Skill Grader / report card

C

Raftersecurity/rafter-cli

Graded C on context cost and craft. 2,401 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #315 of 374 on the leaderboard →

Score
1.90 / 4
Resident
2,401 tokens
Footprint
heavy
Per activation
2,562 tokens
Share this grade on X ↗Re-grade now →View on GitHub ↗Grade another skillLast graded Nov 12, 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.

Skill Grader: C
Markdown
[![Skill Grader: C](https://seoagent.com/skill-grader/badge/Raftersecurity/rafter-cli.svg)](https://seoagent.com/skill-grader/Raftersecurity/rafter-cli)
HTML
<a href="https://seoagent.com/skill-grader/Raftersecurity/rafter-cli"><img src="https://seoagent.com/skill-grader/badge/Raftersecurity/rafter-cli.svg" alt="Skill Grader: C" height="20"></a>

Report card

C
C overall · 1.90/4
github.com/Raftersecurity/rafter-cli@HEAD · 18 skills · 2,401t resident (heavy) · 2,562t per activation · 221,640t bundle
F
Resident footprint
2,401t of description text ride in the system prompt of every message across 18 skills (paper's observed per-skill range: 50–280t).
C
Description honesty
Defensive padding detected: 214 comma-separated trigger keywords; 1392 words (a quiet description is ~15–40). Padding is individually rational and collectively ruinous — it dilutes every co-installed skill.
B
Body size
Largest body is 1,631 words (~2,562t), loaded on every trigger. Corpus median 921, p90 2207.
C
Progressive disclosure
102 auxiliary .md files ship but the body never points at them — the agent won't find them.
A
Factoring
Scoped to a coherent procedure set.
A
CLI leverage
Drives a CLI (`rafter`, 173 invocations + 47 shell blocks) — verification and state live in code, not prompt.
C overall (1.90/4). 18 skill(s), 2,401t resident on every message (heavy), 2,562t 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.