Skill Grader / report card

aimpact-inc/repo-harness

Graded C on context cost and craft. 1,038 tokens of this skill ride in the system prompt of every message, whether or not it fires.

Ranked #233 of 314 on the leaderboard →

Score: 2.00 / 4
Resident: 1,038 tokens
Footprint: heavy
Per activation: 3,657 tokens

Share this grade on X ↗Re-grade now →View on GitHub ↗Grade another skillLast graded Nov 13, 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/aimpact-inc/repo-harness.svg)](https://seoagent.com/skill-grader/aimpact-inc/repo-harness)

HTML

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

Report card

C overall · 2.00/4

github.com/aimpact-inc/repo-harness@HEAD · 19 skills · 1,038t resident (heavy) · 3,657t per activation · 180,642t bundle

Resident footprint

1,038t of description text ride in the system prompt of every message across 19 skills (paper's observed per-skill range: 50–280t).

Description honesty

Defensive padding detected: 47 comma-separated trigger keywords; 544 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 2,398 words (~3,657t), loaded on every trigger. Corpus median 921, p90 2207.

Progressive disclosure

Body routes to 41 reference file(s); 101 auxiliary .md files are fetched at point of use instead of riding in the body.

Factoring

Scoped to a coherent procedure set.

CLI leverage

Drives a CLI (`repo-harness`, 18 invocations + 4 shell blocks) — verification and state live in code, not prompt.

C overall (2.00/4). 19 skill(s), 1,038t resident on every message (heavy), 3,657t 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.