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 perniemann/pnCore --skill pn-ai-fluency-curriculumgit clone --depth 1 https://github.com/perniemann/pnCoreWrote 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/perniemann/pncore/pn-ai-fluency-curriculum)<a href="https://agentmods.dev/skills/perniemann/pncore/pn-ai-fluency-curriculum"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-ai-fluency-curriculum/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/perniemann/pncore/pn-ai-fluency-curriculum"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-ai-fluency-curriculum.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 | $0.00069 | $0.01638 |
| Opus 5 | $0.00034 | $0.00819 |
| Sonnet 5 | $0.00014 | $0.00328 |
| Haiku 4.5 | $0.00007 | $0.00164 |
Grade A, and why
pn-ai-fluency-curriculum 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 7d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Fluency Curriculum Skill
When used as a standalone skill, begin every response with [pn-skill] 🔺
When to use
- Onboarding a team that is new to AI agents (Cursor, pnCore, or other tooling)
- Building a structured internal AI education or upskilling program
- Designing a self-paced learning track for an individual engineer, designer, or manager
- Assessing where a team currently sits on the AI fluency spectrum
- Creating practical exercises and checkpoints, not just reading lists
AI fluency levels
| Level | Label | Description |
|---|---|---|
| 0 | Observer | Aware AI exists; has not used it on real work |
| 1 | Prompter | Uses AI reactively — one-off questions, copy-paste outputs |
| 2 | Collaborator | Iterates with AI on real tasks; understands output quality signals |
| 3 | Orchestrator | Directs multi-step agentic workflows; can debug agent failures |
| 4 | Builder | Designs, ships, and governs AI-powered features or tools |
| 5 | Multiplier | Improves how their whole team uses AI; creates skills/rules/agents for others |
Most teams start spread across levels 1–2. The curriculum goal is to pull everyone to at least level 3 and grow level 4–5 champions.
Instructions
1. Assess the team's current level
Run a quick calibration:
- Ask each team member to rate themselves on the 0–5 scale above.
- Ask: "Describe the last time you used an AI tool to complete a real work task. What happened?" — listen for iteration depth, not just outcome.
- Ask: "What stops you from using AI more?" — common answers: trust in output, speed, not knowing the right prompts, fear of mistakes.
Produce a team fluency map: anonymized distribution across levels, with top blockers noted. Use this to calibrate which modules to prioritize.
2. Design the learning path
Build from a three-layer curriculum:
Layer A — Foundation (Level 0 → 2, ~2 weeks)
| Module | Goal | Format |
|---|---|---|
| A1: What agents actually do | Correct mental model of LLMs and agents | 30-min read + Q&A |
| A2: Prompt craft basics | Write prompts that get useful first drafts | Paired exercise with real task |
| A3: Output evaluation | Judge quality, catch errors, iterate | Review workshop |
| A4: Safe use in production | What not to share, when to review outputs | Policy walkthrough |
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.
- 7d ago First seen · 144 lines · 69 tokens per session scan A b78780eff71f
pn-ai-fluency-curriculum is a skill published in the GitHub repository perniemann/pnCore (0 stars, last pushed 4d ago), licensed MIT. It adds 69 tokens to every session and 1,638 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
playwright
Use when the task requires capturing or automating a real browser from the terminal.
typescript
TypeScript coding conventions, best practices, and patterns for writing clean, maintainable code.
eli5
Explain concepts in very simple terms suitable for a five-year-old.
transformer-attention
Use when reasoning about Transformer self-attention, multi-head attention, positional encoding, masked decoder attention, or why attention replaced recurrence/convolutions in sequence models; not for generic NLP or unrelated attention topics.
maestro-coach
Decision support and grounded teaching for the human. Invoke when the user signals a message did not land ("wait, what?", "I don't understand", "explain it like I'm five", "which is better?", "I'm not sure") about a question or fork they have been asked, or when they hand over a locked decision, a lesson, or a bundle…
ml-llm-wiki
Use when answering questions from this machine-learning knowledge base. Triggers: questions about transformers, attention cost and efficiency, and long-context scaling; 'what do we know about attention', 'check the ML wiki'. Read-only querying of compiled knowledge; to add, update, supersede, lint, audit, or critique…