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 slaveOftime/open-relay --skill oly-appsgit clone --depth 1 https://github.com/slaveOftime/open-relayWrote 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/slaveoftime/open-relay/oly-apps)<a href="https://agentmods.dev/skills/slaveoftime/open-relay/oly-apps"><img src="https://agentmods.dev/badge/skills/slaveoftime/open-relay/oly-apps/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/slaveoftime/open-relay/oly-apps"><img src="https://agentmods.dev/badge/skills/slaveoftime/open-relay/oly-apps.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00032 | $0.00887 |
| Opus 5.5 | $0.00013 | $0.00355 |
| Sonnet 5.5 | $0.00006 | $0.00177 |
| Haiku 4.5 | $0.00003 | $0.00089 |
Grade A, and why
oly-apps 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Publish a web app through oly
1) Locate state and enable trusted apps
- Run
oly daemon statusto getROOT(<STATE_DIR>) and the liveHTTPendpoint (HTTP must be enabled). - Apps live at
<ROOT>/wwwroot/apps/<app-name>/and are served athttp://127.0.0.1:<PORT>/apps/<app-name>/behind the daemon's HTTP authentication. - Custom apps, proxies, and
wwwrootoverrides are disabled by default. With operator authorization, set flat"trusted_apps_enabled": truein<ROOT>/config.jsonand confirm hot reload. - Security boundary: App routes share the control-plane origin and allow inline scripts. Only publish reviewed, trusted code — never untrusted output.
2) Choose an app mode
Static HTML (no manifest needed)
Create <ROOT>/wwwroot/apps/<app-name>/index.html and relative assets (./ or /apps/<app-name>/). Discovery uses the HTML <title>.
Static app / SPA (oly.app.json)
Create <ROOT>/wwwroot/apps/<app-name>/oly.app.json:
{
"title": "My App",
"app_type": "spa",
"entry": "index.html",
"redirect_files": ["index.html"]
}
app_type: "spa"is a display hint only; use hash routing or"redirect_files": ["index.html"]for history-route fallback (prefer/apps/<app-name>/asset paths so deep links resolve assets cleanly).- Every path in
redirect_filesmust already exist on disk or the manifest is rejected. - Local app files support GET/HEAD and always use
private, no-cachewith content-based ETags, even for hash-shaped filenames. Conditional requests still require auth. Other static methods return 405; proxies keep their own method/cache behavior. The built-in PWA does not runtime-cache apps. - Keep app assets under
/apps/<app-name>/; do not replace generated UI bundle URLs with mutable files, since a browser may already have an immutable copy.
Loopback service proxy (oly.app.json)
{
"title": "Local dashboard",
"app_type": "spa",
"entry": "http://127.0.0.1:5173/"
}
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 · +6 lines 84465f145b20
- 2d ago Changed · -33 lines 7da44fde765d
- 5d ago Changed · +40 lines · +11 tokens per session 211946e2f76e
- 1mo ago First seen · 59 lines · 21 tokens per session scan A 2243aee3b71f
oly-apps is a skill published in the GitHub repository slaveOftime/open-relay (95 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 887 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
mcp-builder
Design, build, configure, or debug Model Context Protocol servers for codewhale, including stdio and HTTP/SSE transports.
scaffold-project
Scaffold a new app, API, backend, fullstack project, mobile app, polyglot service, monorepo, or starter with Better Fullstack. Use when the user wants to create, start, bootstrap, initialize, or generate a project from a stack description. Prefer the bundled Better Fullstack MCP server: guidance, schema…
tui-explorer
Discover and replay terminal UI paths using agent-tui. Use when you need to launch a TUI app, explore navigation with bounded BFS, generate markdown acceptance tests, and verify those tests repeatedly. Do not use for web or desktop GUI automation.
api-request
Send HTTP API requests using curl. Use when the user asks to call an API, fetch data from a URL, send POST/PUT/PATCH/DELETE requests, work with REST or GraphQL endpoints, upload files, authenticate with Bearer tokens or API keys, debug HTTP responses, or interact with any web service via HTTP.
agent-tui
Automate terminal UI (TUI) apps with agent-tui for testing, inspection, demos, and scripted interactions. Use when automating CLI/TUI flows, regression testing terminal apps, verifying interactive behavior, or extracting structured text from terminal UIs. Also use when asked what agent-tui is, how it works, or to demo…
domain-cloud-native
A set of guidance for building cloud-native applications, which run as services in containers or cloud environments.