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/skills/verify-tokens/SKILL.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/skills/oyusypenko/rob-mcp/verify-tokens)<a href="https://agentmods.dev/skills/oyusypenko/rob-mcp/verify-tokens"><img src="https://agentmods.dev/badge/skills/oyusypenko/rob-mcp/verify-tokens/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/oyusypenko/rob-mcp/verify-tokens"><img src="https://agentmods.dev/badge/skills/oyusypenko/rob-mcp/verify-tokens.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 | $0.00106 | $0.01116 |
| Opus 5.5 | $0.00042 | $0.00446 |
| Sonnet 5.5 | $0.00021 | $0.00223 |
| Haiku 4.5 | $0.00011 | $0.00112 |
Grade A, and why
verify-tokens 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify & maintain the Stock Token registry
Authoritative source order: docs/developers/architecture.md (D-11's official-source,
script-seeded, on-chain-verified snapshot design) and docs/developers/tools.md (what registry
fields the tools consume). Docs win over this skill; report drift.
Issuer semantics come from the chain's issuer profile (data/chains.json). On 4663: Stock Tokens
are ERC-20 (18 decimals) + ERC-8056 (uiMultiplier(), balanceOfUI()), and the Chainlink
tokenized-equity feeds are 8-decimal USD and already include the uiMultiplier — a feed entry
that needs multiplier math is a registry bug, not a tool bug. Other chains/issuers verify against
their own profile's fields. D-21 records
0xcfAEce2151502dA2a21d47234ae1f08618A60A94 as the verified 4663 ForwarderV4 participant;
zero-address mint/redeem classification takes precedence over participant flow.
Docs-first rule (mandatory, every run)
Before relying on any flag or ABI shape, consult current docs — context7
(resolve-library-id → query-docs) for viem (multicall) and Chainlink data feeds; WebFetch
fallbacks: https://docs.chain.link/data-feeds/price-feeds/addresses?network=robinhood and the
Robinhood Chain Token Contracts, Stock Token APIs, and "Building with Stock Tokens" pages.
Invariants this skill will not violate
- Read-only. No private key, no signing, no state change. The only env vars referenced are
the
RPC_URL_<chainId>vars (by name — never read a real.env). - Nothing enters a token registry unverified. Every entry in every
data/tokens/<chainId>.jsonmust pass the on-chain check below before commit; a failing entry is removed or fixed, never waved through. - Quote assets and pools are verified too. Validate each chain registry quote token/feed, and accept pool addresses only when factory discovery plus bytecode/token/fee checks pass (D-19). No pool is a valid result; never add a plausible address to avoid an empty venue list.
- No hardcoded market metrics — the verify step sanity-checks that a feed ANSWERS, never asserts what the price should be.
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 · 73 lines · 106 tokens per session scan A bc121c1cb337
verify-tokens is a skill published in the GitHub repository oyusypenko/rob-mcp (1 stars, last pushed 3mo ago), licensed MIT. It adds 106 tokens to every session and 1,116 once invoked, about $0.0004 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 skills, from other repositories
signature-replay
Signature replay attacks — missing nonces, missing chain ID, ecrecover zero address, signature malleability, cross-chain replay.
official-sui-skills
Pointer to the official Mysten Labs skills for building on Sui — language fundamentals, object model, PTBs, SDKs, publishing, upgrades, frontend integration, accessing on-chain data. Maintained upstream at github.com/MystenLabs/skills; pinned to the same ref the audit catalog derives from (see…
bridge
Cross-chain token transfers using Wormhole and CCTP.
onchainkit
Build onchain apps with Coinbase's OnchainKit React components - wallets, swaps, NFTs, payments.
marginfi
MarginFi — Solana lending and borrowing.
devtools-event-client
Create typed EventClient for a library. Define event maps with typed payloads, pluginId auto-prepend namespacing, emit()/on()/onAll()/onAllPluginEvents() API. Connection lifecycle (5 retries, 300ms), event queuing, enabled/disabled state, SSR fallbacks, singleton pattern. Unique pluginId requirement to avoid event…