# Sum Threshold Scoring

> Sum NOS's item-level stars and bucket into good (≥7)/fair (4-6)/poor (≤3) — a fixed threshold lookup, structurally distinct from worst-case-lookup's take-the-worst-value approach. Use this after star-awarding has produced the per-item stars; this is NOS's terminal step.

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

---


# Sum Threshold Scoring

Sum-then-bucket, NOS's own aggregation shape — deliberately kept separate from worst-case-lookup since NOS sums rather than takes a worst-case value (structurally different aggregation, not a value-domain variant of the same algorithm).

## Execution

Subagent — spawned via spawn-agent skill.

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

## Available SOPs

| SOP | When to use |
| --- | --- |
| spawn-agent | Spawn a customized CC subagent with full MCP tool access. |

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