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 premium-watchgit 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/premium-watch)<a href="https://agentmods.dev/skills/metis-rwa/mcp/premium-watch"><img src="https://agentmods.dev/badge/skills/metis-rwa/mcp/premium-watch/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/premium-watch"><img src="https://agentmods.dev/badge/skills/metis-rwa/mcp/premium-watch.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 | $0.00034 | $0.00393 |
| Opus 5 | $0.00017 | $0.00197 |
| Sonnet 5 | $0.00007 | $0.00079 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
premium-watch 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.
What it actually says
Premium watch on $ARGUMENTS
A tokenized equity should track the security it represents. When it does not, the gap is the most informative number available about whether the mint and redeem path is clearing.
For the asset in $ARGUMENTS, or the one the user names if the argument is
empty:
observe_assetfor the current cycle, which reads the token price, the reference price, and the pool state together at one moment.get_observation_historyfor the stored window, so the current reading has something to sit against.
What to report
- The premium now, in basis points, and which side of the reference it sits on.
- Where it sits inside the stored window: is this the widest it has been, is it converging, or is it noise around zero?
- Whether liquidity and hourly transaction counts moved with it. A premium that widens while liquidity drains is a different story from one that widens on heavy two-sided volume.
- Any detection the cycle fired, with the baseline it crossed.
What not to do
Do not present a premium as an arbitrage. Say what would have to be true to capture it: someone would need to mint or redeem at the reference price, in size, at that moment, and the reference itself has to be live rather than a stale republished quote from outside market hours. Most visible gaps on tokenized equities are one of those two things rather than free money.
If the asset has little or no stored history, say so and treat the reading as a single point rather than a trend.
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 · 41 lines · 34 tokens per session scan A a61eb1fefa2f
premium-watch is a skill published in the GitHub repository metis-rwa/mcp (0 stars, last pushed 29d ago), licensed MIT. It adds 34 tokens to every session and 393 once invoked, about $0.0002 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
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.