JDArmy/BREAK

Security
Data & research

Graded A on context cost and craft. 19 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #9 of 38 on the leaderboard →

Score: 3.70 / 4
Resident: 19 tokens
Footprint: light
Per activation: 2,143 tokens

Re-grade now →View on GitHub ↗Share the grade Grade another skillLast graded Sep 29, 2026 from HEAD

Add the badge to your README

It shows the current letter grade and links back to this page. Improve the skill, hit Re-grade now, and the badge follows — GitHub may keep the old image for up to an hour.

Markdown

[![Skill Grader: A](https://seoagent.com/skill-grader/badge/JDArmy/BREAK.svg)](https://seoagent.com/skill-grader/JDArmy/BREAK)

HTML

<a href="https://seoagent.com/skill-grader/JDArmy/BREAK"><img src="https://seoagent.com/skill-grader/badge/JDArmy/BREAK.svg" alt="Skill Grader: A" height="20"></a>

Report card

A overall · 3.70/4

github.com/JDArmy/BREAK@HEAD · 1 skill · 19t resident (light) · 2,143t per activation · 91,189t bundle

Resident footprint

19t of description text ride in the system prompt of every message (paper's observed per-skill range: 50–280t).

Description honesty

Reads as a statement of purpose, not defensive trigger padding.

Body size

Largest body is 734 words (~2,143t), loaded on every trigger. Corpus median 921, p90 2207.

Progressive disclosure

29 auxiliary .md files ship but the body never points at them — the agent won't find them.

Factoring

Scoped to a coherent procedure set.

CLI leverage

Drives a CLI (`npm`, 2 invocations + 6 shell blocks) — verification and state live in code, not prompt.

A overall (3.70/4). 1 skill(s), 19t resident on every message (light), 2,143t loaded per activation. Weakest axis: progressive disclosure (C).

Six deterministic axes, no LLM, same result every run. Tokens are approximated as chars/4. Read the methodology, or see how SEO skills score on task outcomes in the open SEO skill benchmark.