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-castgit 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-cast)<a href="https://agentmods.dev/skills/peters/horizon/horizon-cast"><img src="https://agentmods.dev/badge/skills/peters/horizon/horizon-cast/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-cast"><img src="https://agentmods.dev/badge/skills/peters/horizon/horizon-cast.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 | $0.00043 | $0.00184 |
| Opus 5.5 | $0.00017 | $0.00074 |
| Sonnet 5.5 | $0.00009 | $0.00037 |
| Haiku 4.5 | $0.00004 | $0.00018 |
Grade A, and why
horizon-cast 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 8d 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
Horizon casting
Use the public cast tool on the Horizon browser MCP server (--browser-mcp).
The calling agent must run in a Horizon workspace on Linux.
Read the casting reference before receiver or session operations.
Use the current tool schema for arguments. If the tool or supporting host is absent,
report the missing capability. Do not use private runtime files or another capture path.
A task to examine casting does not authorize a cast to a real TV. Start, pair, stop, or forget only within the user's requested receiver and task. Application capture needs the person's permission in the Cast picker. An agent cannot grant that permission.
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.
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.
- 8d ago First seen · 18 lines · 43 tokens per session scan A cab8002e971d
horizon-cast is a skill published in the GitHub repository peters/horizon (717 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 184 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-09.
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.
meta-compile
A generator for 1C configuration objects, such as directories, documents, registers, reports, and shared modules, from a JSON definition.
cfe-patch-method
A code-file generator for intercepting a method in a 1C configuration extension. A method interceptor adds code before, after, or instead of the original method.
db-load-cf
A command that imports a binary `.cf` configuration file into a 1C information database. The import replaces the database’s existing configuration.