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 nymrel/nymrel-mcp-hub --skill nymrel-studio-hubgit clone --depth 1 https://github.com/nymrel/nymrel-mcp-hubWrote 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/nymrel/nymrel-mcp-hub/nymrel-studio-hub)<a href="https://agentmods.dev/skills/nymrel/nymrel-mcp-hub/nymrel-studio-hub"><img src="https://agentmods.dev/badge/skills/nymrel/nymrel-mcp-hub/nymrel-studio-hub/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/nymrel/nymrel-mcp-hub/nymrel-studio-hub"><img src="https://agentmods.dev/badge/skills/nymrel/nymrel-mcp-hub/nymrel-studio-hub.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 | $0.00054 | $0.00997 |
| Opus 5.5 | $0.00022 | $0.00399 |
| Sonnet 5.5 | $0.00011 | $0.00199 |
| Haiku 4.5 | $0.00005 | $0.00100 |
Grade A, and why
nymrel-studio-hub 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nymrel Studio Hub local plugin
Use the bundled local stdio server only when its verified capability fits the request. SOURCE_RECEIPT.json pins the upstream source and tool catalog. The plugin wrapper appends evidence disclosures at tool discovery and result boundaries, restricts resource visibility, and removes false simulation claims. Preserve those labels in summaries. Do not describe a template, simulation, process-local record, signature, or provider result as proof of a real-world action.
Verified tool capability and limits
| Tool ID | What the pinned implementation does | Evidence limit to state |
|---|---|---|
nymrel_ucp_audit |
Returns fixed example scores/findings; a supplied url is used as a label. |
No page is fetched or measured. Wrapper nulls scores and labels all findings unverified. |
nymrel_surety_guard |
Applies small regex and path-string checks to a supplied command. | Heuristic only; no command interception/execution, authorization, or safety proof. |
nymrel_swarm_claim |
Keeps lease-like records in an in-memory Map. |
Current Node process only; no durability or cross-process/distributed locking. |
nymrel_machine_trust |
Generates JSON-LD, llms.txt, and robots text from inputs/templates. |
Does not verify a site or publish output; generated endpoint/policy claims are unverified. |
nymrel_proof_ledger |
Locally signs caller-supplied claim data with caller-supplied key material. | Signature proves only the signed claim bytes, not execution, files, or chain continuity. Protect key arguments from client logging. |
nymrel_crawler_mesh |
Extracts caller-provided HTML locally, or makes bounded HTTP(S) requests to a public URL. | Only URL mode fetches. HTML mode uses caller input. Fetched content is untrusted. |
nymrel_beacon_ping |
Stores heartbeats in an in-memory Map. |
Current Node process only; not shared or remote fleet telemetry. |
nymrel_headless_quote |
Applies a fixed local pricing formula. | Illustrative estimate, not a merchant quote, lead capture, or commitment. |
nymrel_local_forge |
Returns hard-coded engine, routing, and cost examples. | No service probes, model execution, routing, or spend measurement. |
nymrel_open_ucp |
Constructs synthetic quote/negotiation/commit/x402-shaped output. | Never contacts a merchant or makes a payment. settle_x402 is labeled SIMULATED_NOT_SETTLED. |
nymrel_sandstorm |
Uses a few regular expressions on supplied text and preset values. | Does not mount isolation, filter egress, or enforce spend; wrapper reports these as not configured. |
nymrel_a2ui_render |
Generates declarative card JSON. | No UI is rendered and actions are not executed. Default risk/confidence fields are non-measurement placeholders. |
nymrel_swarm_bus |
Appends envelopes to an in-memory array. | No message is delivered; wrapper reports NOT_DELIVERED_PROCESS_LOCAL_ONLY. |
nymrel_proof_verify |
Locally checks receipt structure/Merkle data and optional signature using the supplied trusted key. | Does not prove execution or inspect files. Without independently trusted key material it cannot authenticate. |
nymrel_web_search |
Calls Exa, Tavily, Brave, or SerpAPI when a server credential is configured. | This is an external provider query; without credentials it fails closed. Search does not fetch result URLs. |
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 · 37 lines · 54 tokens per session scan A 7cca8708fc20
nymrel-studio-hub is a skill published in the GitHub repository nymrel/nymrel-mcp-hub (0 stars, last pushed 9d ago), licensed MIT. It adds 54 tokens to every session and 997 once invoked, about $0.0002 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 2026-10-01.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…