New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Codebase Onboarding Tour

by poshan0126 in poshan0126/dotclaude

Builds a quick mental model of an unfamiliar codebase by dispatching read-only Explore subagents and merging their findings into one brief.

MITAuto-check passedAgent Workflows

Install Codebase Onboarding Tour

skills CLI
$ npx skills add poshan0126/dotclaude --skill onboard -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install poshan0126/dotclaude onboard --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/poshan0126/dotclaude.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/onboard .claude/skills/onboard && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
onboard
GitHub stars
870
Token cost
~858 tokens
SKILL.md length
321 words
Files
1
Skills in repo
14
Repo updated
First seen
Licence
MIT

At a glance

Builds a quick mental model of an unfamiliar codebase by dispatching read-only Explore subagents and merging their findings into one brief.

  • Works in 2 steps: Dispatch the tour → Synthesize the brief
  • Getting oriented in a repository you just cloned
  • SKILL.md covers Orientation (injected —…, Step 1: Dispatch the tour, Step 2: Synthesize the brief and Rules
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

It lists the project root and its manifest files first, then dispatches parallel Explore subagents to answer five questions in order of breadth: an overview of what the project is and its top-level layout, the architecture and request flow, the core data models, how auth and security work, and the team's conventions for naming, testing and real build commands. Each subagent returns a tight summary with file and path pointers rather than pasted file contents, so the heavy reading never enters the main conversation.

The returns are merged into one scannable onboarding brief with nothing pasted verbatim, and if a named area such as auth genuinely doesn't exist, the brief says so instead of inventing one. The skill is strictly read-only, mapping the code without ever changing it, and if the repo is empty or trivial it says that plainly rather than padding the brief.

When your agent uses it

  • Getting oriented in a repository you just cloned
  • Understanding a codebase's architecture before making changes
  • Building a glossary of a project's domain models and conventions

Example prompts

  • “I'm new to this repo, give me the onboarding tour.”
  • “Walk me through this codebase's architecture and data models.”
  • “What are this project's naming and testing conventions?”

Workflow steps

2 steps, taken from the step headings in SKILL.md.

  1. Dispatch the tour
  2. Synthesize the brief

What it can do on your machine

Read from SKILL.md and the folder at commit 94b84b9. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Codebase Onboarding Tour loads about 858 tokens when it runs. Until then it costs about 65 tokens; SKILL.md has 321 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~65
When it runs · the whole SKILL.md, loaded when a task matches
~858

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from poshan0126/dotclaude at commit 94b84b9, republished under its MIT licence (© poshan0126). 321 words, ~858 tokens.

Download SKILL.mdSave it as .claude/skills/onboard/SKILL.md (or your agent's skills folder).
name
onboard
description
Get oriented in an unfamiliar codebase fast. An Explore-subagent-driven tour that goes from a one-paragraph overview down to architecture, data models, auth, conventions, and a glossary — without flooding your main context. Use on a repo you're new to.
argument-hint
[optional: focus area like 'the billing module' or 'auth']
disable-model-invocation
true

Build a mental model of a codebase you're new to — broad first, then narrowing — the way the Claude Code onboarding recipe prescribes. Read only; never modify anything. Delegate the heavy reading to Explore subagents so their file dumps stay out of this conversation and only the summaries return.

Orientation (injected — already in front of you)

Top level:

ls -1 "${CLAUDE_PROJECT_DIR:-.}" 2>/dev/null | head -40

Manifests / entry points present at the root:

ls -1 "${CLAUDE_PROJECT_DIR:-.}" 2>/dev/null | grep -iE '^(package\.json|pyproject\.toml|go\.mod|cargo\.toml|gemfile|composer\.json|pom\.xml|build\.gradle|makefile|dockerfile|readme)' || echo "(no standard manifest at root — this may be a subdir or an unusual layout)"

Step 1: Dispatch the tour

Launch Explore subagents (in parallel where independent) to answer these, starting broad and narrowing. If $ARGUMENTS names a focus area, weight every prompt toward it.

  1. Overview — what this project is, who uses it, the top-level layout and what each major directory holds. Point the agent at the README and manifests first.
  2. Architecture — the main patterns, the entry points, how one request (or CLI invocation) flows end to end, and the module boundaries (what must not depend on what).
  3. Data models — the core domain types/entities/tables and their relationships, and where they're defined.
  4. Auth & security — how authentication and authorization work, where secrets/config load from, and the trust boundaries.
  5. Conventions — naming, file layout, test style and framework, error-handling and logging patterns, and the real build/test/lint commands from the manifests.

Each Explore prompt must ask for a tight summary with file:path pointers, NOT pasted file contents.

Step 2: Synthesize the brief

Merge the returns into one scannable onboarding brief — nothing pasted verbatim, everything a pointer:

# Onboarding: <project>

**What it is**: <2-3 sentences>
**Stack**: <languages, frameworks, key libraries>
**Architecture**: <the 3-5 load-bearing facts + entry points, as file:path>
**Data model**: <core entities and where they live>
**Auth & boundaries**: <how auth works, where secrets load>
**Conventions**: <naming, tests, error handling — the house style>
**Run it**: <build / test / lint commands>
**Glossary**: <project-specific terms an outsider wouldn't know>
**Start here**: <the 2-3 files to read first for the focus area>

If the repo is empty or trivial (no source beyond config), say so plainly instead of padding the brief.

Rules

  • Strictly read-only. This skill maps the code; it never changes it.
  • Summaries and file:line pointers only — never paste large files or diffs into the brief.
  • Prefer several focused Explore subagents over reading everything in the main context; keeping exploration out of this conversation is the whole point.
  • Don't invent structure you didn't verify. If an area (e.g. auth) doesn't exist, say "none found" — don't fabricate one.

© poshan0126, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/onboard of poshan0126/dotclaude.

Open the folder on GitHubat commit 94b84b9

Compare with similar skills

Codebase Onboarding Tour next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Codebase Onboarding Tour compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Codebase Onboarding Tour this skillposhan0126/dotclaude870—~858Automated safety check: PassMIT
Codebase Exploreryologdev/yoyo-evolve1.9k—~2.8kAutomated safety check: PassMIT
Caveman Repository ExplorerJuliusBrussee/caveman111k1 repos~492Automated safety check: PassApache-2.0
Init Deep AGENTS.md Generatorcode-yeongyu/oh-my-openagent70k—~3.5kAutomated safety check: PassCustom licence
Codebase Question ResearchWirasm/prp2.3k—~2.8kAutomated safety check: PassMIT
Orchestrator AdvisorTh0rgal/sandboxed.sh516—~568Automated safety check: PassNone

Similar skills

  • Codebase Explorer

    yologdev/yoyo-evolve

    Builds a structural map of a large or unfamiliar codebase by dispatching sub-agents to summarize regions, keeping the main context small.

    1.9k GitHub stars~2.8k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Caveman Repository Explorer

    JuliusBrussee/caveman

    A read-only explorer for cold-start orientation or failed searches that replies with nothing but file path and line range citations, keeping its reads out of main context.

    111k GitHub starsUsed in 1 repo~492 tokens
    Agent WorkflowsAuto-check passed

  • Init Deep AGENTS.md Generator

    code-yeongyu/oh-my-openagent

    Generates a tree of AGENTS.md files for a repository, one at the root and more in complex subdirectories, so agents learn its structure and conventions.

    70k GitHub stars~3.5k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Codebase Question Research

    Wirasm/prp

    Answers how-and-where questions about a codebase by running parallel explorer agents and writing a research document where every claim cites file and line.

    2.3k GitHub stars~2.8k tokensUpdated 8 days ago
    Agent WorkflowsAuto-check passed

  • Orchestrator Advisor

    Th0rgal/sandboxed.sh

    Acts as a persistent read-only advisor that maps the repository once, then answers a cheaper executor agent's questions concisely across a long session.

    516 GitHub stars~568 tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • How Does This Work Explainer

    cursor/plugins

    Official

    Answers how-does-this-work and where-should-this-live questions by exploring the codebase with read-only subagents and writing an onboarding-depth explanation.

    11k GitHub starsUsed in 6 repos~771 tokens
    DevelopmentAuto-check passed

More from poshan0126/dotclaude

All 14 skills in this repo

  • Session Catchup and Handoff

    poshan0126/dotclaude

    Rebuilds working context after /clear by reading a handoff note and the branch's git state, or writes that handoff note before a session ends.

    870 GitHub stars~811 tokensUpdated 1 mo ago
    Auto-check passed

  • Context Budget Check

    poshan0126/dotclaude

    Estimates the per-turn token cost of a project's .claude folder and CLAUDE.md, split into always-loaded, path-scoped and invoked-only files, and flags what runs over budget.

    870 GitHub stars~1.4k tokensUpdated 1 mo ago
    Auto-check passed

  • Parallel Specialist PR Review

    poshan0126/dotclaude

    Reviews a pull request, staged changes or a file by sending the diff to specialist reviewer agents in parallel, then merges their findings into one compact report.

    870 GitHub stars~1.7k tokensUpdated 1 mo ago
    Auto-check passed

  • dotclaude Project Setup

    poshan0126/dotclaude

    Scans a codebase, interviews you, and installs only the justified Claude Code rules, hooks, agents and skills, tailored to the project's stack.

    870 GitHub stars~3.6k tokensUpdated 1 mo ago
    Auto-check passed

  • Ship Changes

    poshan0126/dotclaude

    Walks through commit, push and pull request creation for the current changes, asking you to confirm the files, message, push and PR text at each step.

    870 GitHub stars~953 tokensUpdated 1 mo ago
    Auto-check: notes

  • Interview-Driven Spec Writer

    poshan0126/dotclaude

    Interviews you about scope, behavior, edge cases and verification, then writes a self-contained SPEC.md that a fresh session can implement without this conversation.

    870 GitHub stars~804 tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Codebase Onboarding Tour

What does Codebase Onboarding Tour do?

Builds a quick mental model of an unfamiliar codebase by dispatching read-only Explore subagents and merging their findings into one brief. It lists the project root and its manifest files first, then dispatches parallel Explore subagents to answer five questions in order of breadth: an overview of what the project is and its top-level layout, the architecture and request flow, the core data models, how auth and security work, and the team's conventions for naming, testing and real build commands. Each subagent returns a tight summary with file and path pointers rather than pasted file contents, so the heavy reading never enters the main conversation.

When should I use Codebase Onboarding Tour?

Codebase Onboarding Tour fits situations like: getting oriented in a repository you just cloned; understanding a codebase's architecture before making changes; building a glossary of a project's domain models and conventions.

How do I install Codebase Onboarding Tour in Claude Code?

Run `npx skills add poshan0126/dotclaude --skill onboard -a claude-code`. Or copy the skill folder (skills/onboard in poshan0126/dotclaude) into .claude/skills/onboard in your project. Claude Code loads it when a task matches its description.

How do I install Codebase Onboarding Tour in Codex?

Run `npx skills add poshan0126/dotclaude --skill onboard -a codex`. Or copy the skill folder (skills/onboard in poshan0126/dotclaude) into .agents/skills/onboard in your project. Codex loads it when a task matches its description.

Can I use Codebase Onboarding Tour in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add poshan0126/dotclaude --skill onboard -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/onboard, .gemini/skills/onboard, .github/skills/onboard and .opencode/skills/onboard in your project.

What does Codebase Onboarding Tour need to run?

SKILL.md names no scripts, command-line tools or credentials: Codebase Onboarding Tour is instructions for the agent only.

Does Codebase Onboarding Tour access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Codebase Onboarding Tour safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Codebase Onboarding Tour use?

Codebase Onboarding Tour is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Codebase Onboarding Tour use?

About 858 tokens (SKILL.md is roughly 3.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Codebase Onboarding Tour?

Skills that share tags, products or a category with Codebase Onboarding Tour: Codebase Explorer (yologdev/yoyo-evolve, 1.9k stars), Caveman Repository Explorer (JuliusBrussee/caveman, 111k stars), Init Deep AGENTS.md Generator (code-yeongyu/oh-my-openagent, 70k stars) and Codebase Question Research (Wirasm/prp, 2.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Codebase Onboarding Tour?

poshan0126 (a GitHub user) maintains it in poshan0126/dotclaude, which has 870 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on August 27, 2026.

Source: poshan0126/dotclaude on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.