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 agent-frontier/wgm --skill teach-megit clone --depth 1 https://github.com/agent-frontier/wgmWrote 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/agent-frontier/wgm/teach-me)<a href="https://agentmods.dev/skills/agent-frontier/wgm/teach-me"><img src="https://agentmods.dev/badge/skills/agent-frontier/wgm/teach-me.svg" alt="Measured on agentmods" 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 | $0.00149 | $0.03595 |
| Opus 5 | $0.00075 | $0.01798 |
| Sonnet 5 | $0.00030 | $0.00719 |
| Haiku 4.5 | $0.00015 | $0.00360 |
Grade A, and why
teach-me 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
teach-me
Make a codebase legible. teach-me runs a disciplined lifecycle:
Triage → Map → Tour → Deep dive → First change → Recap
It is the companion to wgm, and it exists because of a specific failure mode:
wgm can build software faster than its operator can understand it. An autonomous loop ships a
working repo, the human opens it, and owns code they cannot explain. teach-me closes that gap —
and its sibling quiz-me proves the gap actually closed. Learning that is
never tested is a feeling, not a fact.
The same discipline serves the other direction: a repo you are adopting rather than one you built. Both audiences need the same thing — the seams, not the file list.
Invocation & modes
Invoked as /teach-me [<mode>] [only] [<focus>] — or activated whenever the user asks to learn,
understand, or onboard onto a repository.
Parse the input first:
- The first word is a mode only if it is exactly one of
map | tour | deep | change | recapAND it is followed by end-of-input, the wordonly, or a:separator. - Otherwise the entire input is the
<focus>and you run the full lifecycle scoped to it. This is the disambiguation rule:/teach-me map the auth flow for meis a focus — notmapmode. - Single-phase modes run that one phase, then hard-stop at its exit gate. Report and wait.
- The optional trailing
onlyis accepted on any mode for emphasis and always hard-stops. - A
:lets a mode carry a focus, e.g./teach-me deep: the retry logic. - No input → survey the whole repository from Triage.
| Invocation | Behavior |
|---|---|
/teach-me |
Full lifecycle over the whole repo |
/teach-me <focus> |
Full lifecycle, scoped to that area |
/teach-me map only |
Build the cited repo map; stop at Map-exit |
/teach-me tour only |
Guided walkthrough from an existing map; stop at Tour-exit |
/teach-me deep: <area> |
One area, to the level of its invariants and edge cases |
/teach-me change |
Only the validated first-change exercise |
/teach-me recap |
Re-read the artifacts and re-summarize; no new exploration |
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 First seen · 227 lines · 149 tokens per session scan A c2f988e9360a
teach-me is a skill published in the GitHub repository agent-frontier/wgm (3 stars, last pushed 7d ago), licensed MIT. It adds 149 tokens to every session and 3,595 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
extract-wisdom
Extract wisdom, insights, and actionable takeaways from YouTube videos, blog posts, articles, or text files. Use when asked to extract wisdom or key insights from a given content source.
openlibrary
Query the Open Library catalog from the terminal: search books and authors, look up works, editions, and ISBNs, enumerate every edition of a work, read community ratings, and resolve cover-image URLs. Fully keyless public API. Includes the OL…M/W/A key-graph reference, ISBN 302-redirect resolution, search query…
product-adoption
Diagnose and design product adoption for onboarding, activation, behavior change, feature discovery, rollout, and sustained use after launch. Covers consumer, B2B, internal-tool, and public-service contexts with evidence-based decision points and cohort segmentation. Does not own acquisition campaigns or marketing…
ml-llm-wiki
Use when answering questions from this machine-learning knowledge base. Triggers: questions about transformers, attention cost and efficiency, and long-context scaling; 'what do we know about attention', 'check the ML wiki'. Read-only querying of compiled knowledge; to add, update, supersede, lint, audit, or critique…
dsm5
Assess and explain questions about mental health and neurocognitive conditions against DSM-5-TR diagnostic criteria, and guide evidence-based conversations for clinicians, patients, and family members. Use when someone asks about symptoms, possible conditions, differential diagnoses, diagnostic criteria, prevalence…
educate
Use this agent when you need to create end-user learning materials, tutorials, glossaries, user journey maps, quick-start guides, or concept explainers for the project being built.