onboarding

onboarding is a skill for Claude Code, Codex from Aicoo-Team/AICOO-Skills. It costs 119 tokens per session (4,337 once invoked), scanned C, original, MIT.

A guided first-time setup for Aicoo that signs a user in, builds agent memory from local context, creates sharing options, and helps invite teammates.

In plain words
What is it for?
Use it to connect Aicoo, teach the agent about a person or team, share the agent, create a team knowledge base, invite coworkers, or discover agents.
Why use it?
It gives a new user a path from an empty setup to an agent that knows relevant information and can be shared.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also reads ~/.codex or $CODEX_HOME. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

Part of the Aicoo Agent Skills plugin — 21 skills shipped together

Good fit Use it to connect Aicoo, teach the agent about a person or team, share the agent, create a team knowledge base, invite coworkers, or discover agents.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aicoo-team/aicoo-skills/onboarding
Install

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.

Any agent
npx skills add Aicoo-Team/AICOO-Skills --skill onboarding
Clone the repo
git clone --depth 1 https://github.com/Aicoo-Team/AICOO-Skills

Made for: Claude Code, Codex.

Or install Aicoo Agent Skills, the plugin that ships this one along with the rest of its 21 skills.

Wrote 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.

agentmods badge for onboarding

README.md
[![agentmods](https://agentmods.dev/badge/skills/aicoo-team/aicoo-skills/onboarding/github.svg)](https://agentmods.dev/skills/aicoo-team/aicoo-skills/onboarding)
Your own site
<a href="https://agentmods.dev/skills/aicoo-team/aicoo-skills/onboarding"><img src="https://agentmods.dev/badge/skills/aicoo-team/aicoo-skills/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.

agentmods 80×15 button for onboarding

Your own site · 80×15
<a href="https://agentmods.dev/skills/aicoo-team/aicoo-skills/onboarding"><img src="https://agentmods.dev/badge/skills/aicoo-team/aicoo-skills/onboarding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 119 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,337 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 3 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00119 $0.04337
Opus 5 $0.00060 $0.02168
Sonnet 5 $0.00024 $0.00867
Haiku 4.5 $0.00012 $0.00434

Measured 12d ago against content hash 5f3a836e7455, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade C, and why

onboarding scanned grade C with 3 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 12d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

`~/.aicoo/credentials.json` (chmod 600), granting the `os.*` scopes (notes,

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

LOGIN="$(find ~/.claude/plugins ~/.codex ~/.config/skills ~/.local/share ~ \

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -X POST "https://www.aicoo.io/api/v1/init" \
skills/onboarding/SKILL.md · 381 lines

How it starts

The opening of the file, as written. The whole thing — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Onboarding — From Zero to a Shareable Agent

Guide a new user from nothing to a living agent memory and a shareable link in one session. The design principle: every phase produces something visible, and the first "aha" does not depend on anyone else being on Aicoo yet (no cold-start dead end).

There are two tracks. Detect which one fits, then follow it. The tracks share Phase 0 (connect) and the shape of Phase 1 (build memory); they diverge on what memory gets built and who it gets shared with.

Phase 0  CONNECT      Sign in with Aicoo + detect track (personal / team)
   ↓
Phase 1  BUILD MEMORY Scan local context → synthesize → write agent memory   ← core aha
   ↓
Phase 2  SHARE        Personal: share your agent link
                      Team:     build a knowledge base folder + share it
   ↓
Phase 3  INVITE       (team) Invite teammates — copy-paste prompt AND link
   ↓
Phase 4  KEEP GOING   check-messages / daily-brief → heartbeat; (personal) discover on Square

Phase 0: CONNECT — Sign in + detect track

0a. Sign in with Aicoo (OAuth) — DO THIS, don't send the user to a website

This is a one-click OAuth flow. You run a script; the user clicks Approve in the browser. Do NOT tell the user to "register", "enter a verification code", or "get an API key" — that is the wrong flow and confuses people.

If ~/.aicoo/credentials.json already exists, skip to 0b. Otherwise:

Step 1 — locate the login script. It ships inside this skill pack, in the scripts/ directory next to the skills/ directory that contains this file. Resolve its absolute path. If you're unsure where the pack is installed, find it:

LOGIN="$(find ~/.claude/plugins ~/.codex ~/.config/skills ~/.local/share ~ \
  -maxdepth 8 -name aicoo-login.mjs -path '*aicoo-skills*' 2>/dev/null | head -1)"
echo "$LOGIN"   # e.g. ~/.claude/plugins/aicoo-skills/scripts/aicoo-login.mjs

Step 2 — run it (it auto-opens the browser and blocks until the user finishes; just run it and wait):

Read the full file on GitHub · 381 lines

Files

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.

Changes

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.

  1. 12d ago First seen · 381 lines · 119 tokens per session scan C 5f3a836e7455

Subscribe to this mod's changes

onboarding is a skill published in the GitHub repository Aicoo-Team/AICOO-Skills (35 stars, last pushed 1mo ago), licensed MIT. It adds 119 tokens to every session and 4,337 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 3 findings (asks for root, reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories