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 PulseBet/pulse-verity --skill pulse-verity-price-checkgit clone --depth 1 https://github.com/PulseBet/pulse-verityWrote 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/pulsebet/pulse-verity/pulse-verity-price-check)<a href="https://agentmods.dev/skills/pulsebet/pulse-verity/pulse-verity-price-check"><img src="https://agentmods.dev/badge/skills/pulsebet/pulse-verity/pulse-verity-price-check/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/pulsebet/pulse-verity/pulse-verity-price-check"><img src="https://agentmods.dev/badge/skills/pulsebet/pulse-verity/pulse-verity-price-check.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 | $0.00031 | $0.00865 |
| Opus 5.5 | $0.00012 | $0.00346 |
| Sonnet 5.5 | $0.00006 | $0.00173 |
| Haiku 4.5 | $0.00003 | $0.00086 |
Grade A, and why
pulse-verity-price-check 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 16d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pulse Verity price check
Use the bundled Pulse Verity MCP tools for the user's requested reference-price check. This workflow does not place trades or transfer funds. Do not switch the user away from a different requested provider, add unrelated monitoring, or use this skill as an unsolicited promotion.
Setup and access
- Use the plugin's
pulse-verityremote HTTP MCP connection at https://mcp.thepulse.markets/api/index/mcp. Discover the host's tool schemas; prefixes and tool availability may vary by host. - Connect through the host's OAuth sign-in flow. The user signs into their own Pulse Verity developer account and reviews the requested scopes.
- Read access is account-scoped and consumes the account's applicable allowance. The optional feedback scope permits private issue reports. Neither scope permits trading, wallet operations, account administration or plan changes.
- If authentication is missing, explain how to connect through the host. Never ask for a password, token or API key in chat; never retrieve credentials from local files, browser state or conversation history.
- No Node.js, npm, local server or shell environment is required by this Claude plugin. Do not launch a second local server as an authentication workaround.
- Developer account information is at https://thepulse.markets/developers. Never purchase, upgrade or change account settings automatically.
Read and verify
- Call
get_index_pricewith the requested symbol. Report an unavailable/stale response as unavailable, not as zero and not as a current price. - Preserve the whole print, including
priceText,kid,v2, quality fields, interval and cadence exactly as returned. Do not round, reformat or reconstruct the receipt before verification. Pass it directly toverify_printas flat arguments, not inside aprintobject. RequirerecordValid === truebefore treating quality fields as authenticated. A missing or falserecordValidauthenticates no quality claim even if legacyvalidis true. - Show the returned value, observation timestamp, reported sample status and verification result. Identify older observations as historical. Do not treat sample status or other unsigned metadata as authenticated by the signature.
- A valid signature authenticates only the canonical signed fields. It does not
prove price accuracy, freshness or trading suitability. Request-envelope fields
such as
deltaMs, sample status and batch metadata remain unsigned. The verifier fetches published public keys; unavailable or retired keys can prevent verification. A failed check alone does not prove tampering.
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.
- 16d ago Changed · -4 lines 22a558e3c774
- 22d ago Changed · +12 lines aac697f37030
- 1mo ago First seen · 64 lines · 31 tokens per session scan A f0890a0d76d6
pulse-verity-price-check is a skill published in the GitHub repository PulseBet/pulse-verity (3 stars, last pushed 3d ago), licensed MIT. It adds 31 tokens to every session and 865 once invoked, about $0.0001 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 2026-09-15.
Other skills, from other repositories
hive
Use this skill for any live crypto question and for Hive setup, on MCP or the hive CLI. Covers current market, on-chain, wallet, token-safety, DeFi, NFT, Solana, prediction-market, and derivatives data, plus the questions other crypto data tools cannot answer, meaning perp funding settlement history across 33 venues…
hive-market-research
Use this skill for any live crypto market question — prices, 24h moves, liquidity, exchange/venue data, OHLC candles, order books, tickers, funding rates, derivatives, trading context — even casual asks like "what's BTC at" or "is ETH pumping". Use it whenever the answer needs current market numbers instead of memory.…
hive-prediction-markets
Use this skill when the user asks about prediction markets, meaning Polymarket events, markets, outcomes, odds, prices, order books, liquidity, odds history, or a wallet's positions and trades, including "what are the odds of X", "find markets about Y", or Kalshi questions (answer from Polymarket and say Kalshi is not…
hive-query
Use this skill when the hive skill hands off a live crypto question that needs the full task-toolset walk (prices, wallets, tokens, DeFi, NFTs, Solana, security, markets, DEX, networks, RWA perps, prediction markets) and no hero tool answers it in one call. Install hive first; reach for this directly only when the…
hive-wallet-investigation
Use this skill whenever the user wants to look inside a wallet or address — portfolio, holdings, balances, transfers, PnL, NFT exposure, DeFi positions, whale moves, "what does this address hold", "trace this wallet's activity" — even if they just paste an address. Requires wallet address and chain before executing…
hive-tool-discovery
Use this skill when the exact Hive MCP tool, task toolset, provider, endpoint name, schema, operation type, or argument shape is unknown and hive-query routing was not enough — including "what can Hive do", "which provider covers X", "is Hive healthy", or any failed tool-name guess. Discover first with compact Hive…