# Stress Test Saturation Detection

> Determines whether validation has reached saturation — no new weaknesses or failure modes being discovered. Used by all 5 campaigns as termination signal.

- Skill: `yogsoth-ai/stress-test-saturation-detection` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add yogsoth-ai/stress-test-saturation-detection`
- Raw SKILL.md: https://api.skillmd.com/api/skills/yogsoth-ai/stress-test-saturation-detection/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/stress-test-saturation-detection

---


# Saturation Detection

Determines whether validation has reached saturation — no new weaknesses being discovered.

## Execution

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

## Why Subagent

Requires comparing accumulated findings against latest iteration to compute novelty ratio — dedicated context prevents contamination from ongoing analysis.

## Input

- **findings_accumulated**: Running list of all findings from current campaign
- **latest_iteration_findings**: Findings from the most recent iteration

## Output

- **verdict**: `saturated` | `not-saturated`
- **confidence**: 0.0–1.0
- **novelty_ratio**: percentage of latest findings that are genuinely new
- **reasoning**: explanation of verdict

## Hard Constraint

≥3 consecutive iterations with <10% novel findings → `saturated`

## Budget

One unit = one saturation check. Called after each tactic iteration.

<!-- 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) -->