JKHeadley/instar

Agents & automation
Memory & context

Graded D on context cost and craft. 2,050 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #256 of 257 on the leaderboard →

Score: 1.30 / 4
Resident: 2,050 tokens
Footprint: heavy
Per activation: 22,450 tokens

Share this grade on X ↗Re-grade now →View on GitHub ↗Grade another skillLast graded Nov 4, 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: D](https://seoagent.com/skill-grader/badge/JKHeadley/instar.svg)](https://seoagent.com/skill-grader/JKHeadley/instar)

HTML

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

Report card

D overall · 1.30/4

github.com/JKHeadley/instar@HEAD · 24 skills · 2,050t resident (heavy) · 22,450t per activation · 124,115t bundle

Resident footprint

2,050t of description text ride in the system prompt of every message across 24 skills (paper's observed per-skill range: 50–280t).

Description honesty

Defensive padding detected: 176 comma-separated trigger keywords; 1139 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 13,659 words (~22,450t), loaded on every trigger. Corpus median 921, p90 2207.

Progressive disclosure

23 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 (`instar`, 22 invocations + 174 shell blocks) — verification and state live in code, not prompt.

D overall (1.30/4). 24 skill(s), 2,050t resident on every message (heavy), 22,450t 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.