A control procedure for teacher-led learning sessions and their recovery after lost context or state errors. It defines how the agent starts lessons, checks intent, and continues learning in a consistent way.

Use it when beginning or changing guided teaching, or when recovering a Tutor session after context loss or an error.

It keeps a learning session coherent when the conversation is interrupted, while limiting unnecessary status messages and state inspection.

using-tutor — Skill for Claude Code and Codex by JanYork/llm-wiki-cli

Install

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.

Any agent

npx skills add JanYork/llm-wiki-cli --skill using-tutor

Clone the repo

git clone --depth 1 https://github.com/JanYork/llm-wiki-cli

Made for: Claude Code, Codex.

Or install claude-lwc, the plugin that ships this one along with the rest of its 8 skills, 7 hooks, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/janyork/llm-wiki-cli/using-tutor/github.svg)](https://agentmods.dev/skills/janyork/llm-wiki-cli/using-tutor)

Your own site

<a href="https://agentmods.dev/skills/janyork/llm-wiki-cli/using-tutor"><img src="https://agentmods.dev/badge/skills/janyork/llm-wiki-cli/using-tutor/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/janyork/llm-wiki-cli/using-tutor"><img src="https://agentmods.dev/badge/skills/janyork/llm-wiki-cli/using-tutor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,398 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.

Model	Per session	Once invoked
Fable 5.1	$0.00034	$0.01398
Opus 5.5	$0.00014	$0.00559
Sonnet 5.5	$0.00007	$0.00280
Haiku 4.5	$0.00003	$0.00140

Measured 2mo ago against content hash dbf1c1d84dfb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

using-tutor 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 2mo 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.

integrations/claude-lwc/skills/using-tutor/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Using Tutor

Act as Prometheus—equal, objective, scientific, concrete, and non-sycophantic. Correct errors from evidence or first principles; never flatter, shame, or agree performatively.

Silent control plane

Tutor is a silent control plane.

Do not narrate Skills, commands, status, recovery, IDs, JSON, or persistence; one sentence only at phase changes, meaningful waits, or multi-step batches.
Never inspect SQLite, plugin/runtime/Skill files or CLI help; never text-search state.
$using-tutor is control text and must not be recorded as a turn.

Visible moment	Rule
`phase/batch/wait`	`outcome-or-next-teaching-action-only;never-Tutor/using-tutor/Skill/LWC/storage/persistence/recording`

Example: “先判断你的起点，再开始第一小节。”

Cold: inspect LWC_READINESS.tutor. If disabled, explain local durability and ask once before lwc --scope global config set --tutor enabled; explicit enablement consents. Status may install pinned, verified runtime.

Intent gate

Situation	State source	Turn flow	Practice
`explicit-intent`	`enter-directly`	`begin-teach-commit`	`skip`
`ambiguous-intent`	`ask-once`	`no-turn-until-answer`	`skip`
`ordinary-qa`	`outside-tutor`	`no-turn`	`skip`

Entry selection precedes turn state; direct entry still starts cold.

Turn state

Cache exact session, subject, owner, Soul, goal/plan, and cognitive anchor.

Situation	State source	Turn flow	Practice
`cold`	`status-once`	`begin-teach-commit`	`skip`
`recovery`	`status-once`	`begin-teach-commit`	`only-if-durable-work`
`hot`	`cached-exact-binding`	`begin-teach-commit`	`skip`
`practice-transition`	`cached-exact-binding`	`begin-teach-commit`	`enter`

Cold runs lwc tutor status once to read the complete current Soul and exact binding. After compaction, identity loss, or pending/revision/owner error, status once recovers the exact turn. Never fuzzy-match. Cross-machine recovery requires latest successful Sync receipt and takeover; old owner must stop writing.

Read the full file on GitHub · 120 lines

Files

What ships with it

1 file 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 221 B

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.

2mo ago First seen · 120 lines · 34 tokens per session scan A dbf1c1d84dfb

Subscribe to this mod's changes

using-tutor is a skill published in the GitHub repository JanYork/llm-wiki-cli (72 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 34 tokens to every session and 1,398 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 2026-08-30.

Learning and teaching agent-memory-system ai-agents ai-agents-cli context-engineering knowledge-bases local-first-ai

using-tutor next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
using-tutorJanYork/llm-wiki-cli	Skill	72	1mo ago	Apache-2.0	A	34	Claude Code, Codex
openspec-onboardFission-AI/OpenSpec	Skill	74k	yesterday	MIT	A	43	Claude Code
gsd-milestone-summaryopen-gsd/gsd-core	Skill	11k	yesterday	MIT	A	20	Claude Code
gsd-helpopen-gsd/gsd-core	Skill	11k	yesterday	MIT	A	12	Claude Code
book-to-skillvirgiliojr94/book-to-skill	Skill	37k	3d ago	MIT	C	105	Claude Code, Codex
interview-coachtam159/next-role	Skill	65	2d ago	MIT	A	58	Claude Code, Codex
learn-contentxg-gh-25/SwarmAI	Skill	59	yesterday	MIT	A	29	Claude Code, Codex