Ready to supercharge your AI agents?

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

Get Started Free →

Anti-Detect Browser Automation with camoufox-cli · bin-huang | DecimalAI

Agent Toolingby bin-huang

Anti-Detect Browser Automation with camoufox-cli

Anti-detect browser automation CLI & Skills for AI agents.

Never made a case worseMaintained

SkillScore

SkillScore98/100

Test results 100 · Live runs 97

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

48%100%of test cases passed +52 pts

Without skill11 of 23

With skill23 of 23

12 fixed11 passed either way0 still failing0 broke

Measured on gemini-3.6-flash9/25/2026v222 comparable

Track record

Agent runs: 212; 2 in the last 30 days
Forks: 2

See one task, with and without the skill

One test taskMultiple orphan background browser daemon processes were left running from crashed scripts. What single terminal command immediately terminates all active background sessions and frees system browser resources?

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 bin-huang-camoufox-cli
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("bin-huang-camoufox-cli")
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 bin-huang-camoufox-cli

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/bin-huang-camoufox-cli/SKILL.md https://app.decimal.ai/s/bin-huang-camoufox-cli/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/bin-huang-camoufox-cli/SKILL.md

This gets SKILL.md only. The skill's 2 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 bin-huang-camoufox-cli

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("bin-huang-camoufox-cli")
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/bin-huang-camoufox-cli/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/bin-huang-camoufox-cli/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 2 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 bin-huang-camoufox-cli

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("bin-huang-camoufox-cli")
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/bin-huang-camoufox-cli/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/bin-huang-camoufox-cli/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 2 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 bin-huang-camoufox-cli

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("bin-huang-camoufox-cli")
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/bin-huang-camoufox-cli/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/bin-huang-camoufox-cli/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 2 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 bin-huang-camoufox-cli

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("bin-huang-camoufox-cli")
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/bin-huang-camoufox-cli/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/bin-huang-camoufox-cli/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 2 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 bin-huang-camoufox-cli

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("bin-huang-camoufox-cli")
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/bin-huang-camoufox-cli/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/bin-huang-camoufox-cli/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 2 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 bin-huang-camoufox-cli

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("bin-huang-camoufox-cli")
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/bin-huang-camoufox-cli/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/bin-huang-camoufox-cli/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 2 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 bin-huang-camoufox-cli

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("bin-huang-camoufox-cli")
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/bin-huang-camoufox-cli/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 2 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 bin-huang-camoufox-cli

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("bin-huang-camoufox-cli")
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/bin-huang-camoufox-cli/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/bin-huang-camoufox-cli/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 2 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 bin-huang-camoufox-cli

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("bin-huang-camoufox-cli")
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/bin-huang-camoufox-cli/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/bin-huang-camoufox-cli/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 2 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 bin-huang-camoufox-cli

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("bin-huang-camoufox-cli")
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/bin-huang-camoufox-cli/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/bin-huang-camoufox-cli/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 2 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 bin-huang-camoufox-cli

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("bin-huang-camoufox-cli")
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/bin-huang-camoufox-cli/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/bin-huang-camoufox-cli/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 2 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 bin-huang-camoufox-cli

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("bin-huang-camoufox-cli")
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/bin-huang-camoufox-cli/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/bin-huang-camoufox-cli/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 2 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 bin-huang-camoufox-cli

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/bin-huang-camoufox-cli/SKILL.md https://app.decimal.ai/s/bin-huang-camoufox-cli/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/bin-huang-camoufox-cli/SKILL.md

This gets SKILL.md only. The skill's 2 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/bin-huang-camoufox-cli/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/bin-huang-camoufox-cli.json

This gets SKILL.md only. The skill's 2 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v2, tested 9/25/2026
Source: bin-huang/camoufox-cli ↗
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

Anti-Detect Browser Automation with camoufox-cli

Core Workflow

Every browser automation follows this pattern:

Navigate: camoufox-cli open <url>
Snapshot: camoufox-cli snapshot -i (get element refs like @e1, @e2)
Interact: Use refs to click, fill, select
Re-snapshot: After navigation or DOM changes, get fresh refs
Close: camoufox-cli close when the entire task is complete — with the same --tab/--session flags as your other commands. Keep it open if the user may have follow-up instructions.

camoufox-cli open https://example.com/form
camoufox-cli snapshot -i
# Output: - textbox "Email" [ref=e1]
#         - textbox "Password" [ref=e2]
#         - button "Submit" [ref=e3]

camoufox-cli fill @e1 "[email protected]"
camoufox-cli fill @e2 "password123"
camoufox-cli click @e3
camoufox-cli snapshot -i  # Check result

Command Chaining

Commands can be chained with && in a single shell invocation. The browser persists between commands via a background daemon, so chaining is safe and more efficient than separate calls.

# Chain open + snapshot in one call
camoufox-cli open https://example.com && camoufox-cli snapshot -i

# Chain multiple interactions
camoufox-cli fill @e1 "[email protected]" && camoufox-cli fill @e2 "password123" && camoufox-cli click @e3

# Navigate and capture
camoufox-cli open https://example.com && camoufox-cli screenshot page.png

When to chain: Use && when you don't need to read the output of an intermediate command before proceeding (e.g., open + screenshot). Run commands separately when you need to parse the output first (e.g., snapshot to discover refs, then interact using those refs).

Essential Commands

# Navigation
camoufox-cli open <url>              # Navigate to URL (starts daemon if needed)
camoufox-cli back                    # Go back
camoufox-cli forward                 # Go forward
camoufox-cli reload                  # Reload page
camoufox-cli url                     # Print current URL
camoufox-cli title                   # Print page title
camoufox-cli close                   # Close your tab (browser exits when the last tab closes)
camoufox-cli close --all             # Force-close all sessions

# Snapshot
camoufox-cli snapshot                # Full aria tree of page
camoufox-cli snapshot -i             # Interactive elements only (recommended)
camoufox-cli snapshot -s "#selector" # Scope to CSS selector

# Interaction (use @refs from snapshot)
camoufox-cli click @e1               # Click element
camoufox-cli fill @e1 "text"         # Clear + type into input
camoufox-cli type @e1 "text"         # Type without clearing (append)
camoufox-cli select @e1 "option"     # Select dropdown option
camoufox-cli check @e1               # Toggle checkbox
camoufox-cli hover @e1               # Hover over element
camoufox-cli mouse click 660 380     # Click at viewport coordinates (no ref needed)
camoufox-cli press Enter             # Press keyboard key
camoufox-cli press "Control+a"       # Key combination

# Data Extraction
camoufox-cli text @e1                # Get text content of element
camoufox-cli text body               # Get all page text (CSS selector)
camoufox-cli eval "document.title"   # Execute JavaScript

# Capture
camoufox-cli screenshot              # Screenshot as JSON {"base64": "..."}
camoufox-cli screenshot page.png     # Screenshot to file
camoufox-cli screenshot --full p.png # Full page screenshot
camoufox-cli pdf output.pdf          # Save page as PDF

# Scroll & Wait
camoufox-cli scroll down             # Scroll down 500px
camoufox-cli scroll up               # Scroll up 500px
camoufox-cli scroll down 1000        # Scroll down 1000px
camoufox-cli wait @e1                # Wait for element to appear
camoufox-cli wait 2000               # Wait milliseconds
camoufox-cli wait --url "*/dashboard" # Wait for URL pattern

# Tabs
camoufox-cli tabs                    # List open tabs (with owner names)
camoufox-cli switch 2                # Switch to tab by index
camoufox-cli --tab <unique-name> open <url> # Named tab: shared browser + login, own page/refs

# Cookies & State
camoufox-cli cookies                 # Dump cookies as JSON
camoufox-cli cookies import file.json # Import cookies
camoufox-cli cookies export file.json # Export cookies

# Sessions
camoufox-cli sessions                # List active sessions
camoufox-cli --session work open <url> # Use named session
camoufox-cli close --all             # Force-close all sessions

# Setup
camoufox-cli install                 # Download Camoufox browser
camoufox-cli install --with-deps     # Download browser + system libs (Linux)

Common Patterns

Form Submission

camoufox-cli open https://example.com/signup
camoufox-cli snapshot -i
camoufox-cli fill @e1 "Jane Doe"
camoufox-cli fill @e2 "[email protected]"
camoufox-cli select @e3 "California"
camoufox-cli check @e4
camoufox-cli click @e5
camoufox-cli snapshot -i  # Verify submission result

Data Extraction

camoufox-cli open https://example.com/products
camoufox-cli snapshot -i
camoufox-cli text @e5                # Get specific element text
camoufox-cli eval "document.title"   # Get page title via JS
camoufox-cli screenshot results.png  # Visual capture

Cookie Management (Persist Login)

# Login and export cookies
camoufox-cli open https://app.example.com/login
camoufox-cli snapshot -i
camoufox-cli fill @e1 "user"
camoufox-cli fill @e2 "pass"
camoufox-cli click @e3
camoufox-cli cookies export auth.json

# Restore in future session
camoufox-cli open https://app.example.com
camoufox-cli cookies import auth.json
camoufox-cli reload

For long-lived accounts where the site also verifies device stability (not just the cookie), combine this with --persistent so the fingerprint stays fixed alongside the cookies — see the Persistent Identity section below.

Multiple Tabs

camoufox-cli open https://site-a.com
camoufox-cli eval "window.open('https://site-b.com')"
camoufox-cli tabs                    # List tabs
camoufox-cli switch 1                # Switch to second tab
camoufox-cli snapshot -i

Parallel Tabs (shared identity, one browser)

Named tabs share one browser within a session — same fingerprint, same cookies/login state — but each tab keeps its own page, element refs, and navigation history, so concurrent agents never clobber each other. This is the cheap way to parallelize: one Firefox total, roughly 50-150MB per extra tab.

camoufox-cli --tab inbox-scan-x4q open https://app.example.com/inbox
camoufox-cli --tab report-pull-9kf open https://app.example.com/reports
camoufox-cli --tab inbox-scan-x4q snapshot -i   # refs are per tab
camoufox-cli tabs                               # Lists every tab with its owner name
camoufox-cli --tab inbox-scan-x4q close         # Frees only this tab; browser stays for the others

Picking your tab name. Nothing enforces uniqueness — two agents using the same name share one page pointer and will clobber each other. Generate your name ONCE at the start of your task: a short slug of your specific task plus a shell-generated random suffix — don't invent the suffix yourself, LLM-"random" characters are biased and concurrent agents may produce the same ones. Then reuse the printed name verbatim in every subsequent command. (If your instructions explicitly assign you a tab name, use that instead.)

TAB="price-scan-$(openssl rand -hex 2)" && echo "$TAB" && camoufox-cli --tab "$TAB" open https://example.com
# prints e.g. price-scan-9f3c — use that exact name in every later command:
camoufox-cli --tab price-scan-9f3c snapshot -i

Use tabs when subagents should act as the same identity (e.g. all operating the same logged-in account). Cleanup needs no coordination: every agent runs close when done, addressed to its own tab (camoufox-cli --tab <name> close) — it releases only that tab, and the browser exits by itself when the last tab closes.

Tabs share one browser process, so commands from different tabs may queue behind a slow navigation or wait; separate sessions run as independent processes and execute fully in parallel. If a few agents are extremely command-heavy, consider giving those their own session and keeping the rest on tabs.

Parallel Sessions (isolated identities)

Each named session is a separate browser process, so each gets its own randomly-generated fingerprint and its own cookies. Use this when agents must NOT share identity (multi-account work) — it costs a full Firefox (~300-500MB) per session:

camoufox-cli --session s1 open https://site-a.com
camoufox-cli --session s2 open https://site-b.com
camoufox-cli sessions                # List both
camoufox-cli --session s1 snapshot -i
camoufox-cli --session s2 snapshot -i

Separate sessions alone only isolate the browser side. For multi-account work that must survive scrutiny, also give each session its own proxy (sites correlate accounts by IP — use the config file's sessions.<name>.proxy) and --persistent (otherwise the fingerprint is re-randomized every launch, which looks like a new device on each login).

Visual Browser (Debugging)

camoufox-cli --headed open https://example.com
camoufox-cli snapshot -i
camoufox-cli screenshot debug.png

Session Management and Cleanup

When running multiple agents or automations concurrently, give each agent its own name so they don't conflict. Two isolation levels:

--tab <name> (shared identity, recommended default): all agents share one browser — same fingerprint and login state — but each gets an independent tab. Cheap: one Firefox total.
--session <name> (isolated identity): each agent gets its own browser with its own fingerprint and cookies. Expensive: a full Firefox per session. Use only when identities must be separate.

# Shared identity: 3 agents, one browser, one login
camoufox-cli --tab orders-audit-p2m open https://app.example.com/a
camoufox-cli --tab user-export-j8w open https://app.example.com/b
camoufox-cli --tab billing-check-r4t open https://app.example.com/c

# Isolated identities: 2 agents, two browsers
camoufox-cli --session shop-a-buyer open https://site-a.com
camoufox-cli --session shop-b-buyer open https://site-b.com
camoufox-cli sessions                  # Check active sessions

Names are just strings and nothing enforces uniqueness — follow the "Picking your tab name" rule above (task slug + shell-generated random suffix, chosen once). The same applies to session names.

Always run close when done to avoid leaked processes — with the same --tab/--session flags as your other commands, since close releases the tab the command is addressed to. The browser exits when the last tab closes, so every agent cleans up the same way without knowing about the others:

camoufox-cli --tab orders-audit-p2m close       # Free this tab; browser exits if it was the last
camoufox-cli close                              # Same, for the default tab
camoufox-cli --session shop-a-buyer close       # Same, within a named session
camoufox-cli close --all                        # Force-close all sessions (cleanup escape hatch)

If a previous session was not closed properly, the daemon may still be running. Use camoufox-cli close (or close --all) to clean it up before starting new work.

Timeouts and Slow Pages

Some pages take time to fully load, especially those with dynamic content or heavy JavaScript. Use explicit waits before taking a snapshot:

# Wait for a specific element to appear
camoufox-cli wait @e1
camoufox-cli snapshot -i

# Wait for a URL pattern (useful after redirects)
camoufox-cli wait --url "*/dashboard"
camoufox-cli snapshot -i

# Wait a fixed duration as a last resort
camoufox-cli wait 3000
camoufox-cli snapshot -i

When dealing with slow pages, always wait before snapshotting. If you snapshot too early, elements may be missing from the output.

Ref Lifecycle (Important)

Refs (@e1, @e2, etc.) are temporary identifiers assigned by sequential numbering during each snapshot. They are invalidated when the page changes.

Always re-snapshot after:

Clicking links or buttons that navigate
Form submissions
Dynamic content loading (dropdowns, modals, lazy-loaded content)
Scrolling that triggers new content

# CORRECT: re-snapshot after navigation
camoufox-cli click @e5              # Navigates to new page
camoufox-cli snapshot -i            # MUST re-snapshot
camoufox-cli click @e1              # Use new refs

# CORRECT: re-snapshot after dynamic changes
camoufox-cli click @e1              # Opens dropdown
camoufox-cli snapshot -i            # See dropdown items
camoufox-cli click @e7              # Select item

# WRONG: using refs without snapshot
camoufox-cli open https://example.com
camoufox-cli click @e1              # Ref doesn't exist yet!

# WRONG: using old refs after navigation
camoufox-cli click @e5              # Navigates away
camoufox-cli click @e3              # STALE REF - wrong element!

Always take a fresh snapshot before interacting with elements after navigation or page changes.

Troubleshooting

"Ref @eN not found"

The ref was invalidated. Re-snapshot to get fresh refs:

camoufox-cli snapshot -i

Element Not Visible in Snapshot

# Scroll down to reveal element
camoufox-cli scroll down 1000
camoufox-cli snapshot -i

# Or wait for dynamic content
camoufox-cli wait 2000
camoufox-cli snapshot -i

Element Visible on Screen but Not in Snapshot

A checkbox inside a cross-origin iframe (for example a Cloudflare Turnstile "Verify you are human" widget) has no ref. Find it in a screenshot and click by coordinates. Coordinates are viewport CSS pixels. At the default devicePixelRatio of 1, they equal the pixels of a non---full screenshot.

camoufox-cli screenshot page.png     # Locate the checkbox in the image
camoufox-cli mouse click 660 380     # Click its center
camoufox-cli wait 3000
camoufox-cli screenshot page.png     # Confirm the check passed

Too Many Elements in Snapshot

# Scope to a specific container
camoufox-cli snapshot -s "#main-content"
camoufox-cli snapshot -i -s "form.login"

Page Not Fully Loaded

# Wait for URL pattern after redirect
camoufox-cli wait --url "*/dashboard"
camoufox-cli snapshot -i

# Wait a fixed duration as last resort
camoufox-cli wait 3000
camoufox-cli snapshot -i

Global Flags

--session <name>       Named session (default: "default")
--tab <name>           Named tab within the session's shared browser: same
                       fingerprint and cookies/login, independent page/refs/
                       history (default: "default")
--headed               Show browser window (default: headless)
--timeout <seconds>    Daemon idle timeout (default: 1800)
--json                 Output as JSON instead of human-readable
--persistent [path]    Persistent identity — reuse the same fingerprint + cookies across launches
                       (default path: ~/.camoufox-cli/profiles/<session>)
--proxy <url>          Proxy server (http:// or https://; auth: http://user:pass@host:port)
--no-geoip             Disable automatic GeoIP spoofing (auto-enabled with --proxy)
--locale <tag>         Force browser locale (e.g. "en-US" or "en-US,zh-CN")
--version              Print version and exit

Config file (optional). To avoid repeating flags, set defaults in ~/.camoufox-cli/config.json (override path with $CAMOUFOX_CLI_CONFIG): a default block applies to all sessions, and an optional sessions.<name> block layers extra overrides on top whenever you run --session <name> (the name is just whatever you pass to --session — sessions are never pre-registered). Settable keys: proxy, locale, geoip, persistent (true/false/path), headed, timeout, json. Command-line flags always win over the file. Config is read only when a session's daemon first launches.

{
  "default": { "persistent": true, "timeout": 3600 },
  "sessions": { "<your-session-name>": { "proxy": "socks5://127.0.0.1:1080", "locale": "zh-CN" } }
}

Persistent Identity

By default, every launch gets a fresh random fingerprint. Add --persistent [path] to reuse the same fingerprint + cookies across launches — fingerprint/OS/canvas+font seeds are frozen on first launch (delete the directory to reset); --locale and proxy-derived timezone/geolocation are stored but refreshed whenever you pass the flag; --proxy / --no-geoip are never stored, so pass them every launch.

Use it when the same device should see the same fingerprint across visits (account-bound tasks, parallel independent identities, or when cookies import/export alone isn't enough because the site also checks device stability). Skip it for one-off scraping or quick debugging.

# Parallel identities, each with its own fingerprint + cookies
camoufox-cli --session a --persistent ~/.camoufox-cli/profiles/alice open https://app.example.com
camoufox-cli --session b --persistent ~/.camoufox-cli/profiles/bob   open https://app.example.com

# Reset an identity: just remove the directory
rm -rf ~/.camoufox-cli/profiles/alice

Documentation

camoufox-cli documentation -- Full README, setup guide, installation, and command reference

When it activates

Automatically, when a task matches. Use when the user needs to interact with websites with bot detection, CAPTCHAs, or anti-bot blocks, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task that requires bypassing fingerprint checks.

About this skill

Automatic

Coding pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 9/25/2026

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

bin-huang / camoufox-cli

skills/camoufox-cli/SKILL.md

View on GitHub ↗

License MITImported 9/25/2026Version v2Bundled 2 files

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

Other skills for the same job

Published skills whose descriptions closely match this one, 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

Anti-Detect Browser Automation with camoufox-cli

Core Workflow

Command Chaining

Essential Commands

Common Patterns

Form Submission

Data Extraction

Cookie Management (Persist Login)

Multiple Tabs

Parallel Tabs (shared identity, one browser)

Parallel Sessions (isolated identities)

Visual Browser (Debugging)

Session Management and Cleanup

Timeouts and Slow Pages

Ref Lifecycle (Important)

Troubleshooting

"Ref @eN not found"

Element Not Visible in Snapshot

Element Visible on Screen but Not in Snapshot

Too Many Elements in Snapshot

Page Not Fully Loaded

Global Flags

Persistent Identity

Documentation

When it activates

SkillSafety

Source

Other skills for the same job

More in the registry