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-cloudgit 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-cloud)<a href="https://agentmods.dev/skills/peters/horizon/horizon-cloud"><img src="https://agentmods.dev/badge/skills/peters/horizon/horizon-cloud/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-cloud"><img src="https://agentmods.dev/badge/skills/peters/horizon/horizon-cloud.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 | $0.00064 | $0.05216 |
| Opus 5.5 | $0.00026 | $0.02086 |
| Sonnet 5.5 | $0.00013 | $0.01043 |
| Haiku 4.5 | $0.00006 | $0.00522 |
Grade A, and why
horizon-cloud 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 today.
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 — 394 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Horizon cloud MCP
Use this skill for cloud offers, the cloud list of your workspace, Upkeep, companion workers,
a worker's Local Network Bridge, and GitHub access on a cloud worker.
Read the cloud reference for the server and operation you need.
Use tools from the connected server and their current schemas. Do not substitute
private Horizon state for MCP results. Cloud-list worker_image and
image_publication are retained metadata from the matching cloud runtime, or
null when unavailable or the image is unresolved. Registry publication includes
an opaque nonsecret grant ID, never a credential value or path. These fields do
not prove current registry access.
Hetzner offers include all current x86 types in permitted locations. The configured server types are fallback preferences; they do not restrict explicit worker choices.
Cloud cards show the last-read tailnet device name under Connections > Tailnet.
Copy includes the MagicDNS domain when the worker reports it. A stable-name
fallback accepts horizon-tailnet-contract=2 or horizon-tailnet-contract=4;
it does not supply an unknown domain. Marker 2 qualifies this display fallback
only; selected-tailnet operations require marker 4. Connect again to refresh
names after an administrator rename.
A selected tailnet requires horizon-tailnet-contract=4 and an auth key with
only tag:horizon-worker. The tailnet policy must define this tag in tagOwners.
The worker checks Self.Tags after enrollment and once at each resume.
An untagged node or a node with extra tags is refused and logged out.
There is no continuous tag monitoring or separate tag for each workspace.
The tailnet policy controls reachability. The quick-start pin contains marker 4;
selected-tailnet startup still requires storage that enforces private root modes.
The tested RunPod persistent storage does not and is unsupported. Never weaken
these checks; None does not bypass isolation. CPU evidence is not GPU qualification.
Personal API token and OAuth client bindings stay in the desktop OS store,
independently of enrollment auth keys. Stored presence reports kind only; it
does not prove API validity, scope or network access. Saving does not remove
nodes. Never pass an API secret to MCP or a worker.
Settings > Tailnets displays nonsecret API credential status and supplies masked
owner entry, replacement and removal. Saved values never fill a draft.
Read cloud_companions.tailnet_api_credentials for cached ready, pending or
unavailable status without Settings. The CLI is
cloud_deploy tailnets STATE_ROOT [TAILNET_ID]. API status does not qualify an
older worker image. Cached status is not an OS-store watcher; use Tailnets Refresh
for an explicit fresh read. Never pass an API secret to MCP.
Use tailnet_api_credential to request set_personal_token, set_oauth or remove
for an exact saved tailnet ID and caller-chosen UUID request ID. Set requests carry
kind metadata only; the person enters values and selects Save in Settings. The person fulfills
it in Settings > Tailnets; requests never open Settings or authorize a write.
Read status with the same IDs after a lost answer. cancel cancels only a pending
request; a running transaction remains uncertain until its result arrives.
Credentials are desktop-global, so a workspace agent cannot approve its own request.
Status qualification uses the production UI, actual CLI and normal AGENT public
MCP responses; baseline id/name evidence alone does not qualify API status.
Machine-local destination preference helpers retain a checkout/profile scope and nonsecret account or exact registry grant metadata. The launch engine retains that choice before image work. A saved preference is not proof of authentication or registry permission. Keep these settings outside repository files and use the shared transactional save helper to preserve other windows' choices.
Image publication credentials belong on the host. An operation preparation helper retains the authenticated provider account ID and owns a separate temporary Docker login. The engine retains its account and renews the operation login before push. Prebuilt profiles still require an explicit image; build profiles may omit it. Never copy publication credentials to a worker or repository.
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.
- today Changed · +291 lines 6842cd90185c
- yesterday Changed · +49 lines · +14 tokens per session 79e74a16b9e1
- 2d ago Changed · +18 lines dc98e2687787
- 3d ago Changed · +7 lines e5036474e0cc
- 5d ago Changed · +5 lines · +11 tokens per session b3a5d5b6c697
- 6d ago Changed · +4 lines · +10 tokens per session 2e205f42b54c
- 7d ago First seen · 20 lines · 29 tokens per session scan A 322ed99009d7
horizon-cloud is a skill published in the GitHub repository peters/horizon (717 stars, last pushed today), licensed MIT. It adds 64 tokens to every session and 5,216 once invoked, about $0.0003 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
web-info
A status checker for Apache, the web server, and databases published from 1C, a business-application platform.
web-publish
A setup tool that publishes a 1C database through Apache HTTP Server, making it available over the web.
web-stop
A command that stops the Apache HTTP Server used for 1C web publications.
azure-storage-blob-rust
Azure Blob Storage library for Rust. Upload, download, and manage blobs and containers. Triggers: "blob storage rust", "BlobClient rust", "upload blob rust", "download blob rust", "storage container rust", "BlobServiceClient rust".
hotpath_init_grafana
Build a Grafana dashboard JSON for a Rust project profiled with hotpath. Writes the dashboard file with context-aware panels (SQL and HTTP time per route, N+1 detection, memory and time per request, channel queues, lock contention, Tokio workers, per-thread CPU and allocations, profiling overhead) limited to what the…
kimaki-tunnel
Share a local dev server with the user through a public URL. Use when the user should open a localhost app in a browser, test a webhook or OAuth callback against a local server, or preview a dev server from Discord. Runs kimaki tunnel in a named background tuistory session. ALWAYS load before starting a dev server the…