Ready to supercharge your AI agents?

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

x402 + ERC-7710 · internet-court | DecimalAI

Financeby internet-court

x402 + ERC-7710

Design and implement demos combining x402 HTTP payments with ERC-7710 smart contract delegations and ERC-7715 wallet permission requests for subscriptions, bounded agent budgets, recurring spend, pay-per-use APIs, and agentic commerce.

Never made a case worse

SkillScore

SkillScore95/100

Test results 95

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

36%95%of test cases passed +59 pts

Without skill8 of 22

With skill21 of 22

13 fixed8 passed either way1 still failing0 broke

Measured on gemini-3.6-flash8/12/2026v1

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskWhat default price, per-request cap, weekly spend budget, and chain network should be configured if a developer asks for a standard baseline demo of x402 plus ERC-7710?

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 internet-court-x402-erc7710
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("internet-court-x402-erc7710")
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 internet-court-x402-erc7710

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/internet-court-x402-erc7710/SKILL.md https://app.decimal.ai/s/internet-court-x402-erc7710/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/internet-court-x402-erc7710/SKILL.md

This gets SKILL.md only. The skill's 1 other file is 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 internet-court-x402-erc7710

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("internet-court-x402-erc7710")
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/internet-court-x402-erc7710/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/internet-court-x402-erc7710/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 1 other file is 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 internet-court-x402-erc7710

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("internet-court-x402-erc7710")
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/internet-court-x402-erc7710/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/internet-court-x402-erc7710/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 1 other file is 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 internet-court-x402-erc7710

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("internet-court-x402-erc7710")
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/internet-court-x402-erc7710/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/internet-court-x402-erc7710/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 1 other file is 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 internet-court-x402-erc7710

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("internet-court-x402-erc7710")
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/internet-court-x402-erc7710/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/internet-court-x402-erc7710/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 1 other file is 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 internet-court-x402-erc7710

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("internet-court-x402-erc7710")
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/internet-court-x402-erc7710/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/internet-court-x402-erc7710/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 1 other file is 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 internet-court-x402-erc7710

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("internet-court-x402-erc7710")
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/internet-court-x402-erc7710/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/internet-court-x402-erc7710/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 1 other file is 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 internet-court-x402-erc7710

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("internet-court-x402-erc7710")
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/internet-court-x402-erc7710/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 1 other file is 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 internet-court-x402-erc7710

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("internet-court-x402-erc7710")
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/internet-court-x402-erc7710/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/internet-court-x402-erc7710/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 1 other file is 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 internet-court-x402-erc7710

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("internet-court-x402-erc7710")
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/internet-court-x402-erc7710/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/internet-court-x402-erc7710/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 1 other file is 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 internet-court-x402-erc7710

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("internet-court-x402-erc7710")
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/internet-court-x402-erc7710/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/internet-court-x402-erc7710/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 1 other file is 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 internet-court-x402-erc7710

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("internet-court-x402-erc7710")
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/internet-court-x402-erc7710/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/internet-court-x402-erc7710/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 1 other file is 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 internet-court-x402-erc7710

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("internet-court-x402-erc7710")
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/internet-court-x402-erc7710/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/internet-court-x402-erc7710/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 1 other file is 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 internet-court-x402-erc7710

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/internet-court-x402-erc7710/SKILL.md https://app.decimal.ai/s/internet-court-x402-erc7710/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/internet-court-x402-erc7710/SKILL.md

This gets SKILL.md only. The skill's 1 other file is 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/internet-court-x402-erc7710/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/internet-court-x402-erc7710.json

This gets SKILL.md only. The skill's 1 other file is not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 8/12/2026
Source: internet-court/internet-court-skill ↗
License: NOASSERTION

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

x402 + ERC-7710

Use this skill when a user wants a payment or subscription demo where an agent pays for HTTP resources through x402 and spends only within a bounded delegated permission.

Core Model

x402 is the per-request payment rail. A protected resource can respond with HTTP 402 Payment Required, payment requirements, and a retry path where the client submits a signed payment payload. A facilitator can verify and settle the payment before the server returns the resource.
ERC-7710 is the capability redemption interface. It standardizes how a delegation manager validates permission context and executes delegated actions on behalf of a delegator.
ERC-7715 is the wallet permission request layer that can be used to obtain scoped permissions for ERC-7710-style delegation.

Use x402 for "pay now for this HTTP request." Use ERC-7710/7715 for "this agent may keep paying under these constraints."

Discovery-First Boundary

When the user has only asked to use or inspect a paid HTTP service, stay in discovery mode:

Identify the relevant endpoint or resource.
Confirm whether it returns 402 Payment Required.
Summarize the advertised x402 requirements: network, token, amount, payee, route, and extra.assetTransferMethod when present.
State that no paid request has been made.
Ask whether the user wants to set up bounded payment authority.

Do not draft a subscription, mandate, cadence, schedule, spend cap, expiration, or wallet permission until the user asks for setup or confirms they want to continue. Do not infer "daily", "weekly", or "recurring" authority from a product objective alone; wait for the user to approve delegation design.

Good discovery response shape:

I found the paid endpoint and its x402 requirements.

- Endpoint: GET /path
- Network: ...
- Token: ...
- Price: ...
- Payee: ...

I have not made a paid request. Do you want me to help set up bounded payment authority for this task?

Trust Objection Mode

When the user objects to trusting the agent with money, keep the options distinct:

Basic: an agent-controlled funded wallet. This is not a scoped x402/ERC-7710 permission unless another component enforces it. The main limit is the wallet balance.
Guarded: a user-approved smart-account or wallet permission that limits service, route, token, payee, amount, budget period, request count, and expiry.
Adjudicated: guarded permission plus signed intent/receipt evidence and a review path that can continue, constrain, or revoke future use.

Do not assign exact route, price, cadence, or expiry values to the Basic option. Those constraints belong in Guarded or Adjudicated setup after the user chooses that path.

Adjudicated Setup Mode

When the user selects adjudicated authority, proceed to setup instead of drafting a final mandate artifact immediately.

The right response is operational:

confirm adjudicated mode;
state that setup may take a while;
list the steps to create an agent session key, prepare the bounded wallet permission request, open user wallet approval, store the permission artifact, verify the x402 requirements, configure signed evidence, and prepare the review path;
ask the user to approve the guarded wallet permission in their wallet UI;
wait for the user's approval message.

Do not ask for arbitrary expiration, schedule, or spend-cap choices in this beat unless the previous conversation lacks enough facts to create a safe testnet permission request. Do not claim the permission is ready before the user approves it.

Subscription Pattern

For subscriptions, do not make x402 stateful. Keep x402 as the request payment protocol and put recurrence in the delegated spend policy.

Recommended policy fields:

type AgentSpendPolicy = {
  delegator: `0x${string}`;
  delegate: `0x${string}`;
  token: `0x${string}`;
  allowedPayTo: `0x${string}`;
  allowedResourcePattern: string;
  maxPerRequest: bigint;
  maxPerPeriod: bigint;
  periodSeconds: number;
  validAfter: number;
  validUntil: number;
  chainId: number;
  revocable: boolean;
};

Execution flow:

User grants a scoped permission through wallet UX, ideally ERC-7715 when available.
The returned permission context is stored by the agent or subscription manager.
Agent requests an x402-protected endpoint.
Server returns payment requirements.
Agent verifies requirements against the policy: network, token, amount, merchant, route, expiry, and remaining budget.
Agent redeems the ERC-7710 delegation or otherwise executes through the user's smart account to produce the payment authorization.
Agent retries the HTTP request with the x402 payment payload.
Server or facilitator verifies and settles payment.
Subscription manager records spend and receipt for audit, revocation, and disputes.
For supervised wallets, a reporter contract or watcher submits spend snapshots to GenLayer on the review cadence.

Default Demo

Build Agent Research Pass unless the user asks otherwise:

Resource: /api/evidence/report.
Price: 0.05 USDC per report over x402.
Delegation: agent can spend up to 5 USDC per week, max 0.25 USDC per request, only to the provider wallet, only on Base Sepolia or another agreed testnet, expiring in seven days.
Result: the provider returns a signed evidence report with sources and timestamp.
Dispute: if the report is missing, malformed, late, or source-incompatible, route the receipt and report to Internet Court, Arkhai, or GenLayer for refund/release.

Browser Lab Pattern

When building an exploratory dashboard, use this shape:

The user connects their wallet on Base Sepolia and requests ERC-7715 execution permissions.
The page generates a real agent EOA for the demo and exports a JSON package containing the agent private key, ERC-7710 permission context, permission manager, x402 policy, and GenLayer control metadata.
Keep the first asset to Base Sepolia USDC unless the user asks for multi-chain or multi-token support.
Prefer erc20-token-periodic for recurring agent spend, erc20-token-allowance for one-shot budgets, and erc20-token-stream only when continuous accrual is central to the demo.
The x402 service must advertise extra.assetTransferMethod = "erc7710" or the MetaMask x402 client should refuse the payment.
Support multiple allowed HTTP resources in the exported agent package when the service exposes more than one paid route.
Route allowlists are initially enforced by the agent policy before each request. Do not claim route-level malicious-agent resistance unless a custom caveat, smart-account module, or facilitator-bound route proof is implemented.

The exported agent package is a bearer capability in demo form. Include explicit warnings, keep caps tiny, and never export production private keys.

The same delegated-wallet pattern can support non-x402 actions when the wallet and delegation manager expose them: ERC-20 allowance, ERC-20 periodic spend, ERC-20 streams, native token permissions, token approval revocation, and general contract executions through delegation scopes.

Conversational Operator Mode

When the user wants to operate this demo by talking to Codex instead of using a UI, offer a concrete menu before implementing:

Inspect x402 resources and confirm extra.assetTransferMethod = "erc7710".
Generate or import a real Base Sepolia agent wallet.
Draft an ERC-7715 permission request for MetaMask approval.
Build an agent JSON package containing agent key, permission context, allowed resources, budgets, and GenLayer control metadata.
Run or prepare an agent x402 payment attempt from that package.
Build a GenLayer decision payload for continue, warn, constrain, revoke, or escalate.
Apply a revocation/constrain decision through the local EVM controller path when configured.
Extend the demo to non-x402 delegated actions such as token budgets, native token budgets, approval revocation, or contract calls.

Ask direct implementation choices when the user has not specified them, especially:

dashboard vs chat-first flow;
generated agent wallet vs imported agent wallet;
include private key in exported JSON or omit it;
allowed resource paths;
permission type: ERC-20 periodic, ERC-20 allowance, ERC-20 stream, native token allowance, approval revocation, or contract call;
manual demo relay vs trusted watcher vs production bridge for GenLayer decisions.

State the wallet boundary clearly: Codex can prepare the ERC-7715 request, scripts, and artifact, but the user must approve MetaMask wallet prompts. Do not claim Codex can silently grant wallet permissions.

MetaMask Transaction Cards

When the user wants to deploy or configure contracts from MetaMask or WalletConnect:

Never ask for private keys.
Do not invent constructor args or calldata from contract names. Read the source, ABI, or deployment script first.
Show one approval card at a time unless the user asks for a batch.
Do not mark a step complete until the user provides a tx hash, signed artifact, deployed address, or receipt.
Validate receipt proofs before advancing: EVM tx hashes are 0x plus 64 hex characters, and EVM addresses are 0x plus 40 hex characters. Malformed values are not receipts.
If the user explicitly says a proof is simulated or mocked, label the resulting state as simulated and never present it as actually deployed.
If no QR backend exists, show an approval-card summary and say the QR is pending UI implementation.
Do not paste full deployment bytecode or full calldata in chat by default, including permission grants, wallet delegation artifacts, review relay calls, and payment cards. Show selector, hash, byte length, exact args, expected reads, and proof needed; provide the raw payload only on request or as a hidden wallet/backend field.

For the local Internet Court x402 demo, WalletSpendReporter takes the Base BridgeSender.sol address 0x7AB80AE93246108bd1e80b8215c5F1147Ca56af0 as initialBridgeSender. Do not use the Base BridgeReceiver address 0xF92d8e5F1620E464eEac5fab5472dA06fbfA5C73 or the GenLayer BridgeSender Intelligent Contract there. The GenLayer BridgeSender Intelligent Contract is only for the GenLayer supervisor constructor.

For the local Internet Court x402 demo, GenLayerDecisionReceiver.initialSourceContract is the GenLayer supervisor address once known. If the supervisor is not deployed yet, ask for an explicit temporary nonzero placeholder and label it as temporary; never silently use the GenLayer BridgeSender Intelligent Contract as that placeholder.

Periodic GenLayer Control

For supervised delegated payments, model review cadence in the mandate and artifact:

demo cadence: one minute is acceptable for visible iteration;
production-style cadence: twenty-four hours or a risk-based window;
decisions: continue, warn, constrain, revoke, or escalate;
effect path: Base spend reporter -> GenLayer Studio bridge -> GenLayer spend supervisor -> GenLayer Studio bridge -> EVM decision receiver -> revocation or constraint controller -> future ERC-7710 redemptions fail or tighten.

Never say GenLayer directly revokes ERC-7710 unless the EVM-side controller or caveat check has been wired into the redemption path.

Other Demo Ideas

Compute Credits: agent has a daily delegated budget for GPU or inference calls.
Oracle Resolution Credits: prediction-market oracles charge per resolution attempt via x402 while ERC-7710 caps the market operator's spend.
Premium Crawler: agent pays per crawled page but only for whitelisted domains and a fixed monthly budget.
SaaS Seat for Agents: an organization grants an agent a time-bounded subscription permission instead of sharing credentials.
Dispute Insurance: every x402 payment includes a small escrowed premium; disputed deliveries route to GenLayer or Arkhai.

Implementation Checklist

When asked to implement or spec a demo, produce:

Resource server routes and x402 payment requirements.
Buyer agent wallet and delegated permission policy.
Permission request shape, noting whether ERC-7715 is available in the target wallet.
Policy validation before each payment.
Payment receipt store with parent request id, route, amount, token, chain, merchant, tx hash, and timestamp.
Spend snapshot source, such as an x402 permission manager with spent, requestCount, and a generic getDelegatedSpendSnapshot.
GenLayer bridge reporter and decision receiver addresses for Base Sepolia when the demo needs bridge-backed revocation.
Revocation and expiry behavior.
Dispute path and evidence bundle.
Test plan with over-budget, wrong merchant, expired permission, wrong route, failed settlement, stale bridge decision, duplicate bridge message, and replay attempts.

Guardrails

ERC-7710 is draft. Verify the target wallet/delegation manager implementation before promising compatibility.
Always simulate delegation redemption before submitting on-chain.
Never create unlimited approvals or open-ended agent authority.
Keep recurrence off the x402 protocol itself; model it as policy plus accounting.
Prefer testnets for demos. If using mainnet, require explicit confirmation and a hard spend cap.

Signed Evidence Pattern

For paid report or API-resource demos using x402 plus review guardrails:

The x402 paid response should include a service-signed receipt with stable JSON canonicalization, payload hash, signer, route, method, request parameters, response hash, price, and issue time.
The agent should sign an intent envelope before spending: agent address, service origin, route, method, request parameters, instruction hash, permission context hash, user mandate, timestamp, and nonce.
Reject evidence before review unless the paid request returned HTTP 200, produced an x402 payment response header, and the service receipt signature verifies.
If the EVM guardrail permission is separate from the wallet x402 permission context, carry both hashes in evidence and set the review target to the controller-tracked permission hash.
Keep custom guardrail permissions tiny and fresh for each run. Reusing a revoked permission only proves the final blocked state, not a full happy-path demo.
A production-quality malicious-agent block needs a wallet caveat/enforcer or smart-account module wired directly to the EVM RevocationController; agent-side route checks alone are not malicious-agent resistant.

References

references/demo-blueprints.md for detailed demo flows and policy variations.

About this skill

Automatic

Coding pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

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

internet-court / internet-court-skill

integrations/x402-erc7710/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/3/2026Version v1Bundled 1 file

Illustrative Want to see what internet-court/x402-erc7710 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

x402 + ERC-7710

Core Model

Discovery-First Boundary

Trust Objection Mode

Adjudicated Setup Mode

Subscription Pattern

Default Demo

Browser Lab Pattern

Conversational Operator Mode

MetaMask Transaction Cards

Periodic GenLayer Control

Other Demo Ideas

Implementation Checklist

Guardrails

Signed Evidence Pattern

References

SkillSafety

Source

Related skills

More in the registry