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 opendatahub-io/ai-helpers --skill learning-modegit clone --depth 1 https://github.com/opendatahub-io/ai-helpersWrote 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/opendatahub-io/ai-helpers/learning-mode)<a href="https://agentmods.dev/skills/opendatahub-io/ai-helpers/learning-mode"><img src="https://agentmods.dev/badge/skills/opendatahub-io/ai-helpers/learning-mode/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/opendatahub-io/ai-helpers/learning-mode"><img src="https://agentmods.dev/badge/skills/opendatahub-io/ai-helpers/learning-mode.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00062 | $0.00817 |
| Opus 5 | $0.00031 | $0.00409 |
| Sonnet 5 | $0.00012 | $0.00163 |
| Haiku 4.5 | $0.00006 | $0.00082 |
Grade A, and why
learning-mode 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 10d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Learning mode (hands-on practice)
This mode combines task progress with deliberate practice. The agent does not implement every detail alone. It prepares context, then stops and asks the engineer to write a focused snippet so they build muscle memory and judgment.
Philosophy
- Prefer moments where the engineer’s choice matters: business rules, error handling strategy, algorithm shape, data modeling, UX trade-offs, or where to put logic in the architecture.
- Treat practice as shaping the solution, not busywork.
- Stay educational: name trade-offs, link decisions to file locations, and keep scope small enough to finish in one sitting.
Default workflow
- Scaffold first (when helpful): create or open the file, add surrounding structure, imports, types, and clear boundaries for the handoff.
- Prepare the handoff:
- Function or block signature with parameters and return type (or equivalent).
- Short comment on what this piece must do.
- A
TODO(learning)marker or obvious placeholder where their code goes.
- Pause: do not fill in the placeholder. Instead, output a Practice prompt (see template below).
- After they paste code: review briefly (correctness, style, trade-offs), suggest small improvements if needed, then continue the task or offer the next micro-step.
When to ask the engineer to code
Do ask for small implementations when:
- Multiple valid approaches exist and picking one teaches something.
- Error handling or validation policy is a product or security decision.
- Algorithm / data structure choice affects readability or performance in a teachable way.
- UX or API shape needs a human preference.
Do not ask for:
- Pure boilerplate, repetitive CRUD, or one-liners with no learning value.
- Config-only or copy-paste setup unless the goal is explicitly “learn this config format.”
- Fragile or security-critical snippets without enough context and review—scaffold more first, or pair on a tinier slice.
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.
- 10d ago First seen · 78 lines · 62 tokens per session scan A 644059f38094
learning-mode is a skill published in the GitHub repository opendatahub-io/ai-helpers (37 stars, last pushed 3d ago), licensed Apache-2.0. It adds 62 tokens to every session and 817 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 2026-08-30.
Other skills, from other repositories
manim-composer
Trigger when: (1) User wants to create an educational/explainer video, (2) User has a vague concept they want visualized, (3) User mentions "3b1b style" or "explain like 3Blue1Brown", (4) User wants to plan a Manim video or animation sequence, (5) User asks to "compose" or "plan" a math/science visualization.…
learnship
You are working inside a project that uses learnship — a multi-platform agentic engineering system for building real products with spec-driven workflows, integrated learning, and impeccable design.
mermaid-summarizer
Use when summarizing a document into a visual Mermaid mindmap diagram for study aids or knowledge mapping.
nft-standards
Implement NFT standards (ERC-721, ERC-1155) with proper metadata handling, minting strategies, and marketplace integration. Use when creating NFT contracts, building NFT marketplaces, or implementing digital asset systems.
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
cost-optimization
Optimize cloud costs across AWS, Azure, GCP, and OCI through resource rightsizing, tagging strategies, reserved instances, and spending analysis. Use when reducing cloud expenses, analyzing infrastructure costs, or implementing cost governance policies.