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 agentmods add skills/xhostd/xhost-sdk/xhostnpx skills add xhostd/xhost-sdk --skill xhostgit clone --depth 1 https://github.com/xhostd/xhost-sdkWrote 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/xhostd/xhost-sdk/xhost)<a href="https://agentmods.dev/skills/xhostd/xhost-sdk/xhost"><img src="https://agentmods.dev/badge/skills/xhostd/xhost-sdk/xhost.svg" alt="Measured on agentmods" 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 | $0.00091 | $0.10619 |
| Opus 5 | $0.00046 | $0.05310 |
| Sonnet 5 | $0.00018 | $0.02124 |
| Haiku 4.5 | $0.00009 | $0.01062 |
Grade A, and why
xhost scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `download_channel_snapshot` — Download DB Snapshot: mint a short-lived, read-scoped token and return a `curl` command that downloads a snapshot's `.sqlc` archive. The `snapshot_id` is a `list_channel_snapshots` row (an How it starts
The opening of the file, as written. The whole thing — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
xhostd — Agent-First Hosting
xhostd is hosting designed for agents. You create an app, push its code to the git repo the app owns, and deploy it. Every app gets a production HTTPS URL; named channels give preview URLs. The same remote MCP tools are available on Claude Code, claude.ai, Codex, and other OAuth-capable clients. The procedure below is identical across clients — except that a runtime with no shell has no git, and there the commit_files fallback stands in for the push. Tool names are client-specific: examples below use mcp__xhost__<name> as a Claude-style spelling; use the actual names exposed by your runtime.
Authentication
Tools are already authenticated via OAuth — the plugin (Claude Code) and the connector (claude.ai) both handle this. Just call the tools.
If a tool reports unauthenticated:
- Claude Code: tell the user to run
/mcp, select xhost, choose Authenticate. A browser opens, they sign in with Google (picking a username on first sign-in), approve, done. - Codex: refresh or reconnect the xhost plugin/MCP connection, then retry the first tool call. The browser-based Google OAuth flow should open automatically; no token is needed.
- claude.ai: tell the user to reconnect the xhost connector in Settings → Connectors.
There is no API token to mint, copy, paste, or export. Do not ask the user for one.
If a tool listed in this skill or in llms-full.txt is missing from your runtime tool list, the client cached an older tool set at connect time. llms-full.txt is the source of truth — tell the user to reconnect (Claude Code: /mcp → xhost → reconnect; claude.ai: Settings → Connectors → reconnect xhost) to pick up the current tools.
Claude Code may expose this workflow as /xhost; Codex and other clients may not support slash commands. In those clients, describe the task normally or mention the xhost skill.
Write safety
Creating or deleting apps, pushing code, deploying, rewinding, changing environment variables, restoring databases, changing domains, and exposing ports are write operations. Perform them when the user explicitly requests the operation and target; when the target or production impact is ambiguous, ask before acting. Prefer a preview channel when the user asks to preview or test a change, and never expose a port or restore production data without explicit user direction.
What ships with it
16 files 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.
- references/api-reference.md 52 KB
- references/getting-started.md 13 KB
- references/guide-bkm.md 24 KB
- references/guide-diagnose-slowness.md 8.5 KB
- references/guide-git.md 10 KB
- references/guide-index.md 4.7 KB
- references/guide-recipes-app-node.md 14 KB
- references/guide-recipes-app-python.md 13 KB
- references/guide-recipes-blob.md 32 KB
- references/guide-recipes-commit-files.md 17 KB
- references/guide-recipes-docker.md 24 KB
- references/guide-recipes-oauth.md 25 KB
- references/guide-recipes-port-forwarding.md 33 KB
- references/guide-recipes-postgres.md 22 KB
- references/guide-recipes-static.md 11 KB
- references/guide-recipes-worker.md 25 KB
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 First seen · 306 lines · 91 tokens per session scan A 3ab3ea1bfd4f
xhost is a skill published in the GitHub repository xhostd/xhost-sdk (0 stars, last pushed 5d ago), licensed MIT. It adds 91 tokens to every session and 10,619 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
huggingface-spaces
Build, deploy, and maintain applications on Hugging Face Spaces — Gradio / Docker / Static SDKs, ZeroGPU and dedicated hardware, model loading, debugging, buckets, inference providers, community grants. Use whenever the user asks to create or host an app on Hugging Face, port code onto ZeroGPU, fix a Space that won't…
ondb
A logical analysis and reasoning tool for AI. Use when decomposing documents into structured knowledge, querying entities and relations, validating consistency, or indexing files. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", "analyze this document", entity CRUD, or cross-skill…
kagent-dev
Development guide for kagent's v1alpha3 Harness and AgentTemplate CRDs, AgentInstance gRPC control plane, upstream A2A integration, Substrate runtime provisioning, tests, generation, and PR workflow. Use for any implementation, debugging, review, or CI task in the kagent repository.
timoni
Use when deploying applications to Kubernetes with Timoni. Covers installing and upgrading module instances from OCI registries, composing multi-app deployments with bundles, injecting values from clusters or CI with runtimes, targeting multiple clusters, and authoring, testing, signing and publishing modules with CUE.
azmon-mirroredcatalogs-operations-cli
Brings Azure Monitor, Application Insights, and Log Analytics telemetry into Fabric as Eventhouse external delta tables and correlates it with business data. Use to onboard observability data, judge whether latency or availability affected revenue, or build a Real-Time dashboard and Operations Agent over it.
durable-objects
Create and review Cloudflare Durable Objects. Use when building stateful coordination (chat rooms, multiplayer games, booking systems), implementing RPC methods, SQLite storage, alarms, WebSockets, or reviewing DO code for best practices. Covers Workers integration, wrangler config, and testing with Vitest. Biases…