Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/smileynet/teach-menpx agentmods add skills/smileynet/teach-me/generate-topicWrote 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/smileynet/teach-me/generate-topic)<a href="https://agentmods.dev/skills/smileynet/teach-me/generate-topic"><img src="https://agentmods.dev/badge/skills/smileynet/teach-me/generate-topic/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/smileynet/teach-me/generate-topic"><img src="https://agentmods.dev/badge/skills/smileynet/teach-me/generate-topic.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 | $0.00040 | $0.03298 |
| Opus 5.5 | $0.00016 | $0.01319 |
| Sonnet 5.5 | $0.00008 | $0.00660 |
| Haiku 4.5 | $0.00004 | $0.00330 |
Grade A, and why
generate-topic 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 6d 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Topic
Orchestrates the full lesson generation pipeline for one topic. Ensures every downstream step (jargon, quiz, reference, SVG theming, verification) actually happens — not just the lesson writing.
Ownership & Routing
generate-topic is the durable artifact assembly line. It owns the research-backed
authoring sequence; teach owns the conversational relationship. The two never both drive
the same request.
generate-topic owns:
- The single source of truth for the authoring sequence: research → lesson → reference → SR questions → quiz → code extraction → verify (this document's Phase 1–4). Every other skill that needs a durable artifact invokes this pipeline rather than restating it.
- Completeness and the verify gate — a topic is not "done" until Phase 4 passes.
- Committed graph data writes on success (
lesson_file:in MAP.md) and overlay status transitions for the topic being generated.
generate-topic does NOT own (defer, don't duplicate):
- The live learner relationship — mission elicitation, ZPD selection, orientation, and
re-explanation belong to
teach. This pipeline assumes the topic and workspace are already chosen. - Pedagogy rules it applies but does not define: lesson shape and the knowledgeable-colleague
posture (
teachSKILL + ADR 0001), exercise/callout hierarchy (visual-teaching.md), SR-question structure (references/sr-question-authoring.md). - Retention quizzing of taught material (
quiz-me).
Invoked by: teach (when a chosen topic must become a tracked artifact), a direct user
request ("generate/complete topic X"), or map-driven generation. Hands back to teach for
anything conversational once the artifact exists.
See the routing table in the teach skill for how specific learner prompts resolve to one
owner. The short rule: durable + verified artifact → generate-topic; conversation,
orientation, or re-explanation → teach.
What ships with it
1 file 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.
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.
- 6d ago Changed · +42 lines 96b5effbda7d
- 1mo ago First seen · 174 lines · 40 tokens per session scan A 87b9da938d89
generate-topic is a skill published in the GitHub repository smileynet/teach-me (3 stars, last pushed 3d ago), licensed MIT. It adds 40 tokens to every session and 3,298 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
anki
Anki spaced repetition learning system reference. Covers the science of SRS and SM-2 algorithm, card design principles, optimal deck settings, FSRS scheduler, study workflow, essential add-ons, custom templates, filtered decks, and AnkiConnect API.
reading-metaskill
A reading and learning guide based on building a regular reading habit, choosing books, and understanding difficult subjects through original works and explanation.
assisted-mastery
Makes agent reasoning visible, surfaces tradeoffs, and fades help so humans build judgment. Use when reviewing or learning from agent-written code.
antivibe
Code learning and audit framework. Analyze any codebase — new, legacy, or AI-generated — and produce educational explanations or architectural audits. Use when the user wants to understand WHAT and WHY behind any code, not just accept it.
shikhu-inquiry
Answer a question about how or why something in THIS repository works, by showing which tracked files answer it and why, then recording the exchange so it can seed a quiz later. Use it whenever the user asks a genuine question whose subject belongs to this repository — its source, CLI behavior, config, CI, hooks or…
shikhu-study
Tutor the user through a source file with a cached summary, a guided walkthrough, and free-form Q&A — then persist a review record so future quizzes know what was covered.