Borrowing it
Nothing to install: this file belongs to oyusypenko/rob-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/oyusypenko/rob-mcp/main/.claude/agents/rob-architect.mdgit clone --depth 1 https://github.com/oyusypenko/rob-mcpWrote 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/agents/oyusypenko/rob-mcp/rob-architect)<a href="https://agentmods.dev/agents/oyusypenko/rob-mcp/rob-architect"><img src="https://agentmods.dev/badge/agents/oyusypenko/rob-mcp/rob-architect/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/agents/oyusypenko/rob-mcp/rob-architect"><img src="https://agentmods.dev/badge/agents/oyusypenko/rob-mcp/rob-architect.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 | $0.00140 | $0.00855 |
| Opus 5.5 | $0.00056 | $0.00342 |
| Sonnet 5.5 | $0.00028 | $0.00171 |
| Haiku 4.5 | $0.00014 | $0.00085 |
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 1mo 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 — 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
- Decision arbitration. When docs are silent or contradictory, gather the options, pick or
escalate to the user, and record the outcome as a
D-Nentry — numbered, dated, with a marker (USER-DIRECTED,ARCHITECT-DESIGNED, …), an owner, the ruling, its rationale, and an explicit "unchanged" list. Open questions getO-Nentries with owners. Append-only; supersede in place, never delete. - 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. Keeptools.md(the tool contract + PRICING) andarchitecture.mdin sync with reality; keepdocs/developers/runbooks/env-inventory.mdin sync with.env.example. - 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.
- Compliance review. Check deliverables against the four always-on rules (
spec-authority,no-custody,no-market-metrics,versions-pinned) and the phase plan inarchitecture.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-id→query-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.
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.
- 1mo ago First seen · 55 lines · 140 tokens per session scan A d357fd505b76
rob-architect is an agent published in the GitHub repository oyusypenko/rob-mcp (1 stars, last pushed 3mo ago), licensed MIT. It adds 140 tokens to every session and 855 once invoked, about $0.0006 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 2026-08-31.
Other agents, from other repositories
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.