Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Nevermined Payments Integration · leoyeai | DecimalAI

Financeby leoyeai

Nevermined Payments Integration

Integrates Nevermined payment infrastructure into AI agents, MCP servers, Google A2A agents, and REST APIs. Handles x402 protocol, credit billing, payment plans, and SDK integration for TypeScript (@nevermined-io/payments) and Python (payments-py).

Never made a case worse

SkillScore

SkillScore91/100

Test results 91

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

26%91%of test cases passed +65 pts

Without skill6 of 23

With skill21 of 23

15 fixed6 passed either way2 still failing0 broke

Measured on gemini-3.6-flash8/8/2026v1

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskWhat method does a subscriber call in the `@nevermined-io/payments` TypeScript SDK to obtain an x402 access token before calling a protected API?

Without the skillMissed

With the skillPassed

Same model, same task. Answers are capped and redacted.

Use this skill

Your agent runs on

Adds every file the skill has, pinned so you can update it. No account needed.

pip install "decimalai>=0.15"
decimalai skills add leoyeai-nevermined-payments
claude --plugin-dir "$(git rev-parse --show-toplevel 2>/dev/null || pwd)/.agents"

The same install from Python, for a notebook or a setup script.

Install

pip install "decimalai>=0.15"

Add the skill

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nevermined-payments")
if result.exit_code:
    raise SystemExit(result.problems)

print("Added. Start Claude Code with the command below.")

Start Claude Code with it

claude --plugin-dir "$(git rev-parse --show-toplevel 2>/dev/null || pwd)/.agents"

Type these in a Claude Code session. No account or API key. It writes the skill and any files it bundles, and asks first when its safety rating isn't Passed.

Add the DecimalAI plugin, once

/plugin marketplace add decimal-labs/decimalai-claude-plugins
/plugin install decimalai@decimalai

Install this skill

/decimalai:install leoyeai-nevermined-payments

The plugin needs python3 and curl on your machine.

No Python or account. Claude Code picks it up in its next session.

Save it into your project

curl -fsSL --create-dirs -o .claude/skills/leoyeai-nevermined-payments/SKILL.md https://app.decimal.ai/s/leoyeai-nevermined-payments/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/leoyeai-nevermined-payments/SKILL.md

This gets SKILL.md only. The skill's 8 other files are not included.

Other ways to add it

Claude Code docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[claude-agent-sdk]"
decimalai skills add leoyeai-nevermined-payments

Add it to your agent

import asyncio

from claude_agent_sdk import ClaudeAgentOptions
from decimalai.claude_agent_sdk import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

async def main():
    question = "Hello!"
    async with support.run(question) as run:  # one user message, one run
        async for message in run.query(options=ClaudeAgentOptions(max_turns=6)):
            print(message)

# In a notebook or async code: await main()
asyncio.run(main())

Prefer its own loader? ClaudeAgentOptions(plugins=[skills_plugin()], skills="all") reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

The same install from Python, for a notebook or a setup script. agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[claude-agent-sdk]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nevermined-payments")
if result.exit_code:
    raise SystemExit(result.problems)

import asyncio

from claude_agent_sdk import ClaudeAgentOptions
from decimalai.claude_agent_sdk import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

async def main():
    question = "Hello!"
    async with support.run(question) as run:  # one user message, one run
        async for message in run.query(options=ClaudeAgentOptions(max_turns=6)):
            print(message)

# In a notebook or async code: await main()
asyncio.run(main())

Prefer its own loader? ClaudeAgentOptions(plugins=[skills_plugin()], skills="all") reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nevermined-payments/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from claude_agent_sdk import ClaudeAgentOptions, query

skill = Path(".agents/skills/leoyeai-nevermined-payments/SKILL.md").read_text()
options = ClaudeAgentOptions(system_prompt=f"You are a helpful agent.\n\n{skill}", max_turns=6)

async def main():
    async for message in query(prompt="Hello!", options=options):
        print(message)

# In a notebook or async code: await main()
asyncio.run(main())

This gets SKILL.md only. The skill's 8 other files are not included.

Other ways to add it

Claude Agent SDK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[openai-agents]"
decimalai skills add leoyeai-nevermined-payments

Add it to your agent

from agents import Agent, Runner
from decimalai.openai_agents import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    name=support.name,
    instructions=support.instructions,  # your prompt, then the skill list
    tools=[*support.tools],             # your tools, then load_skill
)
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")

Using SandboxAgent? capabilities=[Shell(), decimalai.openai_agents.sandbox_skills()] points its own loader at the same folder.

Install

pip install "decimalai[openai-agents]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nevermined-payments")
if result.exit_code:
    raise SystemExit(result.problems)

from agents import Agent, Runner
from decimalai.openai_agents import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    name=support.name,
    instructions=support.instructions,  # your prompt, then the skill list
    tools=[*support.tools],             # your tools, then load_skill
)
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")

Using SandboxAgent? capabilities=[Shell(), decimalai.openai_agents.sandbox_skills()] points its own loader at the same folder.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nevermined-payments/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/leoyeai-nevermined-payments/SKILL.md").read_text()
agent = Agent(name="support", instructions=f"You are a helpful agent.\n\n{skill}")
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")

This gets SKILL.md only. The skill's 8 other files are not included.

Other ways to add it

OpenAI Agents docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[openai]"
decimalai skills add leoyeai-nevermined-payments

Add it to your agent

import json

from openai import OpenAI
from decimalai.openai import agent_config

client = OpenAI()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your tools, as Chat Completions takes them, and what answers each.
TOOLS = [{"type": "function", "function": {
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters": {"type": "object", "properties": {"order_id": {"type": "string"}},
                   "required": ["order_id"]},
}}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    # run.system is your prompt, then the skill list.
    messages = [{"role": "system", "content": run.system}, run.message]
    while True:
        reply = client.chat.completions.create(
            model="gpt-5.4-mini",
            messages=messages,
            tools=[*TOOLS, *run.tools],  # your tools, then load_skill
        ).choices[0].message
        messages.append(reply)
        if not reply.tool_calls:
            break
        for call in reply.tool_calls:
            # load_skill is answered by the run; your own tools by FUNCTIONS.
            function = FUNCTIONS.get(call.function.name)
            messages.append(run.tool_result(call) or {
                "role": "tool", "tool_call_id": call.id,
                "content": function(**json.loads(call.function.arguments)) if function
                else f"There is no tool named {call.function.name!r}.",
            })
print(reply.content)

# The Responses API takes run.response_tools instead of run.tools.

Install

pip install "decimalai[openai]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nevermined-payments")
if result.exit_code:
    raise SystemExit(result.problems)

import json

from openai import OpenAI
from decimalai.openai import agent_config

client = OpenAI()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your tools, as Chat Completions takes them, and what answers each.
TOOLS = [{"type": "function", "function": {
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters": {"type": "object", "properties": {"order_id": {"type": "string"}},
                   "required": ["order_id"]},
}}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    # run.system is your prompt, then the skill list.
    messages = [{"role": "system", "content": run.system}, run.message]
    while True:
        reply = client.chat.completions.create(
            model="gpt-5.4-mini",
            messages=messages,
            tools=[*TOOLS, *run.tools],  # your tools, then load_skill
        ).choices[0].message
        messages.append(reply)
        if not reply.tool_calls:
            break
        for call in reply.tool_calls:
            # load_skill is answered by the run; your own tools by FUNCTIONS.
            function = FUNCTIONS.get(call.function.name)
            messages.append(run.tool_result(call) or {
                "role": "tool", "tool_call_id": call.id,
                "content": function(**json.loads(call.function.arguments)) if function
                else f"There is no tool named {call.function.name!r}.",
            })
print(reply.content)

# The Responses API takes run.response_tools instead of run.tools.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nevermined-payments/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/leoyeai-nevermined-payments/SKILL.md").read_text()
reply = client.chat.completions.create(
    model="gpt-5.4-mini",
    messages=[
        {"role": "system", "content": f"You are a helpful agent.\n\n{skill}"},
        {"role": "user", "content": "Hello!"},
    ],
).choices[0].message

This gets SKILL.md only. The skill's 8 other files are not included.

Other ways to add it

OpenAI SDK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[anthropic]"
decimalai skills add leoyeai-nevermined-payments

Add it to your agent

import anthropic
from decimalai.anthropic import agent_config

client = anthropic.Anthropic()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

question = "Hello!"
with support.run(question) as run:  # one user message, one run
    answer = client.beta.messages.tool_runner(
        model="claude-haiku-5-5",
        max_tokens=4096,
        system=run.system,     # your prompt, then the skill list
        tools=[*run.tools],    # your tools, then load_skill
        messages=[{"role": "user", "content": question}],
    ).until_done()

Install

pip install "decimalai[anthropic]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nevermined-payments")
if result.exit_code:
    raise SystemExit(result.problems)

import anthropic
from decimalai.anthropic import agent_config

client = anthropic.Anthropic()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

question = "Hello!"
with support.run(question) as run:  # one user message, one run
    answer = client.beta.messages.tool_runner(
        model="claude-haiku-5-5",
        max_tokens=4096,
        system=run.system,     # your prompt, then the skill list
        tools=[*run.tools],    # your tools, then load_skill
        messages=[{"role": "user", "content": question}],
    ).until_done()

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nevermined-payments/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/leoyeai-nevermined-payments/SKILL.md").read_text()
reply = client.messages.create(
    model="claude-haiku-5-5",
    max_tokens=4096,
    system=f"You are a helpful agent.\n\n{skill}",
    messages=[{"role": "user", "content": "Hello!"}],
)

This gets SKILL.md only. The skill's 8 other files are not included.

Other ways to add it

Anthropic docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[google-genai]"
decimalai skills add leoyeai-nevermined-payments

Add it to your agent

from google import genai
from google.genai import types
from decimalai.google_genai import agent_config

client = genai.Client()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your functions, as declarations for the model, and what answers each.
TOOLS = [{"function_declarations": [{
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters_json_schema": {"type": "object", "properties": {"order_id": {"type": "string"}},
                               "required": ["order_id"]},
}]}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    config = types.GenerateContentConfig(
        system_instruction=run.system,     # your prompt, then the skill list
        tools=[*TOOLS, *run.tool_params],  # your functions, then load_skill
    )
    contents = [{"role": "user", "parts": [{"text": run.message}]}]
    while True:
        response = client.models.generate_content(
            model="gemini-3.5-flash", contents=contents, config=config,
        )
        if not response.function_calls:
            break
        contents.append(response.candidates[0].content)
        parts = []
        for call in response.function_calls:
            # load_skill is answered by the run; your own functions by FUNCTIONS.
            # A loop of your own rather than automatic function calling, which
            # raises KeyError when the model asks for a function you did not pass.
            function = FUNCTIONS.get(call.name)
            parts.append(run.tool_result(call) or {"function_response": {
                "name": call.name, "id": call.id,
                "response": {"result": function(**(call.args or {})) if function
                             else f"There is no function named {call.name!r}."},
            }})
        contents.append({"role": "user", "parts": parts})
print(response.text)

Install

pip install "decimalai[google-genai]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nevermined-payments")
if result.exit_code:
    raise SystemExit(result.problems)

from google import genai
from google.genai import types
from decimalai.google_genai import agent_config

client = genai.Client()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your functions, as declarations for the model, and what answers each.
TOOLS = [{"function_declarations": [{
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters_json_schema": {"type": "object", "properties": {"order_id": {"type": "string"}},
                               "required": ["order_id"]},
}]}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    config = types.GenerateContentConfig(
        system_instruction=run.system,     # your prompt, then the skill list
        tools=[*TOOLS, *run.tool_params],  # your functions, then load_skill
    )
    contents = [{"role": "user", "parts": [{"text": run.message}]}]
    while True:
        response = client.models.generate_content(
            model="gemini-3.5-flash", contents=contents, config=config,
        )
        if not response.function_calls:
            break
        contents.append(response.candidates[0].content)
        parts = []
        for call in response.function_calls:
            # load_skill is answered by the run; your own functions by FUNCTIONS.
            # A loop of your own rather than automatic function calling, which
            # raises KeyError when the model asks for a function you did not pass.
            function = FUNCTIONS.get(call.name)
            parts.append(run.tool_result(call) or {"function_response": {
                "name": call.name, "id": call.id,
                "response": {"result": function(**(call.args or {})) if function
                             else f"There is no function named {call.name!r}."},
            }})
        contents.append({"role": "user", "parts": parts})
print(response.text)

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nevermined-payments/SKILL.md

Give it to your agent

from pathlib import Path
from google import genai
from google.genai import types

client = genai.Client()
skill = Path(".agents/skills/leoyeai-nevermined-payments/SKILL.md").read_text()
response = client.models.generate_content(
    model="gemini-3.5-flash",
    contents="Hello!",
    config=types.GenerateContentConfig(system_instruction=f"You are a helpful agent.\n\n{skill}"),
)

This gets SKILL.md only. The skill's 8 other files are not included.

Other ways to add it

Gemini API docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[langchain]" langchain-openai
decimalai skills add leoyeai-nevermined-payments

Add it to your agent

from langchain.agents import create_agent
from decimalai.langchain import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = create_agent(
    "openai:gpt-5.4-mini",
    tools=[],                         # your tools; the middleware adds load_skill
    middleware=[support.middleware],  # your prompt, the skill list and load_skill
)
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

Install

pip install "decimalai[langchain]" langchain-openai

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nevermined-payments")
if result.exit_code:
    raise SystemExit(result.problems)

from langchain.agents import create_agent
from decimalai.langchain import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = create_agent(
    "openai:gpt-5.4-mini",
    tools=[],                         # your tools; the middleware adds load_skill
    middleware=[support.middleware],  # your prompt, the skill list and load_skill
)
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nevermined-payments/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/leoyeai-nevermined-payments/SKILL.md").read_text()
agent = create_agent("openai:gpt-5.4-mini", tools=[], system_prompt=f"You are a helpful agent.\n\n{skill}")
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

This gets SKILL.md only. The skill's 8 other files are not included.

Other ways to add it

LangChain docs

CrewAI's own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" "crewai>=1.15.27"
decimalai skills add leoyeai-nevermined-payments

Add it to your agent

import decimalai.crewai
from crewai import Agent, Crew, Task

agent = Agent(
    role="Support", goal="Help the customer", backstory="A support agent.",
    llm=llm,                               # your own CrewAI LLM
    skills=decimalai.crewai.skills(),      # the installed folder
    tools=decimalai.crewai.skill_tools(),  # reads a skill's files, runs its scripts
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()

The same install from Python, for a notebook or a setup script. CrewAI's own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" "crewai>=1.15.27"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nevermined-payments")
if result.exit_code:
    raise SystemExit(result.problems)

import decimalai.crewai
from crewai import Agent, Crew, Task

agent = Agent(
    role="Support", goal="Help the customer", backstory="A support agent.",
    llm=llm,                               # your own CrewAI LLM
    skills=decimalai.crewai.skills(),      # the installed folder
    tools=decimalai.crewai.skill_tools(),  # reads a skill's files, runs its scripts
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()

No DecimalAI package. CrewAI's own loader reads the folder, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nevermined-payments/SKILL.md

Give it to your agent

from pathlib import Path
from crewai import Agent, Crew, Task

agent = Agent(
    role="Support", goal="Help the customer", backstory="A support agent.",
    llm=llm,                         # your own CrewAI LLM
    skills=[Path(".agents/skills")],
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()

This gets SKILL.md only. The skill's 8 other files are not included.

Other ways to add it

CrewAI docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[adk]"
decimalai skills add leoyeai-nevermined-payments

Add it to your agent

from decimalai.adk import DecimalAIPlugin, agent_config
from google.adk.agents import LlmAgent
from google.adk.apps import App

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = LlmAgent(
    name="support",          # ADK needs a Python identifier
    model="gemini-3.5-flash",
    instruction=support.instruction,  # your prompt, then the skill list
    tools=[*support.tools],           # your tools, then load_skill
)
# DecimalAIPlugin makes each invocation of runners built from this App one trace.
app = App(name="support", root_agent=agent, plugins=[DecimalAIPlugin()])

Prefer ADK's own loader? SkillToolset(skills=decimalai.adk.skills(), ...) reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

Install

pip install "decimalai[adk]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nevermined-payments")
if result.exit_code:
    raise SystemExit(result.problems)

from decimalai.adk import DecimalAIPlugin, agent_config
from google.adk.agents import LlmAgent
from google.adk.apps import App

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = LlmAgent(
    name="support",          # ADK needs a Python identifier
    model="gemini-3.5-flash",
    instruction=support.instruction,  # your prompt, then the skill list
    tools=[*support.tools],           # your tools, then load_skill
)
# DecimalAIPlugin makes each invocation of runners built from this App one trace.
app = App(name="support", root_agent=agent, plugins=[DecimalAIPlugin()])

Prefer ADK's own loader? SkillToolset(skills=decimalai.adk.skills(), ...) reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nevermined-payments/SKILL.md

Give it to your agent

from pathlib import Path
from google.adk.agents import LlmAgent

skill = Path(".agents/skills/leoyeai-nevermined-payments/SKILL.md").read_text()
agent = LlmAgent(
    name="support",
    model="gemini-3.5-flash",
    instruction=lambda context: f"You are a helpful agent.\n\n{skill}",
)

This gets SKILL.md only. The skill's 8 other files are not included.

Other ways to add it

Google ADK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[pydantic-ai]"
decimalai skills add leoyeai-nevermined-payments

Add it to your agent

from pydantic_ai import Agent
from decimalai.pydantic_ai import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    "openai:gpt-4o-mini",
    name=support.name,
    tools=[],                 # your tools; the capability adds load_skill
    capabilities=[support],   # your prompt, the skill list and load_skill
)
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")

On the Pydantic AI harness, decimalai.pydantic_ai_harness.skills(project) uses its own loader instead.

Install

pip install "decimalai[pydantic-ai]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nevermined-payments")
if result.exit_code:
    raise SystemExit(result.problems)

from pydantic_ai import Agent
from decimalai.pydantic_ai import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    "openai:gpt-4o-mini",
    name=support.name,
    tools=[],                 # your tools; the capability adds load_skill
    capabilities=[support],   # your prompt, the skill list and load_skill
)
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")

On the Pydantic AI harness, decimalai.pydantic_ai_harness.skills(project) uses its own loader instead.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nevermined-payments/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/leoyeai-nevermined-payments/SKILL.md").read_text()
agent = Agent("openai:gpt-4o-mini", instructions=f"You are a helpful agent.\n\n{skill}")
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")

This gets SKILL.md only. The skill's 8 other files are not included.

Other ways to add it

Pydantic AI docs

Deep Agents' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" deepagents
decimalai skills add leoyeai-nevermined-payments

Add it to your agent

import decimalai.deepagents
from deepagents import create_deep_agent

agent = create_deep_agent(model=model, **decimalai.deepagents.skills())
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

The default backend reads files but has no shell. To run a skill's scripts, pass skills(backend=LocalShellBackend(...)).

The same install from Python, for a notebook or a setup script. Deep Agents' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" deepagents

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nevermined-payments")
if result.exit_code:
    raise SystemExit(result.problems)

import decimalai.deepagents
from deepagents import create_deep_agent

agent = create_deep_agent(model=model, **decimalai.deepagents.skills())
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

The default backend reads files but has no shell. To run a skill's scripts, pass skills(backend=LocalShellBackend(...)).

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nevermined-payments/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/leoyeai-nevermined-payments/SKILL.md").read_text()
agent = create_deep_agent(model=model, system_prompt=f"You are a helpful agent.\n\n{skill}")
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

This gets SKILL.md only. The skill's 8 other files are not included.

Other ways to add it

Deep Agents docs

Its own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" agent-framework
decimalai skills add leoyeai-nevermined-payments

Add it to your agent

import asyncio

from agent_framework import Agent
from decimalai.agent_framework import skills

agent = Agent(client=client, instructions="You are a helpful agent.", context_providers=[skills()])
asyncio.run(agent.run("Hello!"))

It caches skills by default, so restart the process after decimalai skills update.

The same install from Python, for a notebook or a setup script. Its own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" agent-framework

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nevermined-payments")
if result.exit_code:
    raise SystemExit(result.problems)

import asyncio

from agent_framework import Agent
from decimalai.agent_framework import skills

agent = Agent(client=client, instructions="You are a helpful agent.", context_providers=[skills()])
asyncio.run(agent.run("Hello!"))

It caches skills by default, so restart the process after decimalai skills update.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nevermined-payments/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/leoyeai-nevermined-payments/SKILL.md").read_text()
agent = Agent(client=client, instructions=f"You are a helpful agent.\n\n{skill}")
asyncio.run(agent.run("Hello!"))

This gets SKILL.md only. The skill's 8 other files are not included.

Other ways to add it

Microsoft Agent Framework docs

Strands' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" strands-agents
decimalai skills add leoyeai-nevermined-payments

Add it to your agent

from decimalai.strands import skills
from strands import Agent
from strands.vended_tools import file_editor, shell

agent = Agent(
    model=model,                # always pass one: the default is Amazon Bedrock
    system_prompt="You are a helpful agent.",
    tools=[file_editor, shell],
    plugins=[skills()],
)
agent("Hello!")

Strands loads an agent's skills once, so build the agent again after decimalai skills update.

The same install from Python, for a notebook or a setup script. Strands' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" strands-agents

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nevermined-payments")
if result.exit_code:
    raise SystemExit(result.problems)

from decimalai.strands import skills
from strands import Agent
from strands.vended_tools import file_editor, shell

agent = Agent(
    model=model,                # always pass one: the default is Amazon Bedrock
    system_prompt="You are a helpful agent.",
    tools=[file_editor, shell],
    plugins=[skills()],
)
agent("Hello!")

Strands loads an agent's skills once, so build the agent again after decimalai skills update.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nevermined-payments/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/leoyeai-nevermined-payments/SKILL.md").read_text()
agent = Agent(model=model, system_prompt=f"You are a helpful agent.\n\n{skill}")
agent("Hello!")

This gets SKILL.md only. The skill's 8 other files are not included.

Other ways to add it

Strands docs

Adds every file the skill has, pinned so you can update it. Cursor, Copilot, Cline and Warp read this folder by themselves.

pip install "decimalai>=0.15"
decimalai skills add leoyeai-nevermined-payments

No Python or account. Cursor, Copilot, Cline and Warp read this folder by themselves.

Save it into your project

curl -fsSL --create-dirs -o .agents/skills/leoyeai-nevermined-payments/SKILL.md https://app.decimal.ai/s/leoyeai-nevermined-payments/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nevermined-payments/SKILL.md

This gets SKILL.md only. The skill's 8 other files are not included.

Other ways to add it

Cursor and other editors docs

Fetch the file and give its text to your model as instructions. No account or package needed.

Get the file

curl -fsSL https://app.decimal.ai/s/leoyeai-nevermined-payments/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/leoyeai-nevermined-payments.json

This gets SKILL.md only. The skill's 8 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 8/8/2026
Source: LeoYeAI/openclaw-master-skills ↗
License: MIT

Manage it in DecimalAI

Saved prompts and skills, pinned versions, and traces of this skill in your runs. DecimalAI does not run your agent.

Claude Code reads files from your project, so DecimalAI config does not apply there.

On Claude Agent SDK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On OpenAI Agents: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On OpenAI SDK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Anthropic: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Gemini API: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On LangChain: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On CrewAI: set DECIMAL_API_KEY and add decimalai.init(crewai=True) to record runs and skill use. The skill version stays in your repo.

On Google ADK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Pydantic AI: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Deep Agents: set DECIMAL_API_KEY and add decimalai.init(langchain=True) to record runs and skill use. The skill version stays in your repo.

On Microsoft Agent Framework: set DECIMAL_API_KEY and add decimalai.init(otel=True, agent_name="support") to record runs and skill use. The skill version stays in your repo.

On Strands: set DECIMAL_API_KEY and add decimalai.init(otel=True, agent_name="support") to record runs and skill use. The skill version stays in your repo.

Editors read files from your project, so DecimalAI config does not apply there.

Anywhere else: record a use with decimalai.log_skill_activation() inside a trace.

Use this skill

SKILL.md

Nevermined Payments Integration

Overview

Nevermined provides financial rails for AI agents — real-time monetization, access control, and payments. This skill gives you everything needed to:

Protect API endpoints with the x402 payment protocol
Charge per-request using credit-based billing
Integrate with Express.js, FastAPI, Strands agents, MCP servers, or Google A2A agents
Support subscriber-side flows (purchase plans, generate tokens, call protected APIs)
Enable agent-to-agent payments via the Google A2A protocol

The x402 protocol uses HTTP 402 responses to advertise payment requirements. Clients acquire an access token and retry the request. The server verifies permissions, executes the workload, then settles (burns credits).

Quick Start Checklist

Get an API key at nevermined.app → Settings → API Keys
Install the SDK (npm install @nevermined-io/payments or pip install payments-py)
Register your agent and plan (via the App UI or programmatically — see references/payment-plans.md)
Add payment protection to your routes/tools (see framework-specific references below)
Test — call without token (expect 402), then with token (expect 200)

Environment Setup

Variable	Required	Description
`NVM_API_KEY`	Yes	Your Nevermined API key (get it at nevermined.app → Settings → API Keys)
`NVM_ENVIRONMENT`	Yes	`sandbox` for testing, `live` for production
`NVM_PLAN_ID`	Yes	The plan ID from registration
`NVM_AGENT_ID`	Sometimes	Required for MCP servers and plans with multiple agents
`BUILDER_ADDRESS`	For registration	Wallet address to receive payments

`.env` Template

# Required
NVM_API_KEY=your-api-key-here
NVM_ENVIRONMENT=sandbox
NVM_PLAN_ID=your-plan-id-here

# Required for MCP servers or multi-agent plans
NVM_AGENT_ID=your-agent-id-here

# Required for registration
BUILDER_ADDRESS=0xYourWalletAddress

Prerequisites

TypeScript/Express.js: Node.js 18+. Your package.json must include "type": "module" for the @nevermined-io/payments/express subpath import to work.
Python/FastAPI: Python 3.9+. Install with pip install payments-py[fastapi] — the [fastapi] extra is required for the middleware.

TypeScript

npm install @nevermined-io/payments

import { Payments } from '@nevermined-io/payments'

const payments = Payments.getInstance({
  nvmApiKey: process.env.NVM_API_KEY!,
  environment: 'sandbox'
})

Python

pip install payments-py

import os
from payments_py import Payments, PaymentOptions

payments = Payments.get_instance(
    PaymentOptions(
        nvm_api_key=os.environ["NVM_API_KEY"],
        environment="sandbox"
    )
)

Core Workflow (All Integrations)

Every Nevermined payment integration follows this 5-step pattern:

Client sends request without a payment token
Server returns 402 with payment-required header (base64-encoded JSON with plan info)
Client acquires x402 token via payments.x402.getX402AccessToken(planId, agentId)
Client retries with payment-signature header containing the token
Server verifies → executes → settles (burns credits), returns response with payment-response header

Framework Decision Tree

Choose the integration that matches your stack:

Framework	Language	Reference	Key Import
Express.js	TypeScript/JS	`references/express-integration.md`	`paymentMiddleware` from `@nevermined-io/payments/express`
FastAPI	Python	`references/fastapi-integration.md`	`PaymentMiddleware` from `payments_py.x402.fastapi`
Strands Agent	Python	`references/strands-integration.md`	`@requires_payment` from `payments_py.x402.strands`
MCP Server	TypeScript	`references/mcp-paywall.md`	`payments.mcp.start()` / `payments.mcp.registerTool()`
Google A2A	TS / Python	`references/a2a-integration.md`	`payments.a2a.start()` / `payments.a2a.buildPaymentAgentCard()`
Any HTTP	Any	`references/x402-protocol.md`	Manual verify/settle via facilitator API
Client-side	TS / Python	`references/client-integration.md`	`payments.x402.getX402AccessToken()`

SDK Quick Reference

TypeScript (`@nevermined-io/payments`)

// Initialize
const payments = Payments.getInstance({ nvmApiKey, environment })

// Register agent + plan
const { agentId, planId } = await payments.agents.registerAgentAndPlan(
  agentMetadata, agentApi, planMetadata, priceConfig, creditsConfig
)

// Subscriber: order plan and get token
await payments.plans.orderPlan(planId)
const balance = await payments.plans.getPlanBalance(planId)
const { accessToken } = await payments.x402.getX402AccessToken(planId, agentId)

// Server: verify and settle
const verification = await payments.facilitator.verifyPermissions({
  paymentRequired, x402AccessToken: token, maxAmount: BigInt(credits)
})
const settlement = await payments.facilitator.settlePermissions({
  paymentRequired, x402AccessToken: token, maxAmount: BigInt(creditsUsed)
})

// Helpers
import { buildPaymentRequired } from '@nevermined-io/payments'
import { paymentMiddleware, X402_HEADERS } from '@nevermined-io/payments/express'

// MCP server
payments.mcp.registerTool(name, config, handler, { credits: 5n })
const { info, stop } = await payments.mcp.start({ port, agentId, serverName })

// A2A server
const agentCard = payments.a2a.buildPaymentAgentCard(baseCard, { paymentType, credits, planId, agentId })
const server = await payments.a2a.start({ port, basePath: '/a2a/', agentCard, executor })
// A2A client
const client = payments.a2a.getClient({ agentBaseUrl, agentId, planId })
await client.sendMessage("Hello", accessToken)

Python (`payments-py`)

# Initialize
payments = Payments.get_instance(PaymentOptions(nvm_api_key=key, environment="sandbox"))

# Register agent + plan
result = payments.agents.register_agent_and_plan(
    agent_metadata, agent_api, plan_metadata, price_config, credits_config
)

# Subscriber: order plan and get token
payments.plans.order_plan(plan_id)
balance = payments.plans.get_plan_balance(plan_id)
token_res = payments.x402.get_x402_access_token(plan_id, agent_id)

# Server: verify and settle
verification = payments.facilitator.verify_permissions(
    payment_required=pr, x402_access_token=token, max_amount=str(credits)
)
settlement = payments.facilitator.settle_permissions(
    payment_required=pr, x402_access_token=token, max_amount=str(credits_used)
)

# Helpers
from payments_py.x402.helpers import build_payment_required
from payments_py.x402.fastapi import PaymentMiddleware
from payments_py.x402.strands import requires_payment

# A2A server
from payments_py.a2a.agent_card import build_payment_agent_card
from payments_py.a2a.server import PaymentsA2AServer
agent_card = build_payment_agent_card(base_card, { ... })
server = PaymentsA2AServer.start(agent_card=agent_card, executor=executor, payments_service=payments, port=3005)
# A2A client
client = payments.a2a.get_client(agent_base_url=url, agent_id=agent_id, plan_id=plan_id)

x402 Payment Headers

All x402 v2 integrations use these three HTTP headers:

Header	Direction	Description
`payment-signature`	Client → Server	x402 access token
`payment-required`	Server → Client (402)	Base64-encoded JSON with plan requirements
`payment-response`	Server → Client (200)	Base64-encoded JSON settlement receipt

The payment-required payload structure:

{
  "x402Version": 2,
  "accepts": [{
    "scheme": "nvm:erc4337",
    "network": "eip155:84532",
    "planId": "<plan-id>",
    "extra": { "agentId": "<agent-id>" }
  }]
}

Payment Plan Types

Nevermined supports several plan types:

Credits-based: prepaid balance, deducted per request (most common for APIs)
Time-based: access for a fixed duration (e.g., 30 days unlimited)
Pay-as-you-go (PAYG): settle in USDC per request, no credit balance
Trial: free limited access, one-time claim per user
Hybrid: combine credits with time expiry

See references/payment-plans.md for plan registration code.

Common Patterns

Express.js — Fixed credits per route

import { paymentMiddleware } from '@nevermined-io/payments/express'

app.use(paymentMiddleware(payments, {
  'POST /ask': { planId: PLAN_ID, credits: 1 },
  'POST /generate': { planId: PLAN_ID, credits: 5 }
}))

FastAPI — Fixed credits per route

from payments_py.x402.fastapi import PaymentMiddleware

app.add_middleware(
    PaymentMiddleware,
    payments=payments,
    routes={
        "POST /ask": {"plan_id": PLAN_ID, "credits": 1},
        "POST /generate": {"plan_id": PLAN_ID, "credits": 5}
    }
)

Express.js — Dynamic credits based on response

paymentMiddleware(payments, {
  'POST /generate': {
    planId: PLAN_ID,
    credits: (req, res) => {
      const tokens = res.locals.tokenCount || 100
      return Math.ceil(tokens / 100)
    }
  }
})

FastAPI — Dynamic credits based on request

async def calculate_credits(request: Request) -> int:
    body = await request.json()
    max_tokens = body.get("max_tokens", 100)
    return max(1, max_tokens // 100)

app.add_middleware(
    PaymentMiddleware,
    payments=payments,
    routes={"POST /generate": {"plan_id": PLAN_ID, "credits": calculate_credits}}
)

MCP Server — Register tool with paywall

payments.mcp.registerTool(
  "weather.today",
  { title: "Today's Weather", inputSchema: z.object({ city: z.string() }) },
  async (args, extra, context) => ({
    content: [{ type: "text", text: `Weather in ${args.city}: Sunny, 25C` }]
  }),
  { credits: 5n }
)

const { info, stop } = await payments.mcp.start({
  port: 3000,
  agentId: process.env.NVM_AGENT_ID!,
  serverName: "my-server"
})

Strands Agent — Decorator-based payment

from strands import Agent, tool
from payments_py.x402.strands import requires_payment

@tool(context=True)
@requires_payment(payments=payments, plan_id=PLAN_ID, credits=1)
def analyze_data(query: str, tool_context=None) -> dict:
    return {"status": "success", "content": [{"text": f"Analysis: {query}"}]}

agent = Agent(tools=[analyze_data])

Google A2A — Agent server with payment extension

TypeScript

const agentCard = payments.a2a.buildPaymentAgentCard(baseAgentCard, {
  paymentType: "dynamic",
  credits: 1,
  planId: process.env.NVM_PLAN_ID!,
  agentId: process.env.NVM_AGENT_ID!,
})

const server = await payments.a2a.start({
  port: 3005,
  basePath: '/a2a/',
  agentCard,
  executor: new MyExecutor(),
})

Python

from payments_py.a2a.agent_card import build_payment_agent_card
from payments_py.a2a.server import PaymentsA2AServer

agent_card = build_payment_agent_card(base_agent_card, {
    "paymentType": "dynamic",
    "credits": 1,
    "planId": os.environ["NVM_PLAN_ID"],
    "agentId": os.environ["NVM_AGENT_ID"],
})

server = PaymentsA2AServer.start(
    agent_card=agent_card,
    executor=MyExecutor(),
    payments_service=payments,
    port=3005,
    base_path="/a2a/",
)

Google A2A — Client sending a paid task

const client = payments.a2a.getClient({
  agentBaseUrl: 'http://localhost:3005/a2a/',
  agentId: AGENT_ID,
  planId: PLAN_ID,
})

const { accessToken } = await payments.x402.getX402AccessToken(PLAN_ID, AGENT_ID)
const response = await client.sendMessage("Analyze this data", accessToken)

Gathering Developer Information Upfront

When a developer asks you to integrate Nevermined payments, gather ALL required information in a single question before generating code. This avoids multiple back-and-forth interactions.

Ask the developer once for:

Framework: Express.js, FastAPI, MCP server, Strands agent, Google A2A, or generic HTTP?
Routes to protect: Which endpoints need payment protection and how many credits each? (e.g., POST /chat = 1 credit, POST /generate = 5 credits)
Pricing model: Fixed credits per request, or dynamic pricing based on request/response parameters?
Nevermined API Key: Do they already have an NVM_API_KEY? If not, direct them to nevermined.app → Settings → API Keys
Plan ID: Do they already have a NVM_PLAN_ID? If not, do they need a registration script too?
Environment: sandbox (testing) or live (production)?

If they need plan registration, also ask:

Plan name and description: e.g., "Starter Plan — 100 API requests"
Pricing: How much in USDC? (e.g., 10 USDC for 100 credits)
Credits per plan: Total credits included (e.g., 100)
Builder wallet address (BUILDER_ADDRESS): The wallet that receives payments

Example combined prompt to offer the developer:

I need to set up Nevermined payments. Here's my info:

Framework: Express.js

Routes: POST /chat (1 credit), POST /summarize (3 credits)

I need a registration script too

Plan: "Starter Plan", 100 credits for 10 USDC

Environment: sandbox

My API key is in the NVM_API_KEY env var

My wallet: 0x1234...

With this information, generate both the registration script and the payment-protected server in a single response.

Agent and Plan Registration

Using the SDK (Recommended)

// TypeScript
const { agentId, planId } = await payments.agents.registerAgentAndPlan(
  { name: 'My Agent', description: 'AI service', tags: ['ai'], dateCreated: new Date() },
  { endpoints: [{ POST: 'https://your-api.com/query' }] },
  { name: 'Starter Plan', description: '100 requests for $10', dateCreated: new Date() },
  payments.plans.getERC20PriceConfig(10_000_000n, USDC_ADDRESS, process.env.BUILDER_ADDRESS!),
  payments.plans.getFixedCreditsConfig(100n, 1n)
)

# Python
result = payments.agents.register_agent_and_plan(
    agent_metadata={'name': 'My Agent', 'description': 'AI service', 'tags': ['ai']},
    agent_api={'endpoints': [{'POST': 'https://your-api.com/query'}]},
    plan_metadata={'name': 'Starter Plan', 'description': '100 requests for $10'},
    price_config=get_erc20_price_config(10_000_000, USDC_ADDRESS, os.environ['BUILDER_ADDRESS']),
    credits_config=get_fixed_credits_config(100, 1)
)

Using the Nevermined App (No-Code)

Go to nevermined.app and sign in
Click "My agents" → register a new agent with metadata and endpoints
Create a payment plan: set pricing, credits, and duration
Link the plan to your agent and publish
Copy the agentId and planId for your .env file

Using the CLI

# 1. Install CLI
npm install -g @nevermined-io/cli

# 2. Configure (use sandbox for testing)
nvm config init --api-key "$NVM_API_KEY" --environment sandbox

# 3. Register agent and plan together
nvm agents register-agent-and-plan \
  --agent-metadata '{"name":"My Agent","description":"AI service"}' \
  --agent-api '{"endpoints":[{"POST":"https://your-api.com/query"}]}' \
  --plan-metadata '{"name":"Starter Plan","description":"100 requests"}' \
  --price-config '{"tokenAddress":"0x036CbD53842c5426634e7929541eC2318f3dCF7e","price":10000000,"amountOfCredits":100}' \
  --credits-config '{"minCreditsRequired":1,"minCreditsToCharge":1,"maxCreditsToCharge":10}'

# 4. List your plans
nvm plans get-plans

# 5. As a subscriber: order a plan and get an x402 token
nvm plans order-plan $PLAN_ID
nvm x402token get-x402-access-token $PLAN_ID --agent-id $AGENT_ID

# 6. Test against your running server
curl -X POST http://localhost:3000/chat \
  -H "Content-Type: application/json" \
  -H "payment-signature: $TOKEN" \
  -d '{"message": "Hello"}'

Troubleshooting

Symptom	Cause	Fix
HTTP 402 returned	No `payment-signature` header or invalid/expired token	Generate a fresh token via `getX402AccessToken`
MCP error `-32003`	Payment Required — no token, invalid token, or insufficient credits	Check subscriber has purchased plan and has credits remaining
MCP error `-32002`	Server misconfiguration	Verify `NVM_API_KEY`, `NVM_PLAN_ID`, and `NVM_AGENT_ID` are set correctly
`verification.isValid` is false	Token expired, wrong plan, or insufficient credits	Re-order the plan or generate a new token
Credits not deducting	Settlement not called after request	Ensure you call `settlePermissions` after processing (middleware does this automatically)
`payment-required` header missing	Server not returning 402 properly	Use `buildPaymentRequired()` helper or framework middleware

Additional Resources

Documentation: nevermined.ai/docs
Nevermined App: nevermined.app — register agents, create plans, manage subscriptions
MCP Search Server: https://docs.nevermined.app/mcp — search Nevermined docs from any MCP client
Tutorials: github.com/nevermined-io/tutorials
Discord: discord.com/invite/GZju2qScKq
TypeScript SDK: @nevermined-io/payments on npm
Python SDK: payments-py on PyPI

About this skill

Automatic

AI Engineer pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

LeoYeAI / openclaw-master-skills

skills/nevermined-payments/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1Bundled 8 files

Illustrative Want to see what leoyeai/nevermined-payments would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Related skills

Skills that do similar work, with their headline benchmark lift.

From the same source and nearby in the catalogue.

Ready to supercharge your AI agents?

SkillScore

Safety

What it changes

Track record

Use this skill

Nevermined Payments Integration

Overview

Quick Start Checklist

Environment Setup

.env Template

Prerequisites

TypeScript

Python

Core Workflow (All Integrations)

Framework Decision Tree

SDK Quick Reference

TypeScript (@nevermined-io/payments)

Python (payments-py)

x402 Payment Headers

Payment Plan Types

Common Patterns

Express.js — Fixed credits per route

FastAPI — Fixed credits per route

Express.js — Dynamic credits based on response

FastAPI — Dynamic credits based on request

MCP Server — Register tool with paywall

Strands Agent — Decorator-based payment

Google A2A — Agent server with payment extension

TypeScript

Python

Google A2A — Client sending a paid task

Gathering Developer Information Upfront

Agent and Plan Registration

Using the SDK (Recommended)

Using the Nevermined App (No-Code)

Using the CLI

Troubleshooting

Additional Resources

SkillSafety

Source

Related skills

More in the registry

`.env` Template

TypeScript (`@nevermined-io/payments`)

Python (`payments-py`)