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 obto-inc/platform --skill obto-mcp-extendgit clone --depth 1 https://github.com/obto-inc/platformWrote 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/obto-inc/platform/obto-mcp-extend)<a href="https://agentmods.dev/skills/obto-inc/platform/obto-mcp-extend"><img src="https://agentmods.dev/badge/skills/obto-inc/platform/obto-mcp-extend/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/obto-inc/platform/obto-mcp-extend"><img src="https://agentmods.dev/badge/skills/obto-inc/platform/obto-mcp-extend.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 | $0.00110 | $0.01066 |
| Opus 5 | $0.00055 | $0.00533 |
| Sonnet 5 | $0.00022 | $0.00213 |
| Haiku 4.5 | $0.00011 | $0.00107 |
Grade A, and why
obto-mcp-extend scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Extending the OBTO MCP surface (per-tenant tools, resources, prompts)
The OBTO MCP server is itself extensible from inside a session: the triad CRUD tools — obto_{create,update,delete,list}_mcp_{tool,resource,prompt} — register per-domain dynamic tools, markdown resources, and prompt templates that the server then serves alongside its built-ins to every session in that domain. This is how a tenant grows its own MCP surface without touching server code.
All triad calls are domain-scoped: they require domain (from obto_whoami) but no appName. Regular users target their own domain; super-users may target any tenant. Exposure follows domain inclusion — an artifact registered at domain X is visible to sessions whose domain resolves to X (or to global/a parent).
Dynamic tools (obto_create_mcp_tool)
- Name: lowercase, underscores only (
^[a-z][a-z0-9_]*$, ≤50 chars), unique per domain. It becomes available to all sessions in the domain. zodSchemaString: the input schema as a Zod v4 string, e.g.z.object({query: z.string()}). Zod v4 trap:z.record(valueSchema)with one argument crashes tool listing for the whole domain — always write the two-argument form,z.record(z.string(), valueSchema).handlerFunction: a JavaScript function expression, not a bare statement body — write itasyncso you canawait:async (args) => { const rows = await ...; return { content: [{ type: 'text', text: JSON.stringify(rows) }] }; }argsis the validated input. The handler compiles in a vm sandbox and runs wrapped in a timeout + structured envelope (dynamic_tool_failed), so a broken handler fails loudly per-call instead of taking the session down.- Never save an empty or stub handler. A record whose
handlerFunctionis blank fails to compile at every session init — a dead tool that error-logs forever. If a tool isn't ready, setisActive: falseor delete it. - Annotations are required and reviewed:
readOnlyHint,destructiveHint,openWorldHint(booleans,idempotentHintoptional) plusannotationJustifications— a short written justification for each. Set them truthfully; they drive client-side confirmation behavior.
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.
- 10d ago First seen · 50 lines · 110 tokens per session scan A 38882b4a59e5
obto-mcp-extend is a skill published in the GitHub repository obto-inc/platform (1 stars, last pushed 4d ago), licensed Apache-2.0. It adds 110 tokens to every session and 1,066 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
specflow-use
To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.
ue-mcp-epic-routing
Use when deciding between ue-mcp's native category actions and Epic's wrapped ToolsetRegistry tools (the epic actions, incl. the Blueprint graph DSL) for a task in Unreal. Pulls in when authoring Blueprint graph bodies, or any time both a native action and an epic action could do the job and you need to pick.
mcp-google-map-project
Project knowledge for developing and maintaining @cablate/mcp-google-map. Architecture, Google Maps API guide, GIS domain knowledge, and design decisions. Read this skill to onboard onto the project or make informed development decisions.
frontmcp-setup
Use when starting, scaffolding, or organizing a FrontMCP project. Covers creating a new project (CLI scaffold or manual) for Node, Vercel, and other targets; standalone versus Nx-monorepo layout, naming conventions, generators, and dependency rules; composing multiple @App classes, ESM packages, and remote MCP servers…