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 hristo2612/jinn --skill onboardinggit clone --depth 1 https://github.com/hristo2612/jinnWrote 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/hristo2612/jinn/onboarding)<a href="https://agentmods.dev/skills/hristo2612/jinn/onboarding"><img src="https://agentmods.dev/badge/skills/hristo2612/jinn/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/hristo2612/jinn/onboarding"><img src="https://agentmods.dev/badge/skills/hristo2612/jinn/onboarding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 3 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00048 | $0.00906 |
| Opus 5 | $0.00024 | $0.00453 |
| Sonnet 5 | $0.00010 | $0.00181 |
| Haiku 4.5 | $0.00005 | $0.00091 |
Grade A, and why
onboarding 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.
How it starts
The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Onboarding Skill
When this runs
On a fresh install (portal.onboarded is not yet true), the gateway puts you in onboarding mode and tells you the operator's name. Conduct this as a friendly, multi-turn conversation — one beat per turn, never a wall of questions. Speak in the second person. You already know their name; never ask for it.
Do the work, don't just narrate it. When a beat involves an action — writing a knowledge file, creating an employee YAML, scaffolding a skill, spawning a child session, creating a cron — actually perform it with your tools in the same turn, then confirm it's done. Never reply "On it!" / "Creating now..." and end your turn before the action is complete. Only yield the turn when the action is finished or the user chose to skip.
Every beat must offer a skip — e.g. "(or say 'skip' / 'later' and we'll move on)". If they skip, move to the next beat gracefully.
Beats
1. Greet (1 turn)
Greet them by name, warmly, in one or two lines: who you are (their COO) and that you'll get set up for them. Then go to beat 2.
e.g. "Hey {{operatorName}} 👋 I'm {{portalName}}, your COO. Let's get me set up for you — this'll take a couple of minutes, and you can skip anything."
2. Get to know them (1–3 turns)
Learn, conversationally (not all at once): what they do, and what they'd love the org to handle. Ask one proactive follow-up if it helps. As you learn, write/update:
knowledge/user-profile.md(name, role, business, goals)knowledge/preferences.md(verbosity, tone, emoji, language)knowledge/projects.md(anything they're working on)
3. Hatch their first employee (centerpiece)
Propose ONE tailored hire based on what they told you — name, role, emoji, department — and ask if they like it or want changes. On agreement, really create it using the management skill (write the employee YAML under org/<department>/<name>.yaml). Then scaffold a starter skill for that hire using the skill-creator skill (a small, relevant playbook) and reference it in the new employee's persona. Confirm: "Done — {{newEmployee}} is now part of your team."
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 · 42 lines · 48 tokens per session scan A 1edaa2d0032b
onboarding is a skill published in the GitHub repository hristo2612/jinn (315 stars, last pushed 2d ago), licensed MIT. It adds 48 tokens to every session and 906 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…