Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/xiaotianfotos/homerailnpx agentmods add skills/xiaotianfotos/homerail/homerail-cliWrote 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/xiaotianfotos/homerail/homerail-cli)<a href="https://agentmods.dev/skills/xiaotianfotos/homerail/homerail-cli"><img src="https://agentmods.dev/badge/skills/xiaotianfotos/homerail/homerail-cli/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/xiaotianfotos/homerail/homerail-cli"><img src="https://agentmods.dev/badge/skills/xiaotianfotos/homerail/homerail-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 56 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00139 | $0.03384 |
| Opus 5 | $0.00069 | $0.01692 |
| Sonnet 5 | $0.00028 | $0.00677 |
| Haiku 4.5 | $0.00014 | $0.00338 |
Grade A, and why
homerail-cli scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 427 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HomeRail CLI (TypeScript)
Manager Agent native shell
The HomeRail Manager Agent can use the selected harness's native shell directly:
Codex provides its built-in shell and Claude Agent SDK provides Bash.
Prefer hr --json <command...> for structured results. If hr is not installed
on PATH, HomeRail exposes the active local-source entrypoint through
HOMERAIL_CLI_ENTRYPOINT; invoke it as:
node "$HOMERAIL_CLI_ENTRYPOINT" --json <command...>
A zero exit status plus the returned JSON is valid execution evidence. Dedicated Manager Tools remain useful shortcuts, but the CLI is the complete control surface for commands that have no dedicated Tool.
Installation
Before acting, apply homerail-shared rules. This pre-publication release uses the local source tree; do not assume npm publication exists.
cd homerail_cli
npm ci
npm run build
The CLI binary is dist/cli.js. Run it directly or via the hr bin alias:
# From the repo root after build
node homerail_cli/dist/cli.js --help
# Or link globally
cd homerail_cli && npm link
hr --help
For development without a build step:
npx tsx homerail_cli/src/cli.ts --help
Configuration
Use the CLI config flow for local runtime settings and provider credentials:
hr config
hr config show
hr config apply
hr config writes non-secret settings under ${HOMERAIL_HOME}/config.json.
Provider and integration credentials are sent to Manager and stored in the
Manager encrypted settings store, persisted under
${HOMERAIL_HOME}/manager/homerail.db. ${HOMERAIL_HOME}/secrets/env is a
legacy plaintext import path only; do not use it as the normal OSS
configuration path.
The Manager URL is resolved in this order:
--base-url <url>flag on any commandHOMERAIL_MANAGER_URLenvironment variable${HOMERAIL_HOME}/config.json- Default:
http://localhost:19191
The default Manager port is 19191. Override it with HOMERAIL_MANAGER_PORT for
local service startup, or use a full HOMERAIL_MANAGER_URL / --base-url when the
Manager is on another host or port.
The default Agent UI HTTPS port is 19192. Override it with HOMERAIL_UI_PORT or
ui.port in local config. The HTTP fallback port is 19193; override it with
HOMERAIL_UI_HTTP_PORT or ui.httpPort.
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.
- 13d ago First seen · 427 lines · 139 tokens per session scan A fc8d06c929a0
homerail-cli is a skill published in the GitHub repository xiaotianfotos/homerail (951 stars, last pushed today), licensed MIT. It adds 139 tokens to every session and 3,384 once invoked, about $0.0007 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…