roadmap

roadmap is a skill for Claude Code from yarikleto/claude-teacher-plugin. It costs 64 tokens per session (2,603 once invoked), scanned A, original, MIT.

A visual study-plan maker for learning a subject or reaching a technical goal. It creates an editable Excalidraw diagram, a file format for hand-drawn-style diagrams, plus a text version.

In plain words
What is it for?
Use it to map paths such as backend development, networking, Rust, or an AWS exam. It can show known topics, topics to learn, prerequisites, and milestones.
Why use it?
It turns a broad goal into an ordered path based on what the student already knows. Prerequisites and milestones make it clearer what to learn next.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the claude-teacher plugin — 15 skills, 5 hooks shipped together

Good fit Use it to map paths such as backend development, networking, Rust, or an AWS exam. It can show known topics, topics to learn, prerequisites, and milestones.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add yarikleto/claude-teacher-plugin
Claude Code
/plugin install claude-teacher

Made for: Claude Code.

Or install claude-teacher, the plugin that ships this one along with the rest of its 15 skills, 5 hooks.

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 roadmap

README.md
[![agentmods](https://agentmods.dev/badge/skills/yarikleto/claude-teacher-plugin/roadmap/github.svg)](https://agentmods.dev/skills/yarikleto/claude-teacher-plugin/roadmap)
Your own site
<a href="https://agentmods.dev/skills/yarikleto/claude-teacher-plugin/roadmap"><img src="https://agentmods.dev/badge/skills/yarikleto/claude-teacher-plugin/roadmap/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 roadmap

Your own site · 80×15
<a href="https://agentmods.dev/skills/yarikleto/claude-teacher-plugin/roadmap"><img src="https://agentmods.dev/badge/skills/yarikleto/claude-teacher-plugin/roadmap.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,603 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.
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 $0.00064 $0.02603
Opus 5 $0.00032 $0.01301
Sonnet 5 $0.00013 $0.00521
Haiku 4.5 $0.00006 $0.00260

Measured yesterday against content hash ab29bd088766, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

roadmap 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 yesterday.

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.

skills/roadmap/SKILL.md · 238 lines

How it starts

The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Requested topic/task: $ARGUMENTS

Before accessing education data, read ${CLAUDE_PLUGIN_ROOT}/references/education-data.md. Resolve every <education-db> below using that contract. Current session ID: ${CLAUDE_SESSION_ID}.

Roadmap — Visual Learning Path Generator

Generates an interactive .excalidraw diagram showing the full learning path for a goal or topic area, with nodes color-coded by the student's current knowledge state. Also saves a markdown companion with the same information as text.

Invocation

/claude-teacher:roadmap <goal or topic area>

Examples:

  • /claude-teacher:roadmap backend development
  • /claude-teacher:roadmap networking fundamentals
  • /claude-teacher:roadmap prepare for AWS exam
  • /claude-teacher:roadmap learn Rust from scratch

Process

1. Understand Current State

  1. Read <education-db>/student.json — get goals, level, known technologies, learning style, interests
  2. Read <education-db>/dashboard.json — get all tracked topics and statuses
  3. For topics relevant to the goal, read individual <education-db>/topics/<slug>.json files — get depth, prerequisites, misconceptions
  4. If the student has no profile yet, say: "Run /claude-teacher:init-edu first so I can personalize your roadmap."

2. Research the Learning Path

Use WebSearch to research the standard, industry-accepted learning path for the given goal:

  • Search for curricula, official certification paths, university course sequences, and community-recommended learning orders
  • Identify 8-20 topics that form the path (scale to goal size)
  • Determine prerequisite relationships between topics (which must come before which)
  • Identify 2-4 milestones — meaningful checkpoints where the student can build something or demonstrate competence
  • Note which topics the student already knows (cross-reference with dashboard)

Rules:

  • Every topic in the roadmap must be verified as genuinely part of the learning path — no filler
  • Prerequisites must reflect real dependencies (e.g., you truly need TCP basics before HTTP internals)
  • Milestones should be concrete achievements, not vague labels ("Can build a REST API" not "Understands backend")

Read the full file on GitHub · 238 lines

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. yesterday Changed · +6 lines · +5 tokens per session ab29bd088766
  2. 9d ago First seen · 232 lines · 59 tokens per session scan A ed45b1d068cf

Subscribe to this mod's changes

roadmap is a skill published in the GitHub repository yarikleto/claude-teacher-plugin (8 stars, last pushed 2d ago), licensed MIT. It adds 64 tokens to every session and 2,603 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

learn-anything

A source-grounded adaptive tutor that tracks proof of mastery rather than content completion. Use it to learn a topic systematically, build a course from PDFs, webpages, transcripts or notes, practice retrieval and transfer, resume a long-running course, or verify whether the learner can recall and apply what they…

Nar101/learn-anything · 162 tokens

learn-by-ai

Run long-term, evidence-based adaptive learning and reconnect named study requests to local project records across sessions. Use when a learner says to start, continue, or resume learning a subject; for systematic study plans, source-grounded teaching, layered practice, review, or maintaining a knowledge graph and…

iyohesohoka646-dotcom/learn-by-ai · 77 tokens

learning-mode

Guide active, hands-on learning without completing the chosen learning target for the learner. Use when the user explicitly wants to learn, practice, master, or build something themselves with guidance, especially when a technology or concept is new to them. Diagnose the smallest missing prerequisite, guide prediction…

melsayedx/learning-mode · 116 tokens

fyuu-tutor

Operate long-running, document-backed tutoring projects that turn trusted materials or goals into adaptive HTML lessons, practice, and evidence-guided next steps. Use when creating, continuing, reviewing, or handing off a private learning project; auditing source materials; planning a curriculum; generating lessons or…

fyuuwang/fyuu-tutor · 80 tokens

teach

Use when the user wants to learn or be taught a topic interactively over multiple turns, with the agent acting as tutor rather than answer-giver. Triggers on phrases like "teach me", "tutor me", "quiz me", "let's learn", "help me understand X by working through it step by step", or any request framed around learning a…

SebastianElvis/hammer · 192 tokens

deeptutor-cli

Configure, manage, and use DeepTutor through its CLI, including capabilities, knowledge bases, partners, memory, sessions, notebooks, providers, skills, and the server or Web app.

HKUDS/DeepTutor · 42 tokens