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 Tasachii/Tasachii-Tools --skill craft-teachgit clone --depth 1 https://github.com/Tasachii/Tasachii-ToolsWrote 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/tasachii/tasachii-tools/craft-teach)<a href="https://agentmods.dev/skills/tasachii/tasachii-tools/craft-teach"><img src="https://agentmods.dev/badge/skills/tasachii/tasachii-tools/craft-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/tasachii/tasachii-tools/craft-teach"><img src="https://agentmods.dev/badge/skills/tasachii/tasachii-tools/craft-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 | $0.00264 | $0.14633 |
| Opus 5.5 | $0.00106 | $0.05853 |
| Sonnet 5.5 | $0.00053 | $0.02927 |
| Haiku 4.5 | $0.00026 | $0.01463 |
Grade A, and why
craft-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 — 447 lines — stays where its author put it; the contents beside it link to each section on GitHub.
craft-teach — Zero → Job-Ready, the Full Loop
Turn a topic into one self-contained interactive HTML course that a person with zero background can follow until they can actually do the thing — get the junior job, win the game, ship the project. Not a reading list. A hands-on gym.
Reference files are optional. The house-template files named in Appendices F and G (paths under
~/Documents/Full Course by Tasachi) are the author's own finished courses and are not shipped with this plugin. When a path is absent, build the template from the tokens and component spec written in that appendix — each appendix is self-contained.
North Star (never lose this)
Judge every chapter by one question, in the learner's voice:
"I started knowing nothing. If I read this and do the exercises — can I actually do the job / build the project for real?"
And the companion truth that shapes the whole design:
Reading ≠ ability. Watching someone swim ≠ swimming. The course must force doing — runnable sandboxes, missions with no answer key, real projects built line-by-line. If a learner can passively read through and skip all practice, the course has already failed them.
Operating principles
- Depth over coverage-theater. One concept truly understood + practiced beats ten name-dropped. But also: no gaps — chapter N may not assume anything not taught by N-1.
- Every abstract idea earns its keep with a runnable example immediately after it.
- Explain the jargon. The target reader is a smart beginner, not a peer. Every technical term gets a plain-language unpacking the first time.
- Author and review are different people. Never self-approve in the same pass. The review lens (Phase 5) is a separate lane — ideally a fresh subagent — because the author is blind to their own skipped steps and false claims. (In practice this catches real bugs: e.g., a testing chapter that uses
toBeInTheDocument()without installing@testing-library/jest-dom, or a TS chapter claiming "all valid JS is valid TS" right after enablingstrict.) - Ship something runnable every round. Each iteration ends with a file that actually opens and works, even if incomplete.
- Match the user's real constraints. Default deliverable = a single offline HTML file saved to their machine (see Field Notes: artifact links may 404 for them; CDN is blocked by CSP). Confirm language (default = the user's language), stack, and the end-state job/task before building.
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 · 447 lines · 264 tokens per session scan A ac5992ab571f
craft-teach is a skill published in the GitHub repository Tasachii/Tasachii-Tools (2 stars, last pushed 1mo ago), licensed MIT. It adds 264 tokens to every session and 14,633 once invoked, about $0.0011 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
lean-formalize
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific…
exam-forecast
Analyze past exams from the same professor to surface patterns — subject weighting, recurring issue-spot traps, favored hypo types, policy-vs-doctrine mix — and forecast likely emphases for the upcoming exam. Use when the user says "what's on the exam", "analyze past exams", "predict the exam", or shares past exams.
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.