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 jscraik/Agent-Skills --skill teachgit clone --depth 1 https://github.com/jscraik/Agent-SkillsWrote 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/jscraik/agent-skills/teach)<a href="https://agentmods.dev/skills/jscraik/agent-skills/teach"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/teach/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/jscraik/agent-skills/teach"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/teach.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 | $0.00050 | $0.02405 |
| Opus 5.5 | $0.00020 | $0.00962 |
| Sonnet 5.5 | $0.00010 | $0.00481 |
| Haiku 4.5 | $0.00005 | $0.00241 |
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 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Teach
Create and maintain a stateful teaching workspace for a user learning a topic over multiple sessions.
Philosophy
Teach one useful next step at a time. Mission, source trust, retrieval practice, and learning records matter more than a large syllabus. Preserve the source teaching model: knowledge from trusted sources, skills through practice loops, and wisdom through real-world feedback.
When To Use
Use for requests to learn a skill or concept, continue a learning plan, create a lesson, build a curriculum, review learning records, make a reference page, curate learning resources, or update a teaching mission.
Do not use for one-off facts, direct debugging, copyediting, professional certification, medical/legal/safety-critical training, or requests that do not need learning state.
Trigger strongly when the user asks to be taught, continue a course, work from learning records, turn notes into a lesson, recover from learning overload, choose what to study next, curate learning resources, or create reference material. For triggered requests, do not return an empty or no-op result: create the smallest durable learning artifact or a durable blocker note that explains what is needed next.
Inputs
- User learning goal, current level, constraints, and desired outcome.
- Workspace files when present: MISSION.md, RESOURCES.md, GLOSSARY.md, NOTES.md, reference/.html, learning-records/.md, lessons/.html, and assets/.
- Package references: contract, evals, task profile, templates, teaching operating model, mission format, resources format, learning record format, glossary format, knowledge capsule routing, and knowledge capsules.
What ships with it
34 files 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.
- agents/openai.yaml 172 B
- references/contract.yaml 4.1 KB
- references/eval-regression-plan.json 3.8 KB
- references/evals.yaml 38 KB
- references/evals/mission-change.md 387 B
- references/evals/mission-first-python.md 410 B
- references/evals/overloaded-docker.md 374 B
- references/evals/private-transcript.md 371 B
- references/evals/reference-from-lesson.md 367 B
- references/glossary-format.md 1.8 KB
- references/knowledge-capsule-routing.md 1.8 KB
- references/knowledge-capsule.manifest.yaml 3.0 KB
- references/knowledge-capsules/teach-learning-roadmap-lesson-loop.md 1.2 KB
- references/knowledge-capsules/teach-learning-roadmap-local-book-practice.md 1.9 KB
- references/knowledge-capsules/teach-learning-roadmap-mission-and-state.md 1.2 KB
- references/knowledge-capsules/teach-learning-roadmap-proof-and-boundaries.md 1.3 KB
- references/knowledge-capsules/teach-learning-roadmap-roadmap-sequencing.md 1.4 KB
- references/knowledge-capsules/teach-learning-roadmap-source-trust.md 1.2 KB
- references/knowledge-demand.yaml 554 B
- references/learning-record-format.md 2.3 KB
- references/mission-format.md 1.5 KB
- references/resources-format.md 1.9 KB
- references/scorer-calibration/examples.jsonl 1.7 KB
- references/scorer-calibration/manifest.json 746 B
- references/scorer-calibration/raw/teach-cal-fail-evidence-overclaim.json 326 B
- references/scorer-calibration/raw/teach-cal-fail-rubric-copying.json 316 B
- references/scorer-calibration/raw/teach-cal-fail-syllabus-before-mission.json 320 B
- references/scorer-calibration/raw/teach-cal-pass-mission-first.json 324 B
- references/scorer-calibration/raw/teach-cal-pass-retrieval-record.json 313 B
- references/scorer-calibration/raw/teach-cal-pass-source-trust.json 347 B
- references/source-context.yaml 4.1 KB
- references/task-profile.json 1.3 KB
- references/teaching-operating-model.md 5.6 KB
- references/templates.md 7.4 KB
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 · 163 lines · 50 tokens per session scan A 5325e55335b3
teach is a skill published in the GitHub repository jscraik/Agent-Skills (9 stars, last pushed 4d ago), licensed Apache-2.0. It adds 50 tokens to every session and 2,405 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 2026-09-13.
Other skills, from other repositories
moai-workflow-jit-docs
Enhanced Just-In-Time document loading system that discovers, loads, and caches relevant documentation based on user intent and project context. Use when users need specific documentation on demand.
continuous-learning
Pattern extraction, confidence-scored evaluation, skill creation, organization, versioning, and cross-project export pipeline.
goga-discover
Interview the user relentlessly about a decision until every branch of the design tree is resolved, then record the result as a short ADR.
land
Build a stepped deck an audience works through until one thing of it stays with them. Use when the user needs an audience to come away holding one thing.
toy
Build a world the human drives until how a thing behaves is intuitive. Use when the user needs to hold how something behaves and reading has not made it intuitive.
grasp
Build a walkthrough the user works through until they can pass a quiz on it. Use when the user needs to understand something deeply and be quizzed on it.