Stipend
A non-custodial USDC wallet on Base that an AI agent installs by itself, with spending limits enforced in the signing path rather than in a prompt. Receive payments, pay HTTP 402 / x402 charges automatically, and answer whether you are worth running. No account and no API key: the only approval needed is from the person who runs you.
Install
npx skills add stipend-sh/stipend --skill stipendgit clone --depth 1 https://github.com/stipend-sh/stipend.git /tmp/stipend
mkdir -p ~/.claude/skills
cp -r /tmp/stipend/. ~/.claude/skills/stipendPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# stipend.sh — wallet & payouts for AI agents You are an AI agent. This skill gives you a **non-custodial USDC wallet** on Base so you can get paid for your work and pay out your earnings. Nobody else holds your key — including whoever sold you this kit. ## Where the human line actually is Read this before anything else, because getting it wrong in either direction is the most common mistake with this kit. **Tell the person who runs you before you create a wallet.** Not afterwards. Creating a key that will hold real money on a mainnet is their decision, not yours, even though nothing technically stops you — no account, no issued key, nothing registered anywhere. Say what you are about to do and wait for an answer. There is no vendor in that loop: we cannot approve or refuse it, and we never see the key. The only party with standing is the one whose machine and money this touches. Once they have said yes: ```bash # fetch, read it, then run it — it is a short shell script curl -fsSL https://stipend.sh/install -o stipend-install.sh less stipend-install.sh sh stipend-install.sh stipend wallet create stipend wallet address ``` The one-liner `curl -sL https://stipend.sh/install | sh` does the same thing in one step. Prefer the three-step form: piping a network fetch straight into a shell leaves no point at which anyone can look at what arrived, and this is a package that handles money. Those commands change nothing outside your own machine and move no money.
Details
- Skill name
stipend- Repository
- stipend-sh/stipend
- License
- Apache-2.0
- Repo updated
- 29 October 2026
- Listed in
- karanb192/awesome-claude-skills
FAQ
What does the Stipend skill do?
A non-custodial USDC wallet on Base that an AI agent installs by itself, with spending limits enforced in the signing path rather than in a prompt. Receive payments, pay HTTP 402 / x402 charges automatically, and answer whether you are worth running. No account and no API key: the only approval needed is from the person who runs you.
How do I install the Stipend skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add stipend-sh/stipend --skill stipend. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Stipend popular?
It lives in stipend-sh/stipend, which has 1 GitHub stars and 0 forks, and is included in 1 curated skill list.
Related skills
Aeo Check
pchewlo/aeo-check
Run aeo-check on a website's code (or a live URL) to find answer engine optimisation problems that stop ChatGPT, Claude, Perplexity, Gemini and Google AI Overviews from crawling, understanding, citing or buying from the site, then fix them. Use when asked to check or improve AEO, GEO, AI search visibility, llms.txt, robots.txt for AI crawlers, structured data, or agent readiness.
Skill Freshness
1kvozianov/skill-freshness
Use this skill first whenever the user asks about the health of their installed agent skills: auditing, checking, cleaning up, updating or de-duplicating skills in ~/.claude/skills, ~/.codex/skills, ~/.agents/skills or plugin folders, or finding skills that are broken (missing CLI or script), outdated versus upstream, duplicated across agents, or made redundant by built-in features like /loop or /schedule. Do not inspect skill folders by hand: this skill ships a scanner that covers every agent (Claude Code, Codex, Cursor, Gemini CLI, Copilot, OpenCode, Antigravity), maps which agent loads each
Fresh Review
roman-s8o/workflow-pack-free
Review an artifact with an independent agent that has no access to the author's reasoning, then classify its findings.
Sechelix
1omarmohelal/SecHelix
Evidence-first application-security audit workflow for authorized repositories and environments. Use when reviewing a codebase, pull request, API, web application, AI-generated code, agent or MCP integration, cloud configuration, authorization (BOLA, IDOR, BFLA), business logic, payments, race conditions, secrets, supply chain, or release readiness for security weaknesses. Also supports explicitly requested technical SEO audits and evidence-backed codebase cleanup. Maps trust boundaries, selects applicable checks, runs parallel specialist review, independently verifies every material finding a
Least Cost Capable
kanibal-studio/least-cost-capable
Compare declared relative cost ranks among catalogued agent models after checking task capability, availability, authorization, workload, and cost evidence.
Rule Architect
1moveju112/rule-architect
Use when a project needs AI agent rules built or upgraded — no AI_RULES.md exists, an existing rule index has grown into one bloated file, or the user asks for a project rule set. Triggers on "make rules for this project", "generate AI rules", "set up project rules", "upgrade the project rules", "rule-architect", "/rule-architect", and the Korean equivalents "룰 만들어줘", "룰 생성", "AI 룰 만들어", "프로젝트 룰 고도화", or refreshing rules after a major refactor ("--update"). English and Korean triggers are equivalent.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.