Skill Grader / report card

B

evalstate/fast-agent

  • Design & frontend
  • Debugging & testing

Graded B on context cost and craft. 256 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #122 of 257 on the leaderboard →

Score
3.00 / 4
Resident
256 tokens
Footprint
light
Per activation
1,955 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.

Skill Grader: B
Markdown
[![Skill Grader: B](https://seoagent.com/skill-grader/badge/evalstate/fast-agent.svg)](https://seoagent.com/skill-grader/evalstate/fast-agent)
HTML
<a href="https://seoagent.com/skill-grader/evalstate/fast-agent"><img src="https://seoagent.com/skill-grader/badge/evalstate/fast-agent.svg" alt="Skill Grader: B" height="20"></a>

Report card

B
B overall · 3.00/4
github.com/evalstate/fast-agent@HEAD · 3 skills · 256t resident (light) · 1,955t per activation · 8,539t bundle
B
Resident footprint
256t of description text ride in the system prompt of every message across 3 skills (paper's observed per-skill range: 50–280t).
C
Description honesty
Defensive padding detected: 16 comma-separated trigger keywords; 129 words (a quiet description is ~15–40). Padding is individually rational and collectively ruinous — it dilutes every co-installed skill.
A
Body size
Largest body is 884 words (~1,955t), loaded on every trigger. Corpus median 921, p90 2207.
C
Progressive disclosure
24 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 (`gh`, 1 invocations + 13 shell blocks) — verification and state live in code, not prompt.
B overall (3.00/4). 3 skill(s), 256t resident on every message (light), 1,955t loaded per activation. Weakest axis: description honesty (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.