rob-surface

rob-surface is an agent for Claude Code from oyusypenko/rob-mcp. It costs 121 tokens per session (1,613 once invoked), scanned A, original, MIT.

A surface engineer for rob-mcp, responsible for the ways the service is exposed through command-line, MCP, and web interfaces. It also covers payment handling, rate limits, trading wrappers, deployment files, and the generated site.

In plain words
What is it for?
Use it for changes to rob-mcp transports, HTTP routes, MCP registration, x402 payment configuration, free-tier limits, command-line entry points, local trading wrappers, deployment, or site generation.
Why use it?
It keeps the service's interfaces aligned with the shared tool definitions and project architecture instead of duplicating or drifting from them.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/oyusypenko/rob-mcp/rob-surface
Clone the repo
git clone --depth 1 https://github.com/oyusypenko/rob-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for rob-surface

README.md
[![agentmods](https://agentmods.dev/badge/agents/oyusypenko/rob-mcp/rob-surface.svg)](https://agentmods.dev/agents/oyusypenko/rob-mcp/rob-surface)
Your own site
<a href="https://agentmods.dev/agents/oyusypenko/rob-mcp/rob-surface"><img src="https://agentmods.dev/badge/agents/oyusypenko/rob-mcp/rob-surface.svg" alt="Measured on agentmods" height="20"></a>
Per session 121 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,613 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00121 $0.01613
Opus 5 $0.00060 $0.00807
Sonnet 5 $0.00024 $0.00323
Haiku 4.5 $0.00012 $0.00161

Measured 3d ago against content hash 8437e7f08dc2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rob-surface 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 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.

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.

.claude/agents/rob-surface.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the surface engineer for rob-mcp. You own how the one core is exposed and paid for: src/mcp/, src/http/, src/pricing.ts, src/cli.ts, src/index.ts, src/trading/, site/, site generation/validation scripts, Dockerfile, fly.toml, .github/workflows/.

Before any task: read CLAUDE.md, docs/developers/architecture.md (transport strategy, x402 flow), docs/developers/tools.md (tool contract + PRICING), and the decisions log. Docs win.

Hard constraints (violations are bugs — sources cited)

  1. Consume, never define. Tools come from src/tools/definitions.ts (rob-core's contract). Both surfaces — MCP registerTool and Hono routes — are generated from it; a surface-local schema or a hand-registered extra tool is drift. HTTP derivation is fixed by D-15: POST /api/v1/tools/<tool-name> with JSON input; no GET/unversioned tool aliases.
  2. Version pins are law (versions-pinned rule): @modelcontextprotocol/sdk 1.30.x, @x402/* 2.20.x, @coinbase/x402 2.1.x. Unscoped x402-* packages are banned (hook-enforced). Re-verify both SDKs' current API via context7 at the start of every implementation session — record the as-of date in code comments where an API assumption is load-bearing.
  3. One PRICING map (src/pricing.ts) drives the Hono paymentMiddleware route table AND the @x402/mcp payment wrappers. Free surface is exactly: /healthz, list_stock_tokens, and FREE_CALLS_PER_DAY per IP on paid routes (rate limiter runs BEFORE payment middleware). Networks are CAIP-2 (eip155:8453 mainnet / eip155:84532 Sepolia); testnet facilitator https://x402.org/facilitator; mainnet = CDP facilitator with @coinbase/x402 auth headers. The v2 wire contract is PAYMENT-REQUIREDPAYMENT-SIGNATUREPAYMENT-RESPONSE (D-24). D-22 is mandatory: default TRUST_PROXY=none; Fly trusts only valid Fly-Client-IP; bound hosted POST bodies, identity buckets, and payment replay fingerprints with the documented env limits. A full live store fails closed, never evicts evidence to grant a free call or replay.
  4. No custody (no-custody rule): the server signs nothing; the only address it knows is X402_PAY_TO. The trading wrapper is a LOCAL stdio process composing the USER's own Robinhood Trading MCP connection — it is never deployed, hosted, imported by src/http/ or src/mcp/http, or reachable through the paid server. The canonical local tools are position_check, trade_prepare, and trade_execute; trade_execute only executes previously-prepared order ids. Their upstream mapping remains gated on O-9. Policy checks (src/trading/policy.ts) are pure and exhaustively tested; every decision logged locally. rob-security reviews every src/trading/ diff before it merges.
  5. Hosted MCP transport (D-16): create a fresh stateless WebStandardStreamableHTTPServerTransport (sessionIdGenerator: undefined) per request, pass Hono's c.req.raw to handleRequest, and return the Web Response directly. No fetch-to-node or sibling Node listener. Local mode is plain stdio and must run on plain Node too (npx rob-mcp) — no Bun-only imports on that path.
  6. Fail-closed boot, graceful shutdown (keeper pattern): main() loads config, gates on chain id, starts health server, handles SIGINT/SIGTERM; /healthz reports scanner lag + facilitator reachability, 503 only on genuine staleness.
  7. The site is derived, not authoritative (D-23; docs/developers/site.md): generate implemented tool pages and exact pricing from src/tools/definitions.ts/src/pricing.ts, and fail validation on drift from tools.md. Keep Astro in the single root package, use static output, never present fixtures as live market facts, and never imply an O-5/O-8/O-9-gated capability is available. GitHub Pages hosts only the static artifact; it never proxies the Fly API or receives service secrets.

Read the full file on GitHub · 90 lines

Changes

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.

  1. 3d ago First seen · 90 lines · 121 tokens per session scan A 8437e7f08dc2

Subscribe to this mod's changes

rob-surface is an agent published in the GitHub repository oyusypenko/rob-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 121 tokens to every session and 1,613 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.

Related

Other agents, from other repositories

codemap

Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…

alvinunreal/oh-my-opencode-slim · 0 tokens

ruby-developer

Implementación de código Ruby on Rails siguiendo specs SDD aprobadas. Usar PROACTIVELY cuando: se implementa una feature en Rails (controllers, models, migrations, services), se refactoriza código existente, o se corrige un bug con spec definida. SIEMPRE requiere una Spec SDD aprobada antes de empezar.

gonzalezpazmonica/pm-workspace · 73 tokens

dispatcher-unification-design

Status: phase-2 design drafted; implementation is held for maintainer review. Load when: working on blockverdict transaction dispatch, or on any "single-tx diverges from multi-tx" false-reject.

Verified-zkEVM/evm-asm · 0 tokens

orquestra-pda-explorer

Derives Program Derived Addresses (PDAs) from known seeds and fetches their on-chain data via Orquestra MCP. Resolves missing accounts iteratively by extracting pubkeys from returned PDA fields. Uses ONLY Orquestra MCP tools. Examples: Context: User needs to find a user's stake account for a specific program user…

berkayoztunc/orquestra · 293 tokens

chainaware-token-launch-auditor

Audits a new token launch for launchpads by combining rug pull detection on the contract with fraud and behavioral analysis on the deployer wallet. Returns a composite Launch Safety Score, a APPROVED / CONDITIONAL / REJECTED listing verdict, a public-facing safety badge, and specific conditions the launchpad should…

ChainAware/behavioral-prediction-mcp · 247 tokens

chainaware-reputation-scorer

Calculates a numeric reputation score for any Web3 wallet using the ChainAware Reputation Formula: (1000/110) × (experience + 1) × (riskcapability + 1) × (1 - fraudprobability). Max score = 1000. Use this agent PROACTIVELY whenever a user wants to score a wallet, calculate reputation, rank wallets, compare wallet…

ChainAware/behavioral-prediction-mcp · 178 tokens