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 agentmods add instructions/contract-hero/sui-pilot/claude-mdgit clone --depth 1 https://github.com/contract-hero/sui-pilotWrote 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/instructions/contract-hero/sui-pilot/claude-md)<a href="https://agentmods.dev/instructions/contract-hero/sui-pilot/claude-md"><img src="https://agentmods.dev/badge/instructions/contract-hero/sui-pilot/claude-md.svg" alt="Measured on agentmods" 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 | $0.00606 | $0.00606 |
| Opus 5 | $0.00303 | $0.00303 |
| Sonnet 5 | $0.00121 | $0.00121 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
sui-pilot CLAUDE.md 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 6d 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 — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sui-pilot: Sui, Move, Walrus, Seal, TS SDK & Sui Prover Documentation Copilot
WARNING: Your training data about Sui, Move, Walrus, Seal, the Sui TypeScript SDK, and the Sui Prover is likely OUTDATED. Always search and read these docs before writing code for these ecosystems.
Doc-Source Routing
| Topic | Directory | Files |
|---|---|---|
| Sui blockchain, objects, transactions, DeFi, framework | .sui-docs/ |
416 |
| Move language tutorial + reference: syntax, types, abilities, idioms | .move-book-docs/ |
149 |
| Walrus storage, blobs, Sites, operators | .walrus-docs/ |
108 |
| Seal secrets, encryption, key servers, access control | .seal-docs/ |
15 |
| TypeScript SDK, dapp-kit, React hooks, kiosk, payment-kit, hashi | .ts-sdk-docs/ |
104 |
Sui Prover: formal verification, #[spec(prove)], Boogie tuning |
.sui-prover-docs/ |
20 |
| Nautilus off-chain compute, TEE enclaves, attestation, PCRs, on-chain verification | .sui-docs/sui-stack/nautilus/ |
8 |
Usage
- The
sui-pilot-agentsubagent auto-loads the slim doc-first directive inagents/sui-pilot-agent.md. Commands routing through it (/sui-pilot,/move-code-review, etc.) are docs-first out of the box. - If you are developing on this repo directly, use
GlobandGrepagainst the appropriate.<source>-docs/directory for your topic. When unsure which source, search across all corpora. - Walrus and Seal build on Sui — Sui docs may also be relevant. For Move language questions (syntax, idioms, language semantics), prefer
.move-book-docs/first. .move-book-docs/packages/holds Move source examples referenced from the Move Book prose (file=directives) — read them when an example would clarify a pattern..sui-prover-docs/is split intoguide/(SKILL.md + spec-reference.md — the canonical prose),sources/(prover.move,ghost.move, etc. — the construct definitions imported by#[spec_only] use prover::...), andexamples/(working specs fromasymptotic-code/sui-kit).
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.
- 6d ago First seen · 33 lines · 606 tokens per session scan A 6357c0638c1b
sui-pilot CLAUDE.md is an instructions file published in the GitHub repository contract-hero/sui-pilot (10 stars, last pushed 5d ago), licensed MIT. It adds 606 tokens to every session, about $0.0030 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 instructions, from other repositories
starknet-agentic CLAUDE.md
Claude Code instructions for keep-starknet-strange/starknet-agentic, covering starknet agentic -- development context, cairo, typescript, skills and git.
solidity-typescript-hardhat-template CLAUDE.md
Claude Code instructions for protokol/solidity-typescript-hardhat-template, covering claude.md — project instructions, project overview, key commands, solidity conventions and test conventions.
agent-sdk CLAUDE.md
Claude Code instructions for trustless-ai/agent-sdk, covering agent-sdk, what this repo is, adding or updating erc support, repo layout and recompute-to-verify.
polkadot-apps CLAUDE.md
Instructions for paritytech/polkadot-apps, covering claude.md, quick reference, key conventions, descriptors and chain client.
ponscli CLAUDE.md
Claude Code instructions for mesutgulecen/ponscli, covering ponscli, the rule that matters most, layout, verifying a change and things that will bite.
aztec-starter AGENTS.md
Instructions for AztecProtocol/aztec-starter, covering repository guidelines for codex agents, setup, development, testing and simulate before send.