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-devicegit 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-device)<a href="https://agentmods.dev/skills/peters/horizon/horizon-device"><img src="https://agentmods.dev/badge/skills/peters/horizon/horizon-device/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-device"><img src="https://agentmods.dev/badge/skills/peters/horizon/horizon-device.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 | $0.00059 | $0.03436 |
| Opus 5.5 | $0.00024 | $0.01374 |
| Sonnet 5.5 | $0.00012 | $0.00687 |
| Haiku 4.5 | $0.00006 | $0.00344 |
Grade A, and why
horizon-device 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 3d 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 — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Horizon native VNC and device control
Use this skill for Horizon VNC Device panels, simulators, and isolated native
application tests. Browser pages use the horizon-browser skill and browser_*
tools. Never drive a browser with device input.
Native VNC Device panel
Always observe interactive native tests live through a Horizon native VNC Device panel in the user's current workspace. Use a task-owned isolated desktop and private application state. Do not use noVNC or a browser viewer, or substitute screenshots or recordings for the live panel.
device_panel operations are create, list, inspect, screenshot,
video, visibility, reveal, reconnect, and close.
Use the public device_panel MCP tool for viewer lifecycle. Call
operation: "list" to discover panels in the caller's workspace. Create a
task-owned viewer with operation: "create" and the fixture's numeric loopback
endpoint (IP and nonzero port); retain its returned panel_id. This requires
a Horizon-launched agent and a supporting host. The tool does not provision a
desktop or forward input. The source checkout's scripts/device-smoke/README.md
describes the isolated fixture; launch it with --native-view and use its
vnc_address, not a browser URL.
A VNC server on another machine's loopback is reached with optional ssh in
create: { "host": "lab", "user": "deploy", "port": 2222 } (user and port
optional). endpoint is then the address as seen from that SSH host, typically
127.0.0.1:5900. Horizon runs ssh -W with its own SSH configuration and
keys, with strict host-key checking pinned regardless of ssh_config, so the
host must already be trusted in known_hosts (open it over SSH once); never
pass credentials, key paths or ssh options. Labels may only contain
letters, digits, ., _, - (and : in an IPv6 host), at most 253
characters for the host and 64 for the user, and are refused otherwise, so
nothing reaches ssh as an option or a shell fragment. Inspect and list report ssh for
tunnelled viewers, and connection_error carries ssh's last lines when the
tunnel fails.
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.
- 3d ago Changed · +2 lines ac377feb76ad
- 8d ago Changed · +45 lines dc0ab966fa67
- 10d ago Changed · +19 tokens per session 4569978b62e1
- 13d ago Changed · +6 lines 37b036f1b34e
- 19d ago Changed · +5 lines e8c838dd8df9
- 23d ago Changed · +47 lines 78005c5450e6
- 25d ago Changed · +8 lines 67fc927c189e
- 28d ago First seen · 144 lines · 40 tokens per session scan A ba0f4fbc76a4
horizon-device is a skill published in the GitHub repository peters/horizon (717 stars, last pushed today), licensed MIT. It adds 59 tokens to every session and 3,436 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 2026-09-19.
Other skills, from other repositories
cfe-validate
A checker for the structure of a 1C configuration extension (CFE). It examines the extension’s XML, settings, objects, and borrowed objects.
web-test
A browser-testing tool for 1C:Enterprise, an enterprise business software platform, using Playwright to automate the web client.
skd-validate
A validator for 1C Data Composition Schema files, which define how 1C business reports are structured and displayed. It checks the XML template for structural errors, broken references, and duplicate names.
subsystem-validate
A validator for the XML file that defines a 1C subsystem, or section of a 1C configuration.
ralph
Self-referential loop until task completion with configurable verification reviewer.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.