Skill Grader / report card

C

Parcha-ai/agentrun

Graded C on context cost and craft. 1,398 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #325 of 457 on the leaderboard →

Score
2.00 / 4
Resident
1,398 tokens
Footprint
heavy
Per activation
5,949 tokens
Share this grade on X ↗Re-grade now →View on GitHub ↗Grade another skillLast graded Nov 17, 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/Parcha-ai/agentrun.svg)](https://seoagent.com/skill-grader/Parcha-ai/agentrun)
HTML
<a href="https://seoagent.com/skill-grader/Parcha-ai/agentrun"><img src="https://seoagent.com/skill-grader/badge/Parcha-ai/agentrun.svg" alt="Skill Grader: C" height="20"></a>

Report card

C
C overall · 2.00/4
github.com/Parcha-ai/agentrun@HEAD · 15 skills · 1,398t resident (heavy) · 5,949t per activation · 151,169t bundle
F
Resident footprint
1,398t of description text ride in the system prompt of every message across 15 skills (paper's observed per-skill range: 50–280t).
C
Description honesty
Defensive padding detected: 102 comma-separated trigger keywords; 879 words (a quiet description is ~15–40). Padding is individually rational and collectively ruinous — it dilutes every co-installed skill.
C
Body size
Largest body is 3,366 words (~5,949t), loaded on every trigger. Corpus median 921, p90 2207.
A
Progressive disclosure
Body routes to 7 reference file(s); 34 auxiliary .md files are fetched at point of use instead of riding in the body.
A
Factoring
Scoped to a coherent procedure set.
A
CLI leverage
Drives a CLI (`agentrun`, 39 invocations + 33 shell blocks) — verification and state live in code, not prompt.
C overall (2.00/4). 15 skill(s), 1,398t resident on every message (heavy), 5,949t 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.