Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Chloris-Blaxk/inno-agent-hub --skill homework-gradergit clone --depth 1 https://github.com/Chloris-Blaxk/inno-agent-hubWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/chloris-blaxk/inno-agent-hub/homework-grader)<a href="https://agentmods.dev/skills/chloris-blaxk/inno-agent-hub/homework-grader"><img src="https://agentmods.dev/badge/skills/chloris-blaxk/inno-agent-hub/homework-grader/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/chloris-blaxk/inno-agent-hub/homework-grader"><img src="https://agentmods.dev/badge/skills/chloris-blaxk/inno-agent-hub/homework-grader.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00175 | $0.06417 |
| Opus 5 | $0.00088 | $0.03209 |
| Sonnet 5 | $0.00035 | $0.01283 |
| Haiku 4.5 | $0.00017 | $0.00642 |
Grade A, and why
homework-grader scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
25 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- examples/marketing-plan-rubric.yaml 3.9 KB
- examples/README.md 1.7 KB
- examples/research-paper-rubric.yaml 4.4 KB
- examples/technical-report-rubric.yaml 4.3 KB
- examples/video-project-rubric.yaml 4.0 KB
- LICENSE 1.0 KB
- README.md 11 KB
- references/batch-processing-guide.md 9.7 KB
- references/bias-mitigation.md 13 KB
- references/evaluation-methodology.md 30 KB
- references/multimodal-pipeline.md 10 KB
- references/quality-control-framework.md 11 KB
- scripts/batch_score.py 52 KB runs code
- scripts/calibrate.py 16 KB runs code
- scripts/export_excel.py 15 KB runs code
- scripts/preprocess.py 31 KB runs code
- scripts/requirements.txt 833 B
- scripts/stats.py 18 KB runs code
- templates/calibration-report.md 3.2 KB
- templates/comment-generation-prompt.md 3.2 KB
- templates/gate-check-prompt.md 3.9 KB
- templates/ir-schema.json 6.0 KB
- templates/rubric.yaml.tmpl 4.2 KB
- templates/scoring-output-schema.json 5.1 KB
- templates/scoring-prompt.md 4.1 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago Changed · +2 lines 26b2cf096b3a
- 11d ago First seen · 812 lines · 175 tokens per session scan A afb5999a4f32
homework-grader is a skill published in the GitHub repository Chloris-Blaxk/inno-agent-hub (12 stars, last pushed 5d ago), with no licence file. It adds 175 tokens to every session and 6,417 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
knowledge-absorber
A tool that deeply examines links, documents, code, or images and turns them into teaching notes and knowledge posters. It supports formats such as PDF, Word, Markdown, source code, and images, and can save the results to a knowledge base.
Création de fiches d'évaluation et questionnaires en bureautique
Génère des modèles structurés pour l'évaluation des compétences bureautiques, incluant la fiche d'évaluation principale, les modèles de commentaires de l'évaluateur et les questionnaires de compétences générales, formatés pour Microsoft Word.
data-report
Turns CSV, Excel, or JSON data into a polished visual report page.
pptx-import
A method for adding an uploaded PowerPoint presentation to an existing classroom as extra pages while keeping the slides' original layout. PowerPoint is Microsoft's presentation file format.
deck-ljg-present
A presentation template that converts an outline or Markdown document into large, poster-like slides while keeping the original wording, order, and content. It uses black, red, or yellow colour themes and assigns document elements to slide layouts.
data-report
A template for turning CSV, Excel, or JSON data into a visual report page. It includes summary metrics, charts, a data table, and written observations based on the supplied data.