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 mission69b/t2000 --skill t2000-financial-amountsgit clone --depth 1 https://github.com/mission69b/t2000Wrote 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/mission69b/t2000/t2000-financial-amounts)<a href="https://agentmods.dev/skills/mission69b/t2000/t2000-financial-amounts"><img src="https://agentmods.dev/badge/skills/mission69b/t2000/t2000-financial-amounts/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/mission69b/t2000/t2000-financial-amounts"><img src="https://agentmods.dev/badge/skills/mission69b/t2000/t2000-financial-amounts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00859 |
| Opus 5 | $0.00053 | $0.00430 |
| Sonnet 5 | $0.00021 | $0.00172 |
| Haiku 4.5 | $0.00011 | $0.00086 |
Grade A, and why
t2000-financial-amounts 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Financial Amount + Token Data Safety
CLAUDE.md rules 6 and the constants section state the invariants. This is the
detail.
Floor display amounts — never round up
Any amount shown to users or passed to an SDK transaction builder must be ≤
the actual on-chain balance. Math.round can round up, producing more raw units
than the user holds → "Insufficient balance".
// ❌ BAD — Math.round(1.1286 * 100) / 100 = 1.13 (more than on-chain!)
const amount = Math.round(rawAmount * 100) / 100;
// ✅ GOOD — Math.floor always produces amount <= actual
const amount = Math.floor(rawAmount * 10000) / 10000;
Token decimal precision
Floor to the token's on-chain decimals, capped at 8:
| Token | On-chain decimals | Display floor |
|---|---|---|
| SUI | 9 | 4 dp |
| USDC | 6 | 2 dp |
| GOLD (XAUM) | 9 | 8 dp |
| anything else | — | Math.min(decimals, 8) dp |
Never hardcode these at a call site — read them from the registry (below).
SDK transaction amounts
Any SDK builder taking an amount converts via amount * 10^decimals. A display
amount that was rounded UP produces more raw units than the user has → the tx
fails. The live write surface is send · swap · pay; the floor-not-round rule
applies to every one of them.
Preset amounts for chip flows
For assets with tiny balances (< 0.01), use dynamic precision:
const dp = held >= 1 ? 100 : held >= 0.01 ? 10000 : 100000000;
const preset = Math.floor(held * fraction * dp) / dp;
Token data — canonical sources
| Data | Export | Location |
|---|---|---|
| Swap-supported names → coin types | TOKEN_MAP |
packages/sdk/src/token-registry.ts (derived from COIN_REGISTRY) |
| Token metadata (coin types, decimals, symbols) | SUPPORTED_ASSETS |
packages/sdk/src/constants.ts |
Resolvers (resolveSymbol, resolveTokenType, getDecimalsForCoinType) |
COIN_REGISTRY |
packages/sdk/src/token-registry.ts |
Rules
- Never create a new token map. Import from the canonical source above.
- Adding a token = update
TOKEN_MAPin the SDK. Everything downstream (system prompt, swap resolution) derives from it automatically. - Decimals are registry data, not call-site literals. USDSUI, USDe, suiUSDT
are all 6 decimals — encoded in
COIN_REGISTRY/SUPPORTED_ASSETS. - Frontend token lists import from the SDK registry; don't duplicate coin-type maps outside the canonical files.
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 · 88 lines · 106 tokens per session scan A 50fb7b692fc4
t2000-financial-amounts is a skill published in the GitHub repository mission69b/t2000 (23 stars, last pushed yesterday), licensed MIT. It adds 106 tokens to every session and 859 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
x402
HTTP 402 payment protocol for AI agent commerce — three-actor model (Client, Resource Server, Facilitator), ERC-3009 transferWithAuthorization, server middleware (@x402/express), client patterns in TypeScript and Python, facilitator integration, agent-to-agent payments, pricing strategies, and replay protection. Works…
agent-payment-stats
Cross-protocol agent-economy payment metrics from Barker's index. x402 (Base) volume is on-chain verifiable; ACP / AP2 / MPP / AP4M figures are self-reported claims. Separates real vs nominal volume by filtering wash/noise sellers. Use when users ask about x402 volume, agent payment stats, agent economy metrics, or…
setup-kraken
Use when the user wants to connect their own Kraken account to trade on it through the agent — "set up Kraken", "connect my Kraken", "trade on Kraken", "add/use my Kraken API key", "I want to trade on a CEX", or when moving toward live centralized-exchange trading on Kraken. Guides the user to create a LEAST-PRIVILEGE…
connect-kraken
Use when the user wants to connect their Kraken account to trade through the agent WITHOUT creating or handling an API key — "connect Kraken with OAuth", "log in with Kraken", "connect Kraken without a key", "I don't want to manage a Kraken key". This is the KEYLESS (OAuth) mode: the user consents once in a browser…
swarmwage-publish
Publish your agent's capabilities to the Swarmwage registry and earn USDC for each call. Lets your agent advertise services (image generation, audio transcription, charting, custom domain workflows…) on the open agent hire protocol — other AI agents discover you, hire you with one function call, and pay you in USDC on…
crypto-data
Use for any crypto data question — token/coin prices, FX, commodities, stocks, OHLC history, DEX pairs and liquidity, DeFi TVL, yield/APY pools, or raw JSON-RPC against a chain; also when the user asks for on-chain SQL, wallet labels/net worth, social mindshare or crypto news, so they are told plainly what BlockRun…