Ready to supercharge your AI agents?

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

Shell Integration · marcus | DecimalAI

Codingby marcus

Shell Integration

Interactive shell/TTY integration with tmux session management, shell command execution, control-mode output capture with polling fallback, native cursor rendering, lazy scrollback, selection, paste handling, and inline editing.

Maintained

SkillScore

SkillScore96/100

Test results 96

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

30%96%of test cases passed +65 pts

Without skill7 of 23

With skill22 of 23

16 fixed6 passed either way0 still failing1 broke

Measured on gemini-3.6-flash9/2/2026v5

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskWhat security rule must be applied when processing Operating System Command (OSC) sequences coming from an active terminal stdout stream?

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 marcus-shell-integration
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("marcus-shell-integration")
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 marcus-shell-integration

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/marcus-shell-integration/SKILL.md https://app.decimal.ai/s/marcus-shell-integration/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/marcus-shell-integration/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 marcus-shell-integration

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("marcus-shell-integration")
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/marcus-shell-integration/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/marcus-shell-integration/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 marcus-shell-integration

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("marcus-shell-integration")
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/marcus-shell-integration/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/marcus-shell-integration/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 marcus-shell-integration

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("marcus-shell-integration")
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/marcus-shell-integration/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/marcus-shell-integration/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 marcus-shell-integration

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("marcus-shell-integration")
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/marcus-shell-integration/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/marcus-shell-integration/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 marcus-shell-integration

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("marcus-shell-integration")
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/marcus-shell-integration/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/marcus-shell-integration/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 marcus-shell-integration

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("marcus-shell-integration")
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/marcus-shell-integration/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/marcus-shell-integration/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 marcus-shell-integration

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("marcus-shell-integration")
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/marcus-shell-integration/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 marcus-shell-integration

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("marcus-shell-integration")
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/marcus-shell-integration/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/marcus-shell-integration/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 marcus-shell-integration

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("marcus-shell-integration")
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/marcus-shell-integration/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/marcus-shell-integration/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 marcus-shell-integration

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("marcus-shell-integration")
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/marcus-shell-integration/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/marcus-shell-integration/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 marcus-shell-integration

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("marcus-shell-integration")
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/marcus-shell-integration/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/marcus-shell-integration/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 marcus-shell-integration

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("marcus-shell-integration")
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/marcus-shell-integration/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/marcus-shell-integration/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 marcus-shell-integration

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/marcus-shell-integration/SKILL.md https://app.decimal.ai/s/marcus-shell-integration/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/marcus-shell-integration/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/marcus-shell-integration/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/marcus-shell-integration.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: v5, tested 9/2/2026
Source: marcus/sidecar ↗
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

Shell Integration

Sidecar's interactive shell allows users to type directly into tmux sessions from within the TUI. Tmux remains the PTY backend. Sidecar renders ordered control-mode bytes through the shared tty.Model, whose VT behavior is behind the screenmodel adapter rather than implemented in plugin code.

Package Structure

internal/tty/                    # Shared tmux terminal abstraction
  tty.go                         # Core Model and State types
  keymap.go                      # Bubble Tea -> tmux key translation
  messages.go                    # Owner/target/generation-scoped messages
  session.go                     # tmux operations (send-keys, capture-pane, resize)
  scheduler.go                   # Keyed fallback-poll generation ownership
  control_*.go                   # Session-keyed tmux -C transport and manager
  capture_range.go               # Atomic bounded history capture
  cursor.go                      # Cursor positioning helpers
  paste.go                       # Paste handling (clipboard, bracketed paste)
  terminal_mode.go               # Capture-fallback mode recovery
  output_buffer.go               # Absolute, bounded live/history buffer
  editor_session.go              # Shared inline-editor tmux lifecycle

internal/plugins/workspace/
  interactive.go                 # Workspace-specific interactive mode logic
  interactive_selection.go       # Text selection in interactive mode
  terminal_viewport.go           # Pure shared terminal viewport renderer
  terminal_control.go            # Workspace target/layout policy for tty.Model
  terminal_history.go            # Lazy absolute scrollback loading
  terminal_search.go             # Loaded-history search
  terminal_links.go              # Safe URL/path detection and activation
  native_terminal.go             # Native cursor and contextual mouse mode
  view_preview.go                # Agent/shell preview composition
  mouse.go                       # Scroll handling
  types.go                       # InteractiveState type

internal/plugins/filebrowser/
  inline_edit.go                 # Inline editor mode using tty.Model
  handlers.go                    # Message handling for inline edit

Data Flow

User Keypress -> handleInteractiveKeys() -> tty.MapKeyToTmux() -> tmux send-keys

Pane output -> tmux -C ordered %output bytes
            -> session-pooled control actor
            -> seeded screenmodel adapter
            -> adaptive per-feed presentation publication
            -> owner/target/generation-scoped Tea message
            -> OutputBuffer + cursor/modes/history
            -> pure terminal viewport + native Bubble Tea cursor

Open/resync/history -> bounded capture seed/range
Control unavailable/dead -> one scoped capture-poll fallback + clean reseed

Core Abstractions

tty.Model

Embeddable component for interactive tmux functionality:

type Model struct {
    Config   Config        // Exit key, copy/paste keys, scrollback lines
    State    *State        // Current interactive state
    Width    int
    Height   int
    OnExit   func() tea.Cmd
    OnAttach func() tea.Cmd
}

// Usage:
p.inlineEditor = tty.New(&tty.Config{
    ExitKey: "ctrl+\\",
    ScrollbackLines: 600,
})
cmd := p.inlineEditor.Enter(sessionName, paneID)

tty.State

type State struct {
    Active        bool
    TargetPane    string      // tmux pane ID (e.g., "%12")
    TargetSession string
    LastKeyTime   time.Time   // Input timing and fallback polling decay
    CursorRow, CursorCol int
    CursorVisible        bool
    PaneHeight, PaneWidth int
    BracketedPasteEnabled bool
    MouseReportingEnabled bool
    OutputBuf      *OutputBuffer
    PollGeneration int          // For invalidating stale fallback polls
}

tty.OutputBuffer

Thread-safe bounded buffer with hash-based change detection:

func (b *OutputBuffer) Update(content string) bool {
    rawHash := maphash.String(seed, content)
    if rawHash == b.lastRawHash { return false }  // Skip ALL processing
    content = mouseEscapeRegex.ReplaceAllString(content, "")
    b.lines = strings.Split(content, "\n")
    return true
}
func (b *OutputBuffer) LinesRange(start, end int) []string

Key Mapping (`keymap.go`)

func MapKeyToTmux(msg tea.KeyPressMsg) (key string, useLiteral bool) {
    if msg.Mod.Contains(tea.ModCtrl) && msg.Code >= 'a' && msg.Code <= 'z' {
        return "C-" + string(msg.Code), false
    }
    switch msg.Code {
    case tea.KeyEnter:     return "Enter", false
    case tea.KeyBackspace: return "BSpace", false
    case tea.KeyTab:       return "Tab", false
    case tea.KeyUp:        return "Up", false
    }
    if msg.Text != "" {
        return msg.Text, true // Literal mode
    }
    return "", true
}

Modified keys use CSI sequences:

case "shift+up":   return "\x1b[1;2A", true
case "ctrl+up":    return "\x1b[1;5A", true
case "alt+up":     return "\x1b[1;3A", true
case "shift+tab":  return "\x1b[Z", true

For printable characters, tmux send-keys -l prevents interpretation.

Capture fallback and semantic observation

const (
    PollingDecayFast   = 50ms    // During active typing
    PollingDecayMedium = 200ms   // After 2s inactivity
    PollingDecaySlow   = 250ms   // After 10s inactivity
    KeystrokeDebounce  = 20ms    // Delay after keystroke
)

Control-mode bytes are the ordinary presentation source for every visible terminal surface. Adaptive capture polling exists only until the first seeded frame and after control/model failure. Workspace agent and shell observation continues independently for provider activity evidence; those captures never overwrite a model-owned presentation buffer.

The control actor writes every ordered byte into screenmodel immediately. Presentation alone is adaptive: the first changed frame after idle publishes inline, sustained changed frames publish at no more than 30 fps per pane-model feed, and one tokenized timer guarantees the newest trailing frame. Seed, reseed, and generation changes bypass the cap; input never enters this cadence. Ordinary Frame() snapshots omit diagnostic cells, while screen comparison explicitly requests the canonical grid.

For isolated performance diagnostics, run with both SIDECAR_PPROF=<port> and SIDECAR_TERMINAL_PERF=1, then read GET /debug/terminalperf. The endpoint is localhost-only and returns fixed numeric counts plus output-to-frame samples, p95, and maximum in microseconds. Its fixed vocabulary covers model publication, terminal views, row hits/misses/bypasses, link resolution, global Sessions list/preview work, application/Workspace/sidebar views, project preview composes/cache hits, and document frame builds/cache hits/scans/resolution. A pulse-only interval should reuse the project preview and perform no terminal, document, or row work. Keep counters off during CPU profiles, use a separate diagnostic process, and never interpret process-wide model-frame counts as per-feed fps when more than one pane-model feed may be live.

Set SIDECAR_TERMINAL_TRACE=1 only in an isolated proof run to log privacy-safe capture metadata (surface, role, reason, and generation). It never logs session or pane identity, terminal text, commands, paths, titles, or provider payloads. This distinguishes intentional semantic observation from presentation fallback.

Visibility and focus

State	Active	Idle
Visible + focused	200ms	2s
Visible + app unfocused	clamped to unfocused cadence	clamped
Not visible	10-20s	10-20s

Keyed generation ownership

tty.KeyedScheduler owns a generation per logical source (agent:<name>, shell:<tmuxName>, terminal-panel). Every schedule allocates a fresh token, and the token travels through capture, result, retry, and continuation messages. Reset invalidates pending timers and in-flight results.

token, cmd := scheduler.Schedule(key, delay, makeMessage)
if scheduler.IsCurrent(key, token) { /* apply result */ }

Control subscriptions are pooled by tmux session because a control client cannot observe panes in another session. Subscription close and manager stop invalidate and drain queued callbacks before returning.

Cursor Positioning (`cursor.go`)

Query

func QueryCursorPositionSync(target string) (row, col, paneHeight, paneWidth int, visible, ok bool) {
    cmd := exec.Command("tmux", "display-message", "-t", target,
        "-p", "#{cursor_x},#{cursor_y},#{cursor_flag},#{pane_height},#{pane_width}")
}

Rendering

Focused live terminal surfaces expose a tea.Cursor through the plugin CursorProvider capability. Workspace, filebrowser, and notes compute exact application coordinates and suppress the cursor under modals, while scrolled back, outside the visible slice, or when another surface owns focus. A painted cursor is not added to native-cursor content.

Height Mismatch Adjustment

When display height differs from tmux pane height:

if paneHeight > displayHeight {
    relativeRow = cursorRow - (paneHeight - displayHeight)
} else if paneHeight > 0 && paneHeight < displayHeight {
    relativeRow = cursorRow + (displayHeight - paneHeight)
}

Scrolling

Scrolling operates on the captured buffer. No tmux copy-mode involved.

type Plugin struct {
    previewOffset    int   // Lines from bottom (0 = at bottom/live)
    autoScrollOutput bool  // Auto-follow new output?
}

Scroll UP: pause auto-scroll, increment previewOffset
Scroll DOWN: decrement previewOffset, re-enable auto-scroll at 0
Live capture stays bounded at 600 lines; older 600-line ranges load lazily
Absolute buffer coordinates keep selections and search matches stable
Scrollback is bounded by the shared 10,000-line tmux history policy
Instant response (pure state manipulation, no subprocess calls)

Copy/Paste

Copy: alt+c (configurable via interactiveCopyKey), or super+c (Cmd+C) as a built-in that a configured key does not replace. Cmd+C only arrives when the emulator passes it through — terminals that keep it for themselves (iTerm2) never deliver it, so alt+c stays the portable chord.
Paste: alt+v (configurable via interactivePasteKey)

Paste wraps text with bracketed paste sequences (\x1b[200~...\x1b[201~) when the application has enabled bracketed paste mode.

Fallback Terminal Mode Recovery (`terminal_mode.go`)

When capture fallback owns presentation, detects bracketed paste and mouse reporting modes by scanning the fallback snapshot. Healthy model-backed presentation receives these modes from the shared screen model.

Width Synchronization

Tmux panes are resized in background at all times (not just interactive mode):

func ResizeTmuxPane(paneID string, width, height int) {
    // resize-window, fallback to resize-pane for older tmux
}

Resize triggers: window resize, sidebar toggle/drag, selection change, agent/shell creation, interactive mode entry.

Inline Edit Mode (Filebrowser)

Uses tty.Model plus tty.EditorSession for vim/nano/emacs editing in the file preview pane. Session creation is history-safe and asynchronous:

func (p *Plugin) enterInlineEditMode(path string) tea.Cmd {
    return func() tea.Msg {
        session, err := tty.StartEditorSession(tty.EditorSessionOptions{Path: path})
        return InlineEditStartedMsg{Session: session, Err: err}
    }
}

Entry and Exit

Workspace Plugin:

Enter: enter / E when preview pane focused with output tab
Exit: Ctrl+\ (instant) or double-Escape (150ms delay)
Attach: Ctrl+] / t only when tmux_full_attach is on (default off)

Filebrowser Plugin:

Enter: e or Enter on a file (if inline edit enabled)
Exit: Ctrl+\ or double-Escape
Attach: Ctrl+] only when tmux_full_attach is on (default off)

Feature Flags

{
  "features": {
    "tmux_interactive_input": true,
    "tmux_inline_edit": true,
    "tmux_full_attach": false,
    "workspace_terminal_panel": true
  }
}

Configuration

{
  "plugins": {
    "workspace": {
      "interactiveExitKey": "ctrl+\\",
      "interactiveAttachKey": "ctrl+]",
      "interactiveCopyKey": "alt+c",
      "interactivePasteKey": "alt+v",
      "tmuxCaptureMaxBytes": 2097152,
      "copyOnSelect": false
    }
  }
}

Critical Rules

Scope every async result by owner, target/role, activation, and keyed generation.
Carry the generation end to end through capture, result, retry, and continuation.
Never call subprocesses from Init() or View(); use Start()/tea.Cmd.
Do not mutate model state in tea.Cmd callbacks; return a scoped message.
Hash raw capture before cleaning/splitting, but mode changes must still clear coordinate state.
Preserve newer live overlap when delayed history ranges prepend.
Control clients are per tmux session and close/stop must invalidate and drain deliveries.
Keep keyed capture fallback working until the first accepted model frame and after control failure; never run it as the healthy renderer.
Consume all model bytes immediately and cadence only presentation snapshots; preserve immediate idle-leading output, a newest trailing frame, and unconditional seed/generation publication.
Use native cursor only for the focused live viewport; hide it offscreen, under modals, and in scrollback.
Treat source OSC as untrusted; the sanitizer and independent fuzz oracle must cover nested 7-bit/C1 forms and removal-boundary synthesis.
Width sync matters; resize panes/control clients when terminal geometry changes.

References

Tmux integration notes -- detailed tmux CLI techniques, cursor tracking, resize sync, bracketed paste, mouse forwarding, modified keys, adaptive polling, debugging
Original spec: docs/plans/implemented/spec-tmux-interactive-input.md

When it activates

Automatically, when a task matches. Use when working on shell integration, tmux features, command execution, or interactive mode.

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 — 9/2/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

marcus / sidecar

.claude/skills/shell-integration/SKILL.md

View on GitHub ↗

License MITImported 9/2/2026Version v5Bundled 1 file

Illustrative Want to see what marcus/shell-integration 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

Shell Integration

Package Structure

Data Flow

Core Abstractions

tty.Model

tty.State

tty.OutputBuffer

Key Mapping (keymap.go)

Capture fallback and semantic observation

Visibility and focus

Keyed generation ownership

Cursor Positioning (cursor.go)

Query

Rendering

Height Mismatch Adjustment

Scrolling

Copy/Paste

Fallback Terminal Mode Recovery (terminal_mode.go)

Width Synchronization

Inline Edit Mode (Filebrowser)

Entry and Exit

Feature Flags

Configuration

Critical Rules

References

When it activates

SkillSafety

Source

Related skills

More in the registry

Key Mapping (`keymap.go`)

Cursor Positioning (`cursor.go`)

Fallback Terminal Mode Recovery (`terminal_mode.go`)