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 SlashyIsTaken/fp-pluginplaza --skill fp-yoohoogit clone --depth 1 https://github.com/SlashyIsTaken/fp-pluginplazaWrote 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/slashyistaken/fp-pluginplaza/fp-yoohoo)<a href="https://agentmods.dev/skills/slashyistaken/fp-pluginplaza/fp-yoohoo"><img src="https://agentmods.dev/badge/skills/slashyistaken/fp-pluginplaza/fp-yoohoo/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/slashyistaken/fp-pluginplaza/fp-yoohoo"><img src="https://agentmods.dev/badge/skills/slashyistaken/fp-pluginplaza/fp-yoohoo.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 | $0.00161 | $0.01570 |
| Opus 5 | $0.00081 | $0.00785 |
| Sonnet 5 | $0.00032 | $0.00314 |
| Haiku 4.5 | $0.00016 | $0.00157 |
Grade A, and why
fp-yoohoo 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 11d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fp-yoohoo — the terminal comes to you
fp-yoohoo is the only plugin in the plaza that changes nothing about how you think or write. It injects no prior, reads no transcript, and tags no claims. It is pure mechanism, and it does one thing. When Claude Code stops to ask the user something, the terminal window comes to the front, so a waiting session cannot be missed and the user never has to remember to check back.
You have no behavior to follow here. If this skill loaded, the user is asking about the plugin, not asking you to act differently. Answer from the reference below and get out of the way.
What sets it off
fp-yoohoo subscribes to the Notification hook, filtered by notification type.
| Type | Meaning | On by default |
|---|---|---|
permission_prompt |
a tool call needs approval | yes |
elicitation_dialog |
a question or plan dialog is open | yes |
agent_needs_input |
an agent is blocked on the user | yes |
idle_prompt |
the prompt has sat idle for 60 seconds | no, opt in |
Turn end (the Stop hook) is deliberately not wired up. It fires after every
single reply, which would raise the window dozens of times an hour and teach the
user to ignore it.
How the raise happens
The hook runs as a grandchild of the terminal emulator, so it walks the parent chain until it meets one (Konsole, kitty, Alacritty, WezTerm, Ghostty, foot, Windows Terminal and friends). That pid is what a window gets matched on.
Backends are tried in order, and the first one whose desktop is present wins:
- KDE Plasma, Wayland or X11, through a temporary KWin script loaded over D-Bus. Wayland forbids a client from raising itself, so the compositor is asked to do it instead. No extra packages are needed.
- Hyprland and sway, through
hyprctlorswaymsg. - X11, through
wmctrlorxdotool. - macOS, through System Events, fronting the app by its unix id.
- Windows, through
SetForegroundWindow, falling back to flashing the taskbar entry when the OS refuses a background focus change.
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.
- 11d ago First seen · 138 lines · 161 tokens per session scan A ac1c35a26cb2
fp-yoohoo is a skill published in the GitHub repository SlashyIsTaken/fp-pluginplaza (2 stars, last pushed 1mo ago), licensed MIT. It adds 161 tokens to every session and 1,570 once invoked, about $0.0008 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
cco-budget
Configure token budget limits, auto-compact settings, and view current budget status (model-aware — Claude 5 lineup, Opus 5 default fallback, full 1M context at standard price).
cco-clean
Clean up old tracking data and reset statistics.
gws-quick-ref
Quick reference for gws CLI syntax — core patterns, key flags, pagination, field masks, and output formats.
gws-events-subscribe
Google Workspace Events: Subscribe to Workspace events and stream them as NDJSON.
gws-gmail-forward
Gmail: Forward a message to new recipients.
recipe-block-focus-time
Create recurring focus time blocks on Google Calendar to protect deep work hours.