could occur)

## Output

- **scores**: List of (failure_mode_id, detection_score, justification)
- **detection_gaps**: Modes with no current detection mechanism

<!-- 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) -->