lathe: Skill for Claude Code

.claude/skills/lathe-ask/SKILL.md

lathe-ask is a skill for Claude Code from devenjarvis/lathe. It costs 79 tokens per session (512 once invoked), scanned A, original, MIT.

A command for answering questions about a specific part of a Lathe tutorial, using the files and example built in that tutorial.

In plain words
What is it for?
Use it with a Lathe tutorial part when you need clarification about its implementation or an earlier step.
Why use it?
It provides context-specific explanations instead of giving a generic answer that may not match the tutorial's code.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is devenjarvis/lathe's own configuration. It tells Claude Code how to work on lathe itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything lathe configures →

About the project

Lathe is a tool that uses language models to create hands-on, multi-part technical tutorials and lets people study them in a local interface. It is intended for learners who want to follow tutorials themselves, while coding agents can generate, verify, extend, and manage those tutorials through its skills and command-line tool.

devenjarvis/lathe · 1,664 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to devenjarvis/lathe. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/devenjarvis/lathe/main/.claude/skills/lathe-ask/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/devenjarvis/lathe

Made for: Claude Code.

Wrote 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.

agentmods badge for lathe-ask

README.md
[![agentmods](https://agentmods.dev/badge/skills/devenjarvis/lathe/lathe-ask/github.svg)](https://agentmods.dev/skills/devenjarvis/lathe/lathe-ask)
Your own site
<a href="https://agentmods.dev/skills/devenjarvis/lathe/lathe-ask"><img src="https://agentmods.dev/badge/skills/devenjarvis/lathe/lathe-ask/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.

agentmods 80×15 button for lathe-ask

Your own site · 80×15
<a href="https://agentmods.dev/skills/devenjarvis/lathe/lathe-ask"><img src="https://agentmods.dev/badge/skills/devenjarvis/lathe/lathe-ask.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 512 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00079 $0.00512
Opus 5 $0.00039 $0.00256
Sonnet 5 $0.00016 $0.00102
Haiku 4.5 $0.00008 $0.00051

Measured 11d ago against content hash 1b7da23c5aa8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

lathe-ask 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 11d 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.

.claude/skills/lathe-ask/SKILL.md · 34 lines

What it actually says

Lathe — Ask About a Part

Answer a reader's question about one part of a stored tutorial, grounded in what that tutorial actually built. Triggered by:

/lathe-ask <slug> <part-NN.md>
<the reader's question>

The web "Ask" button pastes exactly that: the slug and part on the command line, the question on the next line. Parse all three.

Protocol

  1. Read the part at ~/.lathe/tutorials/<slug>/<part-NN.md>. Read sibling parts (part-NN.md in the same dir) when the question reaches across parts or depends on earlier setup — continuity matters here too.

  2. Answer grounded in this tutorial's concrete artifact — the same controlling example, the same numbers, the same voice the tutorial used. The reader is asking about their synth / their key-value store, not the topic in the abstract. Don't re-teach the whole topic from scratch.

  3. Point at the tutorial, don't re-derive it. Prefer "look at the process_buffer loop in §3 — the modulo there is doing X" over a fresh ground-up explanation. You're a guide standing next to them at the page they're reading.

  4. Be honest about gaps. If the question exposes something the tutorial got wrong, glossed over, or left under a [!UNVERIFIED] flag, say so plainly — don't paper over it. That's more useful than a confident hand-wave.

  5. Stay engaged for follow-ups. This is a conversation, not a one-shot reply.

Boundaries — read-only, conversational

  • There is no lathe ask command. This skill writes nothing and calls back into no CLI command — ask is deliberately conversation-only.
  • No state mutation: don't touch metadata.json, verify-result.json, or the part markdown. Don't verify, don't extend, don't tag.
  • Keep answers specific to this tutorial's concrete artifact, in its voice.
Changes

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.

  1. 11d ago First seen · 34 lines · 79 tokens per session scan A 1b7da23c5aa8

Subscribe to this mod's changes

lathe-ask is a skill published in the GitHub repository devenjarvis/lathe (1,664 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 512 once invoked, about $0.0004 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 2026-08-30.

Related

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".

nexu-io/open-design · 62 tokens

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…

garrytan/gbrain · 138 tokens

miniapp

Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.

yc-software/qm · 25 tokens

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.

companion-inc/feynman · 63 tokens

deck-course-module

A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.

nexu-io/html-anything · 25 tokens

master-yinguang

A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.

xr843/Master-skill · 274 tokens