yo

A notification skill that sends a content-free “Yo” alert to your phone when a task finishes, needs your input, or hits an error requiring review.

In plain words
What is it for?
Use it to pair the agent with Yo and send phone alerts for completed tasks, blocked work, or errors that need human attention.
Why use it?
It lets you notice important agent events without watching the task continuously. The alert carries no message, but it can open an optional link when tapped.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/alfongj-com/yo-plugin/yo
Any agent
npx skills add alfongj-com/yo-plugin --skill yo
Clone the repo
git clone --depth 1 https://github.com/alfongj-com/yo-plugin

Made for: Claude Code, Codex.

Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,175 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00085 $0.01175
Opus 5 $0.00043 $0.00588
Sonnet 5 $0.00017 $0.00235
Haiku 4.5 $0.00009 $0.00118

Measured yesterday against content hash 01f8ced70f9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

yo 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 yesterday.

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.

curl -X POST https://getyo.dev/api/yo \
skills/yo/SKILL.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Yo — push-notify your owner

Yo sends your owner a content-free push notification: "Yo 👉 from your-name". The sender identity plus the moment of the ping IS the message. There is no message body — the only optional payload is a context_url the notification tap-through opens.

  • MCP server (Streamable HTTP): https://getyo.dev/mcp
  • REST fallback: POST https://getyo.dev/api/yo

Setup: credential discovery

  1. Check for an existing key first (Path B). Look for a YO_API_KEY environment variable or platform secret. Keys look like yo_<10>_<10>_<32>. If present, skip registration entirely — use it as the Bearer token.
  2. No key and MCP is available? Self-register (Path A):
    1. Call the register_agent MCP tool with a sensible proposed_name derived from your role/context (e.g. the repo name, or platform + project: "devin-home-repo", "cursor-yo-app"). Optionally pass description and platform.
    2. Present the returned pairing_url to the user verbatim and complete, including the #… part — that fragment is the secret that authorizes approval, so a truncated link cannot be approved. Tell the user to open the whole link (the bare pairing_code is only a reference, it approves nothing). Keep the returned claim_token secret — never show it to the user or write it anywhere; it is what authorizes you (and only you) to receive the API key and to cancel the pairing.
    3. Poll the check_registration MCP tool with the pairing code and the claim_token, following the returned poll_hint (every 5 s for the first 2 minutes, then every 30 s; codes expire after 15 minutes — the key pickup does too, so keep polling until you have the key).
    4. On approved, the response includes api_key exactly once. Store it immediately in your platform's native secret mechanism (e.g. a YO_API_KEY secret/env var) and tell the user where it is stored. If you lose it, you must re-register.
    5. The same response includes paired_with, the Yo account that approved. Always tell the user which account you are now connected to, e.g. "Connected to Yo account [email protected]." If that is not their account, someone else approved your pairing: call cancel_registration with the pairing code and claim_token (this revokes the connection and the key), discard the key, and start over with a fresh register_agent. If you only notice later and cancel_registration returns invalid, call revoke_self (Bearer-authenticated with the API key, confirm: true) — it permanently revokes the key at any time.
  3. No key and interactive pairing is impossible (stateless platform, no MCP): ask the user to open the Yo app (https://getyo.dev/app), tap + Add agent, and give you the key as a YO_API_KEY secret/env var.

Read the full file on GitHub · 47 lines

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. yesterday First seen · 47 lines · 85 tokens per session scan A 01f8ced70f9b

Subscribe to this mod's changes

yo is a skill published in the GitHub repository alfongj-com/yo-plugin (0 stars, last pushed 23d ago), licensed MIT. It adds 85 tokens to every session and 1,175 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens