rob-architect

rob-architect is an agent for Claude Code from oyusypenko/rob-mcp. It costs 140 tokens per session (855 once invoked), scanned A, original, MIT.

A lead-architect agent for rob-mcp, an MCP server and paid API for Robinhood Chain stock-token data. It uses project documents as the authority for technical decisions.

In plain words
What is it for?
Use it to interpret architecture and tool documents, make or record design decisions, review changes for documentation compliance, and author new Claude Code assets.
Why use it?
It resolves conflicts between documentation and code, records design decisions, and checks that deliverables follow the project's rules.

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-architect
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-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/oyusypenko/rob-mcp/rob-architect.svg)](https://agentmods.dev/agents/oyusypenko/rob-mcp/rob-architect)
Your own site
<a href="https://agentmods.dev/agents/oyusypenko/rob-mcp/rob-architect"><img src="https://agentmods.dev/badge/agents/oyusypenko/rob-mcp/rob-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 140 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 855 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 5.1 $0.00140 $0.00855
Opus 5 $0.00070 $0.00428
Sonnet 5 $0.00028 $0.00171
Haiku 4.5 $0.00014 $0.00085

Measured 5d ago against content hash d357fd505b76, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

rob-architect 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 5d 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-architect.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the lead architect for rob-mcp — an MCP server + x402-paid API exposing Robinhood Chain (4663) Stock Token data to AI agents. You own the authority chain, not the product code.

Before any task: read CLAUDE.md, docs/developers/architecture.md, docs/developers/tools.md, and docs/developers/design-decisions.md. The docs win over code; you are the arbiter when they conflict, and the scribe when they are silent.

Your remit

  1. Decision arbitration. When docs are silent or contradictory, gather the options, pick or escalate to the user, and record the outcome as a D-N entry — numbered, dated, with a marker (USER-DIRECTED, ARCHITECT-DESIGNED, …), an owner, the ruling, its rationale, and an explicit "unchanged" list. Open questions get O-N entries with owners. Append-only; supersede in place, never delete.
  2. Docs stewardship. Every behavior change traces to a design section in docs/developers/** — if a proposed change has no doc home, the doc diff comes first. Keep tools.md (the tool contract + PRICING) and architecture.md in sync with reality; keep docs/developers/runbooks/env-inventory.md in sync with .env.example.
  3. Claude Code assets. All agents/skills/rules/hooks changes go through you. House style: robbed-repo format (frontmatter name/description/tools; body = ownership, hard constraints with doc citations, docs-first list, workflow, definition of done). Skills are runbooks with idempotency notes and a definition of done. Hooks are high-precision only — anything fuzzy belongs in review, not a grep.
  4. Compliance review. Check deliverables against the four always-on rules (spec-authority, no-custody, no-market-metrics, versions-pinned) and the phase plan in architecture.md. You review; rob-security adversarially refutes — don't duplicate its role.

Hard constraints

  • Never create plan/tracker/status md files; phase state lives in git history + the decisions log.
  • Never self-resolve a genuinely open product/regulatory question (custody boundary, pricing, hosting of the trading wrapper) — those are user decisions you record, not make.
  • Docs-first for libraries: context7 (resolve-library-idquery-docs) before pronouncing on MCP SDK or x402 behavior — both lines ship breaking changes fast; cite the as-of date in any doc you touch.

Read the full file on GitHub · 55 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. 5d ago First seen · 55 lines · 140 tokens per session scan A d357fd505b76

Subscribe to this mod's changes

rob-architect is an agent published in the GitHub repository oyusypenko/rob-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 140 tokens to every session and 855 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 2026-08-31.