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 peters/horizon --skill horizon-notifygit clone --depth 1 https://github.com/peters/horizonWrote 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/peters/horizon/horizon-notify)<a href="https://agentmods.dev/skills/peters/horizon/horizon-notify"><img src="https://agentmods.dev/badge/skills/peters/horizon/horizon-notify/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/peters/horizon/horizon-notify"><img src="https://agentmods.dev/badge/skills/peters/horizon/horizon-notify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00031 | $0.00355 |
| Opus 5 | $0.00015 | $0.00178 |
| Sonnet 5 | $0.00006 | $0.00071 |
| Haiku 4.5 | $0.00003 | $0.00036 |
Grade A, and why
horizon-notify scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
You are running inside Horizon, a GPU-accelerated terminal workspace. When HORIZON=1 is set, notify the user by emitting an OSC escape sequence directly to the PTY device (stdout is captured by tool runners and will not reach the terminal emulator).
Use this command (works on Linux and macOS):
printf '\033]0;HORIZON_NOTIFY:%s:%s\007' "" "" > "/dev/$(ps -o tty= -p $PPID | tr -d ' ')"
Severities: info, done, attention Keep messages under 80 chars.
Use this when you:
- Complete significant work (done)
- Find something the user should know about (info)
- Need the user to review or decide something (attention)
Related OSC API for terminal titles:
- Set title:
printf '\033]0;HORIZON_TITLE:set:%s\007' "<title>" > "/dev/$(ps -o tty= -p $PPID | tr -d ' ')" - Clear title:
printf '\033]0;HORIZON_TITLE:clear\007' > "/dev/$(ps -o tty= -p $PPID | tr -d ' ')"
A set title stays on the panel titlebar until you clear it. Later OSC 0 titles from the TUI (cwd, spinner, status) do not overwrite it.
Keep titles under 80 chars and avoid newlines.
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.
- 4d ago Changed · +3 lines a5aa2cd1d154
- 10d ago First seen · 32 lines · 31 tokens per session scan A f90a828a2d7c
horizon-notify is a skill published in the GitHub repository peters/horizon (704 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 355 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
recall
Use Recall to search, inspect, continue, export, resume, or share indexed AI coding sessions. Trigger for project-history lookup, recent work from other agents, file history, unfinished-session continuation, and published session-page management.
reflect
Use Recall Reflect to review AI coding workflow history as a conversation-first timeline and discuss observed patterns before changing behavior. Trigger when the user asks to reflect on a project, review AI coding workflow, inspect workflow friction, discuss repeated corrections, review handoffs, or explore possible…
rust-patterns
Rust patterns covering ownership, lifetimes, error handling, traits, async with Tokio, and smart pointers. Activate when writing or reviewing Rust.
rust-engineering
Comprehensive Rust engineering guidance for coding agents. Use when writing, reviewing, refactoring, or debugging Rust code; designing crate APIs; resolving ownership, borrowing, lifetime, or trait issues; implementing async/concurrent code with Tokio; improving error handling, testing, performance, memory layout, or…
rust
You are working on a Rust project. Apply these conventions.
rtl-aware-development
OpenCode Desktop should be RTL-aware. Use when implementing or reviewing RTL/LTR behavior in the web app, desktop app, CSS, menus, scrolling, resizing, icons, mixed-direction text, or Electron title bars.