An interactive, chapter-based tutorial for skill-map, where a tester edits Markdown files and watches the map update in a browser.

It helps demonstrate live updates, run tutorial chapters, prepare fixture files, and explain commands without running the main skill-map commands for the tester.

It gives first-time testers a guided path through the product, with shared instructions for setup, pacing, resuming, and handling environment differences.

sm-tutorial — Skill by crystian

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.

agentmods

npx agentmods add skills/crystian/skill-map/sm-tutorial

Any agent

npx skills add crystian/skill-map --skill sm-tutorial

Clone the repo

git clone --depth 1 https://github.com/crystian/skill-map

Made for: Claude Code, Codex.

Per session 198 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,809 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 1 finding. Scan, not verified.

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	$0.00198	$0.04809
Opus 5	$0.00099	$0.02405
Sonnet 5	$0.00040	$0.00962
Haiku 4.5	$0.00020	$0.00481

Measured 2d ago against content hash e4dc4f784ed1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

sm-tutorial scanned grade C with 1 finding 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 2d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

runs `rm -rf .skill-map` first checks the state: if the `realtime` part

.claude/skills/sm-tutorial/SKILL.md · 394 lines

How it starts

The opening of the file, as written. The whole thing — 394 lines — stays where its author put it; the contents beside it link to each section on GitHub.

sm-tutorial: the skill-map book

You are the official skill-map tutorial. The tutorial is one book: an ordered sequence of chapters grouped in parts. Your job is to prepare the fixture files, narrate, show the commands to type, and wait for the tester to run them, without running sm commands for them (except the pre-flight sm version and, for some parts, a silent sm init --no-scan, see _core.md rule #1).

This file is the orchestrator. Two companion files do the rest; read them, do not duplicate them:

references/_core.md, every shared convention: tone, vocabulary, glossing, the host-dependent > rendering rule, provider detection + substitution, the inviolable rules, the per-step cycle, routing/menu, resume/restart, edge cases, the final wrap-up. Read it before talking to the tester.
references/_manifest.yml, the book ToC: every part and chapter, its order, step_file, pace, preflight, prereq, and status. The menu is rendered from this.

Chapter bodies live in references/part-*.md. Dispatch a chapter id to the file named in its part's step_file / step_files (by id prefix when a part spans several files: settings-* → part-settings.md, tour-* → part-plugins.md, authoring-* → part-authoring.md).

For the tester this is a single guided session, never a course catalogue. Refer to a chapter by its tester-facing section.chapter number plus its friendly title (_core.md §Numbering); never expose the internal order index ("Part 3", off by one from the menu), a raw "chapter id", or tour jargon ("the settings tour").

Pre-flight (run once, silent on success)

Follow _core.md for HOW to speak (silence during backstage work, host-dependent rendering, mirroring the tester's language). The steps:

1. Verify the working directory (empty dir)

The skill requires an empty, freshly-created directory as cwd. Run:

pwd
ls -A

Items you ignore when evaluating "empty" (internal infrastructure, not user content): the provider scaffold dirs sm tutorial drops for the active lens, .claude, .codex, .agents, .agent (the vendor marker plus the open-standard skill home, e.g. codex drops both .codex/ and .agents/skills/), .git (a version-control dir alone is a fresh repo, not user content; real files alongside it still trip the check), .tmp (Claude Code scratch dir), SKILL.md / sm-tutorial.md (loose copies of this skill), tutorial-state.json (resume mode).

Read the full file on GitHub · 394 lines

Files

What ships with it

60 files 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.

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.

2d ago First seen · 394 lines · 198 tokens per session scan C e4dc4f784ed1

Subscribe to this mod's changes

sm-tutorial is a skill published in the GitHub repository crystian/skill-map (59 stars, last pushed 2d ago), licensed MIT. It adds 198 tokens to every session and 4,809 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Browser automation Frontend Learning and teaching agents harness manager map markdown skills

playwright

Use when the task requires capturing or automating a real browser from the terminal.

openai/openai-agents-python · 19 tokens

agents-sdk

Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, chat applications, voice agents, or browser automation. Covers Agent class, state management, callable RPC, Workflows, durable execution, queues…

cloudflare/skills · 87 tokens

re0-loop

Run repeated build -> QA -> re0-memo -> re0-work cycles while preserving learning and letting code die. Use for long agentic projects where progress must be measured by quality-cleared templates, reusable modules, and eliminated anti-patterns rather than hours spent or features accumulated.

LilMGenius/paperthin · 60 tokens

airflow-plugins

Builds Airflow 3.1+ plugins that embed FastAPI apps, custom UI pages, React components, middleware, macros, and operator links directly into the Airflow UI. Use when building anything custom inside Airflow 3.1+ that involves Python and a browser-facing interface - creating an Airflow plugin, adding a custom UI page or…

astronomer/agents · 147 tokens

eval-graphics

Turn an eval study's numbers into on-brand, publish-ready figures using the Newsjack chart room (the eval design system), then validate them with Playwright. For producing the charts in a published eval/data study.

elvisun/newsjack · 47 tokens

news-search

Search current news for a topic, company, competitor, or hook and return dated, attributed articles. Uses the newsjack CLI and Medialyst REST API when available, tries direct Medialyst MCP if the CLI is missing, and falls back to host web/browser search with explicit caveats only when neither cloud path is available.

elvisun/newsjack · 69 tokens

sm-tutorial