garrytan/gbrain

Memory & context
Data & research

Graded C on context cost and craft. 3,185 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #285 of 293 on the leaderboard →

Score: 1.50 / 4
Resident: 3,185 tokens
Footprint: heavy
Per activation: 7,408 tokens

Share this grade on X ↗Re-grade now →View on GitHub ↗Grade another skillLast graded Nov 10, 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: C](https://seoagent.com/skill-grader/badge/garrytan/gbrain.svg)](https://seoagent.com/skill-grader/garrytan/gbrain)

HTML

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

Report card

C overall · 1.50/4

github.com/garrytan/gbrain@HEAD · 40 skills · 3,185t resident (heavy) · 7,408t per activation · 115,430t bundle

Resident footprint

3,185t of description text ride in the system prompt of every message across 40 skills (paper's observed per-skill range: 50–280t).

Description honesty

Defensive padding detected: 189 comma-separated trigger keywords; 4 shouted imperatives (ALWAYS/NEVER/MUST…); 1746 words (a quiet description is ~15–40). Padding is individually rational and collectively ruinous — it dilutes every co-installed skill.

Body size

Largest body is 4,485 words (~7,408t), loaded on every trigger. Corpus median 921, p90 2207.

Progressive disclosure

1 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 (`gbrain`, 347 invocations + 81 shell blocks) — verification and state live in code, not prompt.

C overall (1.50/4). 40 skill(s), 3,185t resident on every message (heavy), 7,408t loaded per activation. Weakest axis: resident footprint (F).

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.