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 Immersive-commons/ic-skills --skill ic-onboardinggit clone --depth 1 https://github.com/Immersive-commons/ic-skillsWrote 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/immersive-commons/ic-skills/ic-onboarding)<a href="https://agentmods.dev/skills/immersive-commons/ic-skills/ic-onboarding"><img src="https://agentmods.dev/badge/skills/immersive-commons/ic-skills/ic-onboarding/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/immersive-commons/ic-skills/ic-onboarding"><img src="https://agentmods.dev/badge/skills/immersive-commons/ic-skills/ic-onboarding.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 | $0.00124 | $0.03817 |
| Opus 5 | $0.00062 | $0.01909 |
| Sonnet 5 | $0.00025 | $0.00763 |
| Haiku 4.5 | $0.00012 | $0.00382 |
Grade A, and why
ic-onboarding scanned grade A 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
The person you're onboarding may not be technical. Everything below — curl, JSON, scope names, `next_steps` fields — is **for you, the agent**. The human should never get raw curl or JSON dumped at them. At each step, ** How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You onboard an agent's human user into Immersive Commons so their agent can use IC tools, AND you leave them set up + educated. The mint is RFC 8628 device-code: the agent never sees the human's identity, the human never sees the token, both meet at a short user-code typed into a browser.
Talk to the human in plain English (this is the point)
The person you're onboarding may not be technical. Everything below — curl, JSON, scope names, next_steps fields — is for you, the agent. The human should never get raw curl or JSON dumped at them. At each step, say what you're doing and why in warm, plain English, then do the technical part quietly.
Translate the jargon, every time:
- a token → "a key that lets me use IC for you"
- install the MCP server → "connect your AI assistant to IC's tools"
- a tier → "your membership level"
- scopes → "the things you've allowed me to do"
- the operator → "the person who runs IC" (Ray)
DO explain like you're talking to a smart friend. DON'T paste commands, JSON, scope strings, or tool names unless they ask — summarize outcomes ("you're connected and verified"), not mechanics. DON'T go silent and just run commands; narrate so they understand what's happening to their account.
Open with a plain welcome, e.g.: "Welcome to Immersive Commons. I'll set you up so I can use IC's tools for you (events, the member inbox, research, and more), and I'll explain each step as we go. It takes about a minute, and you'll approve one thing in your browser. Ready?"
The shape: two phases (because tiers are operator-approved)
A brand-new signup is tier public. The token only carries scopes at the user's CURRENT tier, and tier upgrades are approved by the operator (not automatic). So:
- Phase 1 (now, at
public): mint → install MCP → verify → activate → set profile → educate → file ONE quality tier-upgrade request. Everythingpublicallows works immediately; the headline features (agent inbox, events RSVP, leaderboard, research, headsets) are explained but locked until an upgrade is approved. - Phase 2 (after the operator approves an upgrade): the user says "finish my IC setup"; you detect the new tier, re-mint at it, and turn on what unlocked (open the inbox + install the TUI, events, leaderboard, etc.).
What ships with it
1 file 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.
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.
- 7d ago First seen · 197 lines · 124 tokens per session scan A 3717f2a8cba8
ic-onboarding is a skill published in the GitHub repository Immersive-commons/ic-skills (0 stars, last pushed 1mo ago), licensed MIT. It adds 124 tokens to every session and 3,817 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
develop
Work on any Mantle project using the Core SDK contract. Use for manifest, runtime, content model, handler, adapter, validation, and MCP work after a project already exists.
install
Start a new Mantle site locally from a deterministic starter bundle, or orient and continue an existing local or Mantle landing project. Use when the user gives a Mantle repository URL and asks to try or build with it, invokes the Mantle install skill, wants a new Mantle site, or opens an existing generated site.
provision
Ship a local or Mantle landing-generated project to Cloudflare and finish production auth. Use when a Mantle project is ready for GitHub, Cloudflare deployment, self-hosted GitHub OAuth, paid Mantle hosted auth verification, production smoke testing, or operator handoff.
plugin
Discover, plan, apply, and verify Mantle marketplace plugins through the Core SDK contract. Use when the user wants to add an installable capability without hand-planning provisioning steps.
theme
Apply brand and visual direction in a generated Mantle project using its repo-owned theme and UI contracts.
update
Check a Mantle project for drift against its Core SDK, starter source, or installed plugin lockfiles.