ai-feedback-design-principles

ai-feedback-design-principles is a skill for Claude Code from GarethManning/education-agent-skills. It costs 36 tokens per session (4,753 once invoked), scanned A, original, no licence file.

A set of design principles for checking and improving feedback produced by artificial intelligence, including its teaching value, timing, and effect on learning.

In plain words
What is it for?
Use it to review or redesign automatic hints, comments, corrections, and explanations in digital learning tools.
Why use it?
It helps prevent automated feedback from being inaccurate, poorly timed, or so complete that learners stop thinking for themselves.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Part of the education-agent-skills plugin — 146 skills shipped together

Good fit Use it to review or redesign automatic hints, comments, corrections, and explanations in digital learning tools.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/garethmanning/education-agent-skills/ai-feedback-design-principles
Install

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.

Any agent
npx skills add GarethManning/education-agent-skills --skill ai-feedback-design-principles
Clone the repo
git clone --depth 1 https://github.com/GarethManning/education-agent-skills

Made for: Claude Code.

Or install education-agent-skills, the plugin that ships this one along with the rest of its 146 skills.

Wrote 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.

agentmods badge for ai-feedback-design-principles

README.md
[![agentmods](https://agentmods.dev/badge/skills/garethmanning/education-agent-skills/ai-feedback-design-principles/github.svg)](https://agentmods.dev/skills/garethmanning/education-agent-skills/ai-feedback-design-principles)
Your own site
<a href="https://agentmods.dev/skills/garethmanning/education-agent-skills/ai-feedback-design-principles"><img src="https://agentmods.dev/badge/skills/garethmanning/education-agent-skills/ai-feedback-design-principles/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.

agentmods 80×15 button for ai-feedback-design-principles

Your own site · 80×15
<a href="https://agentmods.dev/skills/garethmanning/education-agent-skills/ai-feedback-design-principles"><img src="https://agentmods.dev/badge/skills/garethmanning/education-agent-skills/ai-feedback-design-principles.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,753 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00036 $0.04753
Opus 5 $0.00018 $0.02377
Sonnet 5 $0.00007 $0.00951
Haiku 4.5 $0.00004 $0.00475

Measured 12d ago against content hash 7a5306d9a9e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ai-feedback-design-principles 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 12d 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.

skills/ai-learning-science/ai-feedback-design-principles/SKILL.md · 232 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

Changes

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.

  1. 12d ago First seen · 232 lines · 36 tokens per session scan A 7a5306d9a9e7

Subscribe to this mod's changes

ai-feedback-design-principles is a skill published in the GitHub repository GarethManning/education-agent-skills (764 stars, last pushed 14d ago), with no licence file. It adds 36 tokens to every session and 4,753 once invoked, about $0.0002 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.