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 agentmods add instructions/oyusypenko/rob-mcp/agents-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/instructions/oyusypenko/rob-mcp/agents-md)<a href="https://agentmods.dev/instructions/oyusypenko/rob-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/oyusypenko/rob-mcp/agents-md.svg" alt="Measured on agentmods" 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 | $0.04350 | $0.04350 |
| Opus 5 | $0.02175 | $0.02175 |
| Sonnet 5 | $0.00870 | $0.00870 |
| Haiku 4.5 | $0.00435 | $0.00435 |
Grade A, and why
rob-mcp AGENTS.md 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.
How it starts
The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rob-mcp — MCP server + x402-paid API for tokenized stocks (Robinhood Chain first)
Source of truth: README.md + the developer docs under docs/developers/**. When code and docs
disagree, the docs win; when the docs are silent or self-contradictory, never self-resolve — ask, or
record the decision in docs/developers/design-decisions.md (numbered D-N, dated, append-only).
This file is the map. Policy lives in .claude/rules/ — all four rules are always on:
spec-authority (docs-first + context7), no-custody, no-market-metrics, versions-pinned.
Rule violations are bugs, not style — write-time enforcement is in .claude/hooks/ (hard-rule grep
on write, secret/destructive-command guard, typecheck on stop). Never create plans/trackers/
status/progress md files anywhere — phase state lives in git history and design-decisions.md.
Harness-portable (D-9). .claude/** is the only hand-edited harness source; the OpenAI Codex
mirror (AGENTS.md, .codex/**, .agents/skills/**) is GENERATED by bun run sync-codex and
drift-checked by bun run validate. Never hand-edit a generated file — edit the .claude/ source
and re-run the generator. Runbook: docs/developers/runbooks/codex-parity.md.
What this is
One core, two surfaces, chain-agnostic (D-8): chains are data (data/chains.json + issuer
profiles + per-chain token registries), never assumptions in core code — Robinhood Chain 4663 is
the first and default enabled chain; scope is EVM-only (viem). Pure data services (stock-token
premium vs Chainlink oracle, cross-DEX liquidity/spreads, whale + mint/redeem flow) behind ports,
exposed as:
(a) a Hono JSON API (POST /api/v1/tools/<tool-name>) paywalled per-call with x402 (USDC on
Base) — what x402 Bazaar lists;
(b) an MCP server — free local stdio (bun run dev from a source checkout until npm
publication, BYO-RPC) and hosted Streamable HTTP with x402-paid tools. Plus a local-only
trading wrapper around the user's own Robinhood Trading MCP.
src/tools/definitions.ts is the single source of truth feeding both surfaces; the one PRICING
map drives both paywalls. Full design: docs/developers/architecture.md; tool contract:
docs/developers/tools.md.
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.
- 5d ago First seen · 231 lines · 4,350 tokens per session scan A 716cfc348d04
rob-mcp AGENTS.md is an instructions file published in the GitHub repository oyusypenko/rob-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 4,350 tokens to every session, about $0.0217 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 instructions, from other repositories
gmgn-skills CLAUDE.md
Claude Code instructions for GMGNAI/gmgn-skills, covering claude.md, critical rule — read this first, project overview, available skills and quick decision guide.
mercato-dapp AGENTS.md
Instructions for mercato-supply-chain/mercato-dapp, covering mercato — agent guide, quick facts, documentation map, domain glossary and user roles.
coingecko-mcp-server CLAUDE.md
Claude Code instructions for cyanheads/coingecko-mcp-server, covering developer protocol, what's next?, core rules, patterns and tool.
gensyn-delphi-skills CLAUDE.md
Instructions for gensyn-ai/gensyn-delphi-skills, a project described as: Skills for agents to view markets and place trades on Gensyn's Delphi prediction markets.
x402-stellar-kit CLAUDE.md
Claude Code instructions for CodeStrux/x402-stellar-kit, a project described as: x402 payment primitives for Stellar: intent binding, a deterministic policy engine, a pluggable approver, and an agent surface. Apache-2.0.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.