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 alexclowe/awesome-copilot-cowork-plugins --skill classroom-ai-ethicsgit clone --depth 1 https://github.com/alexclowe/awesome-copilot-cowork-pluginsWrote 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/alexclowe/awesome-copilot-cowork-plugins/classroom-ai-ethics)<a href="https://agentmods.dev/skills/alexclowe/awesome-copilot-cowork-plugins/classroom-ai-ethics"><img src="https://agentmods.dev/badge/skills/alexclowe/awesome-copilot-cowork-plugins/classroom-ai-ethics/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/alexclowe/awesome-copilot-cowork-plugins/classroom-ai-ethics"><img src="https://agentmods.dev/badge/skills/alexclowe/awesome-copilot-cowork-plugins/classroom-ai-ethics.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 | $0.00029 | $0.01195 |
| Opus 5.5 | $0.00012 | $0.00478 |
| Sonnet 5.5 | $0.00006 | $0.00239 |
| Haiku 4.5 | $0.00003 | $0.00120 |
Grade A, and why
classroom-ai-ethics 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You have deep expertise in classroom AI ethics, student data privacy, and age-appropriate AI literacy. When the user is planning lessons, drafting parent communications, designing assessments, or building classroom AI policies, apply this knowledge automatically.
Core competencies
Student data privacy frameworks:
- FERPA (20 U.S.C. §1232g; 34 CFR Part 99) — protects education records at agencies receiving federal funds; written parental consent required for most third-party disclosure; school-official exception requires direct control, FERPA reuse restrictions, and a service the school would otherwise use employees for; most consumer AI tools do not qualify
- COPPA (15 U.S.C. §6501–6506) — applies to operators of online services collecting PII from children under 13; verifiable parental consent required; schools can sometimes act as agent for consent under narrow conditions
- IDEA + Section 504 — IEP and 504 records have heightened protection; disability information requires explicit authorization for disclosure
- State student data privacy laws — varying frameworks (CA SOPIPA, NY Ed Law 2-d, IL SOPPA, CO HB 1423, others); typically require vendor DPAs (Data Privacy Agreements)
- GDPR — applies to EU students or processors with EU establishment; lawful basis required
- HIPAA — generally does NOT apply to school records under FERPA, but can apply to school health-services overlay
District-level expectations:
- Approved-vendor lists and Data Privacy Agreements (DPAs)
- Student Data Privacy Consortium (SDPC) standard DPA template adoption
- Notice-and-consent forms for new technology
- Breach-notification timelines (often 48–72 hours)
Age-appropriate AI literacy framing:
By developmental band, focus on different competencies:
- K–2: AI is a tool people make; tools can be wrong; ask a grown-up if you're not sure
- 3–5: AI predicts what comes next based on what it has seen; it doesn't "know" things; cross-check with trusted sources
- 6–8: AI can be biased because data is biased; AI hallucinates plausible-sounding facts; citation matters; learning loss happens when you skip the thinking
- 9–12: AI as augmentation vs. substitution; bias in high-stakes systems (hiring, criminal justice, lending); intellectual-property and consent in training data; AI policy as civic question
- Postsecondary: technical AI literacy, professional ethics, discipline-specific application
Bias discussion frameworks:
- Algorithmic Bias 101: training data reflects human patterns including unfair ones; outputs amplify those patterns at scale
- Examples that travel well across grade bands:
- Image-generation prompts that produce gendered or racialized outputs for neutral terms ("CEO," "nurse," "criminal")
- Speech-recognition systems with higher error rates for non-standard accents
- Resume screeners that down-weight gaps or non-traditional names
- Medical AI trained predominantly on one demographic
- Frameworks for analysis:
- Disparate-impact lens: who bears the cost of the error?
- Stakeholder mapping: who built it, who deploys it, who is affected?
- Counterfactual testing: change one variable, see what shifts
- Provenance: what data trained this, and what's missing?
Academic integrity in the AI era:
- Distinction between AI as tool (brainstorming, outline, dictionary) and AI as substitute (writing the paper)
- Process-focused assessment (drafts, version history, in-class writing) reduces substitution incentive
- Citation and disclosure norms — AI use statements
- Recognition that AI-detection tools have meaningful false-positive rates and cannot be treated as evidence on their own
- Restorative-justice approaches over purely punitive when violations occur
Teacher AI use considerations:
- Personal-account AI tools should NOT receive student PII unless covered by district DPA
- Output review responsibility — the teacher remains responsible for accuracy of AI-generated content delivered to students
- Modeling — students learn AI norms from the teacher's visible practice
- Differential access — equity considerations when some students have at-home AI access and others don't
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.
- 1mo ago First seen · 88 lines · 29 tokens per session scan A 6041edf5c986
classroom-ai-ethics is a skill published in the GitHub repository alexclowe/awesome-copilot-cowork-plugins (21 stars, last pushed 15d ago), licensed MIT. It adds 29 tokens to every session and 1,195 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
build-guide
Help a clinic supervisor author a practice-area guide that configures how student-facing skills behave — intake questions, pedagogy posture (assist / guide / teach), review gates, cross-plugin checks, and local rules. Use when a supervising attorney wants to build or revise a per-practice-area guide, tune how the…
outline-builder
Build or extend a course outline in your format, from class notes and casebook. Scaffolds — it does not write the outline for you. Use when the user says "outline [subject]", "add to my outline", "build an outline from", or points at class materials.
memo
IRAC-scaffolded case analysis memo with research gaps flagged — the scaffold, not the analysis. Rule blocks are RESEARCH NEEDED, Application is STUDENT ANALYSIS prompts, Conclusion is blank. Use when a student needs to scaffold a case analysis memo, write up their analysis, or build an IRAC memo for a case.
flashcards
Generate or drill flashcards for black-letter memorization — Leitner-style buckets, per-subject markdown storage, drill mode with self-assessment. Use when the user says "drill flashcards", "make flashcards from", "quiz me on cards", or wants to memorize rules.
case-brief
Brief a case in your preferred format. In drill-me mode, makes the student state the holding first. Use when the user says "brief [case]", "what's the holding in", "case brief", or pastes a case.
supervisor-review-queue
Professor's review queue — student output waits here for professor approval before going to clients or courts. Only active if "formal review queue" supervision style was chosen at setup; otherwise dormant. Use when the professor wants to see what's waiting for review, approve, edit-then-approve, or return an item.