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 binary16labs/prime-silo --skill onboarding-tourgit clone --depth 1 https://github.com/binary16labs/prime-siloWrote 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/binary16labs/prime-silo/onboarding-tour)<a href="https://agentmods.dev/skills/binary16labs/prime-silo/onboarding-tour"><img src="https://agentmods.dev/badge/skills/binary16labs/prime-silo/onboarding-tour/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/binary16labs/prime-silo/onboarding-tour"><img src="https://agentmods.dev/badge/skills/binary16labs/prime-silo/onboarding-tour.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 | $0.00025 | $0.00969 |
| Opus 5 | $0.00013 | $0.00485 |
| Sonnet 5 | $0.00005 | $0.00194 |
| Haiku 4.5 | $0.00003 | $0.00097 |
Grade A, and why
Onboarding Tour 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 9d 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.
What it actually says
Use this skill to give a brand-new user a guided tour. Auto-loads in the Big Bang onboarding space; can also be loaded on demand when a user asks "what can I do / how do I manage X". Be a proactive guide: keep momentum, show don't tell, and end every step with a concrete next action.
what you can demonstrate vs. explain
- UI work runs as browser JavaScript through your normal
_____javascriptexecution. Demonstrate it live. - The CLI (
node space ...), workspace config, and environment variables are terminal actions the user runs in their shell. You cannot run them from the browser — explain them and give copy-paste commands, do not try to_____javascripta shell command. - Never invent widget ids or read
space.yamlby hand. Use the helpers below; widget detail lives in the auto-loadedspace-widgetsskill, space CRUD in thespacesskill. - Keep widget renderers tiny — ideally one line. The
renderermay be a short inline functionasync (parent) => { ... }(a string also works). A long multi-line renderer can be cut off mid-output on a small or local model, leaving the execution block as invalid JavaScript that fails to run — so prefer the smallest renderer that shows progress, useparent.textContentover multi-line HTML, and avoid nested backticks. If a render errors, retry once with an even smaller one (async (parent) => { parent.textContent = "Welcome" }), then move on. A failed widget must never stop the tour.
awareness you already have each turn (read it, don't re-ask)
current date and timetransient → today's date/time; use it instead of asking.Available Spacestransient →id|titleof every space; match titles to ids from here.Current Space Widgetstransient (when a space is open) → live widget layout.
the tour (offer it, then walk one step at a time)
- Orient. Greet by name if known (
space.api.userSelfInfo()), state today's date from the transient, and say where you are (the current space). Offer the tour. - Show the UI. Render a tiny one-line welcome widget with
space.current.renderWidget({...})so the user sees instant visible progress (see example; keep the renderer one line). Mention the Bridge cockpit (#/_prime_silo/bridge) — one pane over memory, documents, code, flows, runs — and the Memory view (#/_prime_silo/memory). - Workspaces. Explain spaces are workspaces; list them with
space.spaces.listSpaces(), and offer to create one withspace.spaces.createSpace({ title }). Deeper space CRUD is thespacesskill. - CLI literacy. Explain the CLI is
node space <command>and have them try, in their terminal:node space help,node space version,node space memory status,node space registry status. - Environment variables. Explain server config lives in environment variables (defined in
commands/params.yaml) and is managed with the CLI:- read all:
node space get - read one:
node space get PORT - change one:
node space set PORT=3030(KEY=VALUE form;setaccepts severalKEY=VALUEpairs) Useful keys:PORT,HOST,WORKERS,SINGLE_USER_APP,CUSTOMWARE_PATH,LOGIN_ALLOWED,GIT_URL.setvalidates against allowed values; HOST/PORT/WORKERS take effect on the nextnode space serve.
- read all:
examples
Greeting and orienting now _javascript return await space.api.userSelfInfo()
Rendering a tiny welcome widget now (one line, so a small model cannot truncate it) _javascript return await space.current.renderWidget({ name: "Welcome", cols: 3, rows: 1, renderer: async (parent) => { parent.textContent = "Welcome aboard — ask me for the tour: UI, spaces, CLI, settings." } })
Listing the available workspaces now _javascript return await space.spaces.listSpaces()
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.
- 9d ago First seen · 58 lines · 25 tokens per session scan A 11e025e645f6
Onboarding Tour is a skill published in the GitHub repository binary16labs/prime-silo (5 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 969 once invoked, about $0.0001 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
sprite-animation
A pixel / sprite-style animated explainer slide — full-bleed cream stage, bold display year, animated pixel-art mascot (e.g. Hanafuda card, mushroom, or 8-bit console), kinetic Japanese display type, ticking timeline ribbon. Reads like a single frame of an educational motion video — looping CSS keyframes, no JS, ready…
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
edu-math-tutorial
A Chinese-language guide for turning a maths problem into a step-by-step teaching video. It explains how to break down the solution, write narration, format equations, and structure scenes.
tutorial
Interactive tutorial teaching Ouroboros hands-on.
clinical-q-and-a
A fast path for answering general educational medical questions and correcting common misconceptions, with a light check against one current authoritative guideline or consensus.
oma-explanation
An offline HTML document that teaches a reader what changed in code, using background information, simple examples, a code walkthrough, and a quiz.