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 skills add metis-rwa/mcp --skill token-safetygit clone --depth 1 https://github.com/metis-rwa/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/metis-rwa/mcp/token-safety)<a href="https://agentmods.dev/skills/metis-rwa/mcp/token-safety"><img src="https://agentmods.dev/badge/skills/metis-rwa/mcp/token-safety/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/metis-rwa/mcp/token-safety"><img src="https://agentmods.dev/badge/skills/metis-rwa/mcp/token-safety.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 | $0.00073 | $0.00693 |
| Opus 5 | $0.00036 | $0.00347 |
| Sonnet 5 | $0.00015 | $0.00139 |
| Haiku 4.5 | $0.00007 | $0.00069 |
Grade A, and why
token-safety 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 10d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What the issuer can do to a holder
Someone is asking what they are exposed to if they hold this token. Answer with what the chain says, not with reassurance and not with alarm.
Read the controls first
Call get_token_controls with the symbol or mint. It returns mint authority,
freeze authority, and every Token-2022 extension, each marked:
!!the issuer can move, freeze, or block a holder's position!economics or displayed balances can change.informational
Report every !! finding in plain language. The ones that matter most:
- Permanent delegate: tokens can be transferred or burned out of any account without the holder signing anything.
- Freeze authority: any account can be frozen, which blocks selling and redemption from that account.
- Pausable: transfers can be halted chain-wide.
- Transfer hook: every transfer runs through a program that can reject it, which is how an allowlist is enforced. Say whether a hook program is actually set, since the extension can be present with none configured.
- Default account state frozen: new accounts cannot transact until the issuer thaws them. The token is permissioned by default.
- Mint authority: supply is not capped and can be issued at any time.
Then say what it means
Give the honest reading, which is usually not a scandal. A redeemable asset-backed token needs most of these powers: an issuer that cannot mint cannot honour a new deposit, and one that cannot freeze cannot comply with a court order or a sanctions list. The right conclusion is almost never "this is a scam" and almost never "this is fine". It is: here is who can act on your position, and here is what you are trusting them not to do.
Never call a token a scam or a rug on the strength of its extensions alone. Never tell someone to buy or sell. If asked for a verdict, give the conditions instead: what would have to be true about the issuer for these powers to be acceptable.
Fill in the rest when it is asked for
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.
- 10d ago First seen · 65 lines · 73 tokens per session scan A 91c6f3b062d2
token-safety is a skill published in the GitHub repository metis-rwa/mcp (0 stars, last pushed 28d ago), licensed MIT. It adds 73 tokens to every session and 693 once invoked, about $0.0004 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 skills, from other repositories
mpp-agent
Pay HTTP 402 APIs via Machine Payments Protocol (MPP).
crypto-market-rank
Crypto market rankings and leaderboards. Query trending tokens, top searched tokens, Binance Alpha tokens, tokenized stocks, social hype sentiment ranks, smart money inflow token rankings, top meme token rankings from Pulse launchpad, and top trader PnL leaderboards. Use this skill when users ask about token rankings…
trading-signal
Subscribe and retrieve on-chain Smart Money signals. Monitor trading activities of smart money addresses, including buy/sell signals, trigger price, current price, max gain, and exit rate. Use this skill when users are looking for investment opportunities — smart money signals can serve as valuable references for…
hyperliquid
Hyperliquid L1 perps DEX (69% market share).
bridge
Cross-chain token transfers using Wormhole and CCTP.
token-pick
One token recommendation and one prediction market pick - scored, quantified, with a skip branch when signals are weak.