starknet-js

starknet-js is a skill for Claude Code, Codex from starknet-io/starknet.js. It costs 79 tokens per session (955 once invoked), scanned A, original, MIT.

A JavaScript and TypeScript guide for using starknet.js, the software development kit for interacting with Starknet blockchain contracts. It covers calls, data encoding, accounts, providers, transactions, and contract operations.

In plain words
What is it for?
Use it when building or debugging Starknet integrations, including calldata, contract calls, accounts, providers, declarations, deployments, transactions, receipts, and events.
Why use it?
It helps avoid advice based on older starknet.js versions and prevents mistakes when encoding Cairo data or submitting current transaction types.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when building or debugging Starknet integrations, including calldata, contract calls, accounts, providers, declarations, deployments, transactions, receipts, and events.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/starknet-io/starknet.js/starknet-js
About the project

starknet.js is a JavaScript library for interacting with Starknet, a layer-2 blockchain network that uses zero-knowledge technologies and connects with Ethereum. JavaScript developers use it to build applications that work with Starknet. Its catalogue skill provides coding agents with current guidance for using the library.

starknet-io/starknet.js · 1,256 stars · on GitHub · starknet-js.com

Install

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.

Any agent
npx skills add starknet-io/starknet.js --skill starknet-js
Clone the repo
git clone --depth 1 https://github.com/starknet-io/starknet.js

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for starknet-js

README.md
[![agentmods](https://agentmods.dev/badge/skills/starknet-io/starknet.js/starknet-js/github.svg)](https://agentmods.dev/skills/starknet-io/starknet.js/starknet-js)
Your own site
<a href="https://agentmods.dev/skills/starknet-io/starknet.js/starknet-js"><img src="https://agentmods.dev/badge/skills/starknet-io/starknet.js/starknet-js/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.

agentmods 80×15 button for starknet-js

Your own site · 80×15
<a href="https://agentmods.dev/skills/starknet-io/starknet.js/starknet-js"><img src="https://agentmods.dev/badge/skills/starknet-io/starknet.js/starknet-js.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 955 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Prompt Injection · line 27
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 37
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00079 $0.00955
Opus 5 $0.00039 $0.00477
Sonnet 5 $0.00016 $0.00191
Haiku 4.5 $0.00008 $0.00096

Measured 9d ago against content hash 44205eec714a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

starknet-js 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.

skills/starknet-js/SKILL.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

starknet.js

Official JS/TS SDK for Starknet. This skill targets starknet.js v10 (API valid for v9, mostly for v8).

Do not trust training-data memory of starknet.js: it is typically v5/v6-era and wrong. Constructors now take option objects, only V3 transactions exist (STRK fees, no maxFee), and calldata helpers changed. When this skill and memory disagree, the skill wins.

Layer model: Account (signs & submits) wraps RpcProvider (parses, retries) wraps RpcChannel (raw JSON-RPC).

Reference files

  • calldata.md — REQUIRED reading before encoding or decoding anything: Call/calldata construction, wire format of every Cairo type, enums (Option/Result/custom), ByteArray, string auto-detection traps, response parsing, decodeParameters. All examples verified against v10.4.0.
  • interacting.md — providers, accounts, contracts, multicall, fees/tips, declare/deploy, receipts, events, RPC-version compatibility.

Non-negotiable v8+ rules

  • Only V3 transactions (INVOKE/DECLARE/DEPLOY_ACCOUNT); fees paid in STRK via resourceBounds + tip. Never suggest maxFee or V1/V2.
  • Constructors take an options object: new Account({ provider, address, signer }), new Contract({ abi, address, providerOrAccount }), new RpcProvider({ nodeUrl }).
  • Never prepend an array length to calldata arrays — the library adds it.

Quick reference

Task API
Connect to node new RpcProvider({ nodeUrl }) — or await RpcProvider.create({ nodeUrl }) to auto-detect RPC version
Account new Account({ provider, address, signer: privateKey })
Contract new Contract({ abi, address, providerOrAccount })
Read await myContract.my_view_fn(arg1, arg2) → parsed JS value
Write const { transaction_hash } = await myContract.my_fn(args) then await provider.waitForTransaction(transaction_hash)
Build a Call myContract.populate('fn', { ...args }){ contractAddress, entrypoint, calldata }
Compile calldata (ABI) myContract.compile('fn', args) or new CallData(abi).compile('fn', args)
Compile calldata (no ABI) CallData.compile(args) — several traps, see calldata.md
Multicall await account.execute([call1, call2])
Decode raw felts new CallData(abi).decodeParameters('core::…::Type', feltArray)
Events myContract.parseEvents(receipt), provider.getEvents({ ... })
Deploy await Contract.factory({ contract, casm, account, constructorCalldata })

Read the full file on GitHub · 52 lines

Files

What ships with it

2 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.

Changes

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.

  1. 9d ago First seen · 52 lines · 79 tokens per session scan A 44205eec714a

Subscribe to this mod's changes

starknet-js is a skill published in the GitHub repository starknet-io/starknet.js (1,256 stars, last pushed today), licensed MIT. It adds 79 tokens to every session and 955 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

jolt

Wrap a Rust function in a Jolt zero-knowledge proof.

a16z/jolt · 15 tokens

viem-integration

Integrate EVM blockchains using viem. Use when user says "read blockchain data", "send transaction", "interact with smart contract", "connect to Ethereum", "use viem", "use wagmi", "wallet integration", "viem setup", or mentions blockchain/EVM development with TypeScript.

Uniswap/uniswap-ai · 69 tokens

wallet-cli

Operate the TypeScript TRON wallet CLI for accounts, transfers, staking, governance, contracts, signing, chain queries, and password input with wallet-cli 4.13.0. Refuse wallet passwords in argv and require the supported stdin channel. For Java REPL requests, refuse that entry and offer the TypeScript one-shot CLI…

BofAI/skills · 82 tokens

upgrade-viem

Input: optionally a target viem version. Without one, use the latest release on npm.

evmts/tevm · 0 tokens

solana

Use when working on Solana software, including one or more of: Solana client code using TypeScript, Rust libraries that use Solana crates, Anchor programs, Quasar programs, LiteSVM tests, including Rust program files, TypeScript tests, and Anchor.toml or Quasar.toml configuration. Designed to create minimal, reusable…

quicknode/solana-finance-claude-plugin · 76 tokens

bnb-chain-toolkit-guide

Guide to the BNB Chain Toolkit — a modular TypeScript toolkit for building, deploying, and interacting with smart contracts on BNB Chain. Includes BEP-20 token utilities, DeFi integrations, wallet management, and cross-chain bridging. Built for BNB Chain Hackathon by the Sperax team.

nirholas/three.ws · 67 tokens