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 tmusser/ai-engineering-skills --skill teach-backgit clone --depth 1 https://github.com/tmusser/ai-engineering-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/tmusser/ai-engineering-skills/teach-back)<a href="https://agentmods.dev/skills/tmusser/ai-engineering-skills/teach-back"><img src="https://agentmods.dev/badge/skills/tmusser/ai-engineering-skills/teach-back/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/tmusser/ai-engineering-skills/teach-back"><img src="https://agentmods.dev/badge/skills/tmusser/ai-engineering-skills/teach-back.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 | $0.00034 | $0.01037 |
| Opus 5.5 | $0.00014 | $0.00415 |
| Sonnet 5.5 | $0.00007 | $0.00207 |
| Haiku 4.5 | $0.00003 | $0.00104 |
Grade A, and why
teach-back 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Teach Back
Purpose
Turn a verified implementation into transferable human understanding.
Transfer ownership, do not narrate the diff. The goal is for the human to explain, debug, and safely modify the implementation rather than merely receive an agent-generated code tour.
Test understanding, do not assume it. Ask for a small teach-back attempt before supplying a complete explanation, then repair only material gaps using implementation evidence.
When to use
Use after trustworthy verification when at least one learning trigger exists:
- the implementation introduced an unfamiliar technology, pattern, or dependency
- a consequential design decision or trade-off should remain human-owned
- the control flow, state transition, data path, or failure mode is non-obvious
- the human expects to review, debug, maintain, or extend the change later
- learning from the implementation is an explicit task goal
Skip boilerplate, tiny reversible patches, familiar work, and tasks where the human does not want a learning pass.
This skill is optional. A completed implementation does not require a teach-back ritual. Use verify-contract for correctness evidence and handoff for continuation state.
Inputs
- Current task contract or
SPEC.md - Verified changed files or git diff
VERIFY.mdand relevant test evidence- The human's stated learning goal or current familiarity when available
- Directly relevant architecture, interfaces, schemas, or runtime behavior
Workflow
- Confirm that implementation verification is trustworthy enough to teach from. If correctness is unresolved, stop and route to
verify-contractor diagnosis first. - Confirm that a learning trigger exists. If none exists, say that
teach-backis not needed and stop. - Select the smallest useful learning target:
- one behavior path
- no more than three consequential decisions, concepts, or failure seams
- one likely maintenance or debugging responsibility
- Build a compact, source-grounded implementation map. Trace the task through the changed system, for example:
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 · 102 lines · 34 tokens per session scan A 0bd03acd4ec9
teach-back is a skill published in the GitHub repository tmusser/ai-engineering-skills (6 stars, last pushed 5d ago), licensed MIT. It adds 34 tokens to every session and 1,037 once invoked, about $0.0001 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
doca-programming-guide
Use this skill when the user is writing their first DOCA app or asking a library-agnostic programming question — picking a shipped sample to copy and modify, wiring pkg-config + meson (or FFI from Rust / Go / Python against the public C ABI), walking the Core lifecycle (create → configure → start → connect → use →…
notebooklm
Full NotebookLM API via notebooklm-py CLI: create notebooks, add sources, generate podcasts, videos, infographics, slides, quizzes, flashcards, mind maps. Triggers on: "notebooklm", "create a podcast", "audio overview", "generate flashcards", "generate infographic", "/notebooklm".
repo-tutor
Use when a user supplies a local repository path or remote Git URL and asks to "teach me this repo", "explain this codebase simply", "show how this system works", "help me use this project", "onboard me to this repository", or "show me how to build on it", especially when the result should be a visual or multipage…
literature-review
Systematic literature review workflow: scope, search (arXiv, Semantic Scholar, Google Scholar), screen, extract, synthesize, and identify gaps. Triggers on: "literature review", "survey the literature", "related work", "systematic review", "synthesize the research", "find papers about", "research gap analysis".
learning-workspace
Use when a human wants a persistent learning workspace across sessions, resumes lessons from recorded evidence, reports practice or a misconception to revisit, or changes an ongoing learning mission. Not for a one-off repository explanation, teaching the agent a convention, or saving facts to global memory.
diagnose
A short question-based assessment of a pilot's current skill level. It produces a profile and saves it in the connected browser or database.