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 aptos-labs/aptos-agent-skills --skill write-contractsgit clone --depth 1 https://github.com/aptos-labs/aptos-agent-skillsWrote 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/aptos-labs/aptos-agent-skills/write-contracts)<a href="https://agentmods.dev/skills/aptos-labs/aptos-agent-skills/write-contracts"><img src="https://agentmods.dev/badge/skills/aptos-labs/aptos-agent-skills/write-contracts/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/aptos-labs/aptos-agent-skills/write-contracts"><img src="https://agentmods.dev/badge/skills/aptos-labs/aptos-agent-skills/write-contracts.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 | $0.00104 | $0.03131 |
| Opus 5 | $0.00052 | $0.01566 |
| Sonnet 5 | $0.00021 | $0.00626 |
| Haiku 4.5 | $0.00010 | $0.00313 |
Grade A, and why
write-contracts 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 9d 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 — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write Contracts Skill
Core Rules
Digital Assets (NFTs) ⭐ CRITICAL
- ALWAYS use Digital Asset (DA) standard for ALL NFT-related contracts (collections, marketplaces, minting)
- ALWAYS import
aptos_token_objects::collectionandaptos_token_objects::tokenmodules - ALWAYS use
Object<AptosToken>for NFT references (NOT genericObject<T>) - NEVER use legacy TokenV1 standard or
aptos_token::tokenmodule (deprecated) - See
../../../patterns/move/DIGITAL_ASSETS.mdfor complete NFT patterns
Object Model
- ALWAYS use
Object<T>for all object references (NEVER raw addresses) - Generate all refs (TransferRef, DeleteRef) in constructor before ConstructorRef destroyed
- Return
Object<T>from constructors (NEVER return ConstructorRef) - Verify ownership with
object::owner(obj) == signer::address_of(user) - Use
object::generate_signer(&constructor_ref)for object signers - Use named objects for singletons:
object::create_named_object(creator, seed)
Security
- ALWAYS verify signer authority in entry functions:
assert!(signer::address_of(user) == expected, E_UNAUTHORIZED) - ALWAYS validate inputs: non-zero amounts, address validation, string length checks
- NEVER expose
&mutreferences in public functions - NEVER skip signer verification in entry functions
Modern Syntax
- Use inline functions and lambdas for iteration
- Use receiver-style method calls:
obj.is_owner(user)(define first param asself) - Use vector indexing:
vector[index]instead ofvector::borrow() - Use direct named addresses:
@marketplace_addr(NOT helper functions)
Required Patterns
- Use init_module for contract initialization on deployment
- Emit events for ALL significant activities (create, transfer, update, delete)
- Define clear error constants with descriptive names (E_NOT_OWNER, E_INSUFFICIENT_BALANCE)
Testability
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/access-control.md 1.3 KB
- references/complete-example.md 5.7 KB
- references/events.md 1.2 KB
- references/initialization.md 2.8 KB
- references/object-patterns.md 6.2 KB
- references/safe-arithmetic.md 2.6 KB
- references/storage-decision-tree.md 4.4 KB
- references/storage-gas-optimization.md 12 KB
- references/storage-patterns.md 11 KB
- references/storage-types.md 8.9 KB
- references/v2-syntax.md 2.5 KB
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.
- 9d ago First seen · 317 lines · 104 tokens per session scan A d1affe1ea642
write-contracts is a skill published in the GitHub repository aptos-labs/aptos-agent-skills (19 stars, last pushed 2mo ago), licensed MIT. It adds 104 tokens to every session and 3,131 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
official-sui-skills
Pointer to the official Mysten Labs skills for building on Sui — language fundamentals, object model, PTBs, SDKs, publishing, upgrades, frontend integration, accessing on-chain data. Maintained upstream at github.com/MystenLabs/skills; pinned to the same ref the audit catalog derives from (see…
sui-and-move-tools
Use to get bytecode for a deployed Sui package and produce a disassembled working view. One GraphQL call fetches every module's raw bytecode bytes; sui move disassemble (already on the system, running sui prompt) produces .asm files for analysis. Trigger on "fetch this package's bytecode", "get me the .mv for package…
web3-audit
Smart contract security audit — 10 DeFi bug classes (accounting desync, access control, incomplete path, off-by-one, oracle, ERC4626, reentrancy, flash loan, signature replay, proxy), pre-dive kill signals (TVL < $500K etc), Foundry PoC template, grep patterns for each class, and real Immunefi paid examples. Use for…
sora-taira-testnet
Work against the SORA Taira testnet through its deployed Torii MCP endpoint for live account, asset, alias, contract, governance, Musubi package-registry, and transaction workflows. Use when Codex needs to inspect or mutate the Taira testnet, verify or add https://taira.sora.org/v1/mcp, prefer the curated iroha. tool…
mochi-local-sandbox
Bring up and use a Mochi-managed local Iroha sandbox plus its local Torii MCP endpoint. Use when Codex needs a reliable local devnet, needs to print or verify the codex mcp add mochi-local --url ... command, or should consume the generated .env.local and .mochi/generated/ bootstrap files for local-only development.
TronScan Data Lookup
Query TRON blockchain data via the TronScan API — accounts, transactions, tokens, blocks, contracts, transfers, and chain statistics.