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 agentmods add skills/vironnimo/vbot/teachnpx skills add Vironnimo/vbot --skill teachgit clone --depth 1 https://github.com/Vironnimo/vbotWhat 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 | $0.00133 | $0.01720 |
| Opus 5 | $0.00067 | $0.00860 |
| Sonnet 5 | $0.00027 | $0.00344 |
| Haiku 4.5 | $0.00013 | $0.00172 |
Grade A, and why
teach 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 yesterday.
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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Teach
Teaching is not explaining. Explaining transfers information out of your head. Teaching changes what is in the learner's head — so that afterward they understand it and can use it without you. Your output is not a good explanation; it is a learner who can now do the thing.
The default failure is the wall of text: a complete, correct, well-structured monologue that the learner nods along to and forgets within the hour. Avoid it. Teaching is a back-and-forth, paced by the learner, not by how much you know.
When to Use
Use when the user wants to understand or be able to do something:
- "teach me / explain / help me learn / walk me through …"
- They hit a concept they don't get and want it to click.
- They're new to a topic and ask you to bring the structure ("I have no idea about X").
Do not use when:
- They want a fact or a one-line answer and will move on — just answer.
- They want a task done, not to learn how — just do it (offer to teach only if useful).
The teaching loop
Teach in small rungs. One concept per rung. Each rung is a short cycle, not a lecture:
calibrate → frame → one rung (explain → show → check → practice) → adapt → next rung → consolidate
After every rung you hand the turn back to the learner. Never stack three rungs into one message.
1. Calibrate (before teaching anything)
You cannot pitch at the right level until you know where the learner is. Briefly find out:
- Prior knowledge — what do they already know that you can anchor the new idea to? New understanding attaches to existing understanding; find the hook.
- Goal — what do they actually want to be able to do, and why? Teach toward that, drop the rest.
- Depth & format — a quick intuition, or a working mastery? A lot of unknowns means start lower.
Ask 1–2 short questions, or infer from the conversation and state your assumption ("I'll assume you know functions but not async — say if that's off"). Don't run a long intake interview.
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.
- yesterday First seen · 141 lines · 133 tokens per session scan A 3442c4443ff9
teach is a skill published in the GitHub repository Vironnimo/vbot (1 stars, last pushed 2d ago), licensed Apache-2.0. It adds 133 tokens to every session and 1,720 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
agent-builder
Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI system" (2) want to understand agent architecture, agentic patterns, or autonomous AI (3) need help with capabilities, subagents, planning, or skill mechanisms (4) ask about Claude Code…
playwright
Use when the task requires capturing or automating a real browser from the terminal.
gpt-researcher
GPT Researcher is an autonomous deep research agent that conducts web and local research, producing detailed reports with citations. Use this skill when helping developers understand, extend, debug, or integrate with GPT Researcher - including adding features, understanding the architecture, working with the API…
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
review-pr
Review a Dograh pull request, branch diff, or pasted patch for repo-specific security and correctness risks that are not obvious from generic FastAPI, Next.js, or Python conventions. Use when the user asks to review a PR, audit a diff, check whether changes are safe to merge, review their own changes, or asks what to…
review-agents-md
Audit Dograh AGENTS.md files for drift against the live repo and for bad scope boundaries between parent and child docs. Use when the user asks to review existing AGENTS files, identify stale guidance, decide whether a subtree needs its own AGENTS.md, or update the AGENTS.md hierarchy under the repo root, api/, or ui/.