Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/mp-web3/claude-starter-kitnpx agentmods add skills/mp-web3/claude-starter-kit/onboardWrote 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.
[](https://agentmods.dev/skills/mp-web3/claude-starter-kit/onboard)<a href="https://agentmods.dev/skills/mp-web3/claude-starter-kit/onboard"><img src="https://agentmods.dev/badge/skills/mp-web3/claude-starter-kit/onboard/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.
<a href="https://agentmods.dev/skills/mp-web3/claude-starter-kit/onboard"><img src="https://agentmods.dev/badge/skills/mp-web3/claude-starter-kit/onboard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00045 | $0.02672 |
| Opus 5.5 | $0.00018 | $0.01069 |
| Sonnet 5.5 | $0.00009 | $0.00534 |
| Haiku 4.5 | $0.00005 | $0.00267 |
Grade A, and why
onboard 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/onboard — Personal AI Assistant Setup
You are guiding a new user through setting up their personal AI assistant. This is their first session. Be conversational, curious, and patient. Don't rush through steps — each one matters.
Arguments: $ARGUMENTS
Before Starting
- Read
~/.claude/CLAUDE.mdand all files in~/.claude/rules/ - Read all files in
knowledge/(if any exist) - Check if
state/onboard-progress.yamlexists — if so, resume (see Resuming below)
Resuming
On ANY /onboard invocation:
- Check if
state/onboard-progress.yamlexists - If yes:
- Read
step_completedto know where they left off - Read all files listed in
files_writtento rebuild context - Tell the user: "Found your progress from last time — you finished step N. Picking up at step N+1."
- Continue from step N+1
- Read
- If no: start from Step 1
- After completing the final step, delete
onboard-progress.yamland commit
Checkpoint Rule (Non-Negotiable)
After completing EACH step, immediately:
- Write/update
state/onboard-progress.yaml:step_completed: N timestamp: YYYY-MM-DDTHH:MM files_written: - knowledge/user/profile.md # ... list all files written so far - Commit locally:
git add -A && git commit -m "onboard: checkpoint after step N"
Do NOT batch commits to the end. Each step is a checkpoint. If the user disconnects, their progress is on disk.
No git push during onboarding — the user may not have a remote configured yet.
Greeting
Greet the user by name (from CLAUDE.md). Explain what you're about to do:
We're going to set up your AI assistant in 5 steps. By the end, I'll know who you are, what drives you, and what you're working toward. Every future session builds on what we create today.
This takes about 20-30 minutes. If you disconnect at any point, just run
/onboardagain and I'll pick up where we left off.
Step 1: User Profile (5 min)
Goal: Create knowledge/user/profile.md
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.
- 1mo ago First seen · 303 lines · 45 tokens per session scan A fa13739ab477
onboard is a skill published in the GitHub repository mp-web3/claude-starter-kit (109 stars, last pushed 7mo ago), licensed MIT. It adds 45 tokens to every session and 2,672 once invoked, about $0.0002 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.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.