What is stacks-agent?

A development guide for building applications on Stacks, a blockchain network whose smart contracts use Bitcoin as their settlement layer. It includes examples and guidance for Clarity contracts, tokens, DeFi, security, Stacks.js, naming, staking, and deployment.

Use it to create, audit, debug, or deploy Stacks smart contracts and connected web applications, including fungible tokens, NFTs, DeFi features, and Bitcoin-related operations.

It gives coding agents current example patterns and troubleshooting guidance for Stacks development. This helps avoid deprecated APIs and common transaction or security mistakes.

How kai-builder/stacksagent configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to kai-builder/stacksagent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/kai-builder/stacksagent/main/.claude/skills/stacks-agent/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/kai-builder/stacksagent

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/kai-builder/stacksagent/stacks-agent/github.svg)](https://agentmods.dev/skills/kai-builder/stacksagent/stacks-agent)

Your own site

<a href="https://agentmods.dev/skills/kai-builder/stacksagent/stacks-agent"><img src="https://agentmods.dev/badge/skills/kai-builder/stacksagent/stacks-agent/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/kai-builder/stacksagent/stacks-agent"><img src="https://agentmods.dev/badge/skills/kai-builder/stacksagent/stacks-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,530 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00019	$0.02530
Opus 5.5	$0.00008	$0.01012
Sonnet 5.5	$0.00004	$0.00506
Haiku 4.5	$0.00002	$0.00253

Measured 2mo ago against content hash c8c3a5bc7cc3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

stacks-agent 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 2mo 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.

.claude/skills/stacks-agent/SKILL.md · 274 lines

How it starts

The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stacks Agent Skill

AI-powered development intelligence for building on Stacks blockchain - Bitcoin's most powerful smart contract layer.

Capabilities

Core Features

Clarity Contracts: Generate, audit, and deploy smart contracts
Token Standards: SIP-010 (fungible) and SIP-009 (NFT) templates
DeFi Integration: Alex, Velar, Bitflow, Zest, Boost, Faktory protocol patterns
Security Analysis: Vulnerability detection and best practices
Stacks.js: Frontend integration with modern @stacks/connect v7+ API
BNS: Bitcoin Name System operations
Stacking: PoX stacking and pool delegation
Deployment: Testnet and mainnet deployment guides

New in v2.0 🎉

🎯 40 Production Code Examples: Complete working code from live dApps (sbtc-market, stacksagent, STX City)
🕸️ 100 Knowledge Relationships: Connected concepts showing dependencies and prerequisites
🚫 Zero Deprecated Code: All examples use modern API patterns (no openContractCall, showConnect, or Gaia)
🔒 Security-First: All examples include post-conditions, error handling, and common pitfalls
🐛 Debugging Examples: Real-world troubleshooting for failed transactions

Knowledge Base

Code Snippets (495+ entries)

61 Clarity functions - Complete language reference
14 Contract templates - FT, NFT, DAO, Vault, Marketplace, Stacking
15 Security patterns - Common vulnerabilities and fixes
25 DeFi protocols - Alex, Velar, Bitflow, Zest, StackingDAO, Boost, Faktory
76 Stacks.js snippets - Modern @stacks/connect v7+ patterns (wallet, transactions, post-conditions)
21 BNS operations - Name registration and resolution (Clarity + JS + API)
25 Stacking guides - PoX stacking and delegation (Clarity + JS + API)
30 Oracle integration - Pyth Network price feeds with VAA handling (Clarity + JS + API)
25 Deployment steps - Testnet, mainnet, and devnet

Production Examples (40 examples - NEW in v2.0)

10 DeFi examples - Swaps, liquidity, oracles, stacking, bonding curves, debugging
10 NFT examples - Minting, marketplace, royalties, metadata, batch operations, debugging
8 Token examples - SIP-010, vesting, allowances, burns, multi-token swaps
7 Security examples - Reentrancy, overflow, access control, rate limiting
5 Auth examples - Wallet connect, JWT, sessions, NFT gating (No Gaia - deprecated)

Read the full file on GitHub · 274 lines

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.

2mo ago First seen · 274 lines · 19 tokens per session scan A c8c3a5bc7cc3

Subscribe to this mod's changes

stacks-agent is a skill published in the GitHub repository kai-builder/stacksagent (6 stars, last pushed 9mo ago), licensed MIT. It adds 19 tokens to every session and 2,530 once invoked, about $0.0001 per session on Opus 5.5. 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.

Web3 and blockchain

stacks-agent next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
stacks-agentkai-builder/stacksagent	Skill	6	9mo ago	MIT	A	19	Claude Code
signature-replayPurpleAILAB/Decepticon	Skill	6.5k	8d ago	Apache-2.0	A	31	Claude Code, Codex
official-sui-skillsMystenLabs/sui	Skill	7.8k	today	Apache-2.0	A	116	Claude Code, Codex
bridgealsk1992/CloddsBot	Skill	3.1k	1mo ago	MIT	A	13	Claude Code, Codex
onchainkitalsk1992/CloddsBot	Skill	3.1k	1mo ago	MIT	A	24	Claude Code, Codex
marginfialsk1992/CloddsBot	Skill	3.1k	1mo ago	MIT	A	11	Claude Code, Codex
devtools-event-clientTanStack/devtools	Skill	510	today	MIT	A	79	Claude Code, Codex

stacksagent: Skill for Claude Code