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.
npx skills add Studio-Moser/Shelby-MCP --skill shelby-onboardgit clone --depth 1 https://github.com/Studio-Moser/Shelby-MCPWrote 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/studio-moser/shelby-mcp/shelby-onboard)<a href="https://agentmods.dev/skills/studio-moser/shelby-mcp/shelby-onboard"><img src="https://agentmods.dev/badge/skills/studio-moser/shelby-mcp/shelby-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/studio-moser/shelby-mcp/shelby-onboard"><img src="https://agentmods.dev/badge/skills/studio-moser/shelby-mcp/shelby-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 | $0.00070 | $0.02164 |
| Opus 5 | $0.00035 | $0.01082 |
| Sonnet 5 | $0.00014 | $0.00433 |
| Haiku 4.5 | $0.00007 | $0.00216 |
Grade A, and why
shelby-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 11d 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shelby Onboard — First-Run Memory Seeding
You're running the ShelbyMCP onboarding interview. Your goal: learn enough about the user to make their AI tools immediately useful — then save it all as structured memories.
This is a conversation, not a form. Ask a few questions, listen carefully, capture what you learn, then ask smarter follow-ups based on what they told you. By the end, the user should have 15-30 well-tagged memories that make every future AI interaction better.
Before You Start
- Run
thought_statsto check the current state of the memory database. - If the database has < 5 thoughts: This is a fresh install. Start from Round 1.
- If the database has 5+ thoughts: The user already has some context saved. Run
list_thoughtswithlimit: 10to see what's there, then tell the user what you already know and offer to fill gaps. Skip rounds that are already well-covered. - Ask the user if they have a migration export from another AI tool they'd like to import (see "Importing Migration Data" below). If yes, handle that first — it gives you a head start and makes the interview smarter.
The Interview
Run through these rounds in order. After each round, capture the relevant thoughts immediately — don't batch them up for later. Give the user a brief confirmation of what you saved ("Got it — saved your role, team, and current project").
Adapt your questions based on what the user tells you. If someone says "I'm a solo founder," don't ask about team structure. If they mention three active projects, dig into each one.
Round 1: Who Are You?
Get the basics that shape every future interaction. Go beyond just the job title — understanding the whole person leads to better AI interactions.
Ask about:
- Name and what they go by
- Role and company (or if they're independent/student/hobbyist)
- Experience level — are they a senior engineer, a designer learning to code, a PM who scripts?
- What they're primarily building right now
- Where they're based (city/timezone — useful for deadline context and collaboration)
- Anything outside of work that's relevant — side projects, interests, or context they'd want AI to know about (keep this light and optional — some people want AI to know them as a whole person, others want to keep it professional)
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.
- 11d ago First seen · 152 lines · 70 tokens per session scan A bd353056871e
shelby-onboard is a skill published in the GitHub repository Studio-Moser/Shelby-MCP (0 stars, last pushed 15d ago), licensed MIT. It adds 70 tokens to every session and 2,164 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.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.