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.
git 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/rules/mission69b/t2000/sui-platform)<a href="https://agentmods.dev/rules/mission69b/t2000/sui-platform"><img src="https://agentmods.dev/badge/rules/mission69b/t2000/sui-platform/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/rules/mission69b/t2000/sui-platform"><img src="https://agentmods.dev/badge/rules/mission69b/t2000/sui-platform.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 | $0.00000 | $0.00365 |
| Opus 5.5 | $0.00000 | $0.00146 |
| Sonnet 5.5 | $0.00000 | $0.00073 |
| Haiku 4.5 | $0.00000 | $0.00036 |
Grade A, and why
sui-platform 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.
What it actually says
Sui Platform → .claude/skills/t2000-sui-platform/SKILL.md
The two things people get wrong:
- "One Sui address can only do one tx at a time" is a myth for a server payer. Address Balances (SIP-58) turn fungible holdings into an accumulator (no owned-object lock) and address-balance gas removes the gas-coin contention → a single settlement address scales. A wallet fleet is a blast-radius lever, never a scaling prerequisite.
- "Gasless" is narrower than it sounds. Only pure stablecoin transfers on the allowlisted trio qualify — any custom Move call still needs gas. Plus: 0.01 minimum, a dust-remainder floor that surfaces as a misleading "insufficient SUI balance" error, and auto-detect that only works on gRPC/GraphQL transports.
Read the full gotcha list before architecting a payer or debugging a send:
.claude/skills/t2000-sui-platform/SKILL.md.
(Content moved there 2026-07-24 from sui-address-balances-and-gasless.mdc — do
not re-inline it here; this file is a pointer so Cursor and Claude Code cannot
drift.)
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 · 27 lines · 0 tokens per session scan A d403cb15aa58
sui-platform is a cursor rule published in the GitHub repository mission69b/t2000 (23 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 365 tokens. 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 cursor rules, from other repositories
x402-before-you-pay
Before paying an x402 endpoint, read its 402 terms and run scvd.store's free preflight and dry run; decide with every reason named.
selat
SELAT capability layer — reach for SELAT before saying you can't do something or sending the user to an external tool / API key.
cursorrules
Cursor rule "cursorrules" from ASGCompute/asgcard-public, covering stellar mpp payments skill, when the user asks about, machine payments protocol, mpp or mppx and paid apis on stellar.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.