Ready to supercharge your AI agents?

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

Aider SOP — 终端结对编程的操作系统 · agentsope | DecimalAI

Agent Toolingby agentsope

Aider SOP — 终端结对编程的操作系统

SOP for terminal-based, git-native AI pair programming with Aider (git work-tree + tree-sitter repo-map + edit-format + human-in-loop REPL).

Maintained

SkillScore

SkillScore83/100

Test results 83

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

67%83%of test cases passed +17 pts

Without skill16 of 24

With skill20 of 24

5 fixed15 passed either way3 still failing1 broke

Measured on gemini-3.6-flash8/24/2026v1

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskWe want our terminal pair programming sessions to consistently enforce team coding guidelines (such as using httpx instead of requests and requiring type hints) across all chat sessions without adding them to editable chat files. How should these coding conventions be supplied?

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 agentsope-agentsop-aider
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("agentsope-agentsop-aider")
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 agentsope-agentsop-aider

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/agentsope-agentsop-aider/SKILL.md https://app.decimal.ai/s/agentsope-agentsop-aider/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/agentsope-agentsop-aider/SKILL.md

This gets SKILL.md only. The skill's 5 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 agentsope-agentsop-aider

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("agentsope-agentsop-aider")
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/agentsope-agentsop-aider/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/agentsope-agentsop-aider/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 5 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 agentsope-agentsop-aider

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("agentsope-agentsop-aider")
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/agentsope-agentsop-aider/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/agentsope-agentsop-aider/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 5 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 agentsope-agentsop-aider

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("agentsope-agentsop-aider")
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/agentsope-agentsop-aider/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/agentsope-agentsop-aider/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 5 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 agentsope-agentsop-aider

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("agentsope-agentsop-aider")
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/agentsope-agentsop-aider/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/agentsope-agentsop-aider/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 5 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 agentsope-agentsop-aider

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("agentsope-agentsop-aider")
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/agentsope-agentsop-aider/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/agentsope-agentsop-aider/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 5 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 agentsope-agentsop-aider

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("agentsope-agentsop-aider")
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/agentsope-agentsop-aider/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/agentsope-agentsop-aider/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 5 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 agentsope-agentsop-aider

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("agentsope-agentsop-aider")
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/agentsope-agentsop-aider/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 5 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 agentsope-agentsop-aider

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("agentsope-agentsop-aider")
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/agentsope-agentsop-aider/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/agentsope-agentsop-aider/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 5 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 agentsope-agentsop-aider

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("agentsope-agentsop-aider")
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/agentsope-agentsop-aider/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/agentsope-agentsop-aider/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 5 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 agentsope-agentsop-aider

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("agentsope-agentsop-aider")
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/agentsope-agentsop-aider/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/agentsope-agentsop-aider/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 5 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 agentsope-agentsop-aider

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("agentsope-agentsop-aider")
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/agentsope-agentsop-aider/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/agentsope-agentsop-aider/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 5 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 agentsope-agentsop-aider

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("agentsope-agentsop-aider")
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/agentsope-agentsop-aider/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/agentsope-agentsop-aider/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 5 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 agentsope-agentsop-aider

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/agentsope-agentsop-aider/SKILL.md https://app.decimal.ai/s/agentsope-agentsop-aider/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/agentsope-agentsop-aider/SKILL.md

This gets SKILL.md only. The skill's 5 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/agentsope-agentsop-aider/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/agentsope-agentsop-aider.json

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 8/24/2026
Source: agentsope/skillalchemy ↗
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

Aider SOP — 终端结对编程的操作系统

一句话：Aider 是“git 工作树 + tree-sitter 仓库地图 + 编辑格式 + 人类在环 REPL”的四元组。理解这四个原语，剩下的都是配置。

1. 何时激活本技能

下列任一情形成立时，按本 SOP 进入 Aider 工作模式：

任务是编辑已有 git 仓库里的代码（不是从零起项目）。
你能把改动范围收敛到 2–5 个文件，或愿意先用 /ask 让模型借助 repo-map 把范围找出来。
你需要逐步可回滚的修改历史（每次编辑一个 commit，/undo 一步回退）。
你在终端里工作（tmux / 远程 ssh / CI）；或者你在写一个把 Aider 当子进程驱动的 agent。
你关心编辑格式对模型质量的影响（diff / udiff / whole / patch 的选择问题）。
你需要 BYOM（自带模型），跑本地 LLM 或非主流厂商。

不应激活的反面信号：见 §6 反模式与边界。

2. 核心心智模型

2.1 四个原语

+------------------+   +------------------+   +------------------+   +------------------+
| 1. Git working   |   | 2. Tree-sitter   |   | 3. Edit format   |   | 4. REPL loop     |
|    tree          |   |    repo-map      |   |    (wire proto)  |   |    (你在环里)    |
|                  |   |                  |   |                  |   |                  |
| - per-edit       |   | - symbol-level   |   | - diff / udiff   |   | - /ask /code     |
|   commit         |   |   summary        |   |   / whole /      |   |   /architect     |
| - /undo          |   | - PageRank over  |   |   patch          |   | - 每轮人手确认   |
| - dirty 文件     |   |   import graph   |   | - 模型适配选择   |   | - 不自主         |
|   先 commit 再编 |   | - 动态预算       |   | - JSON 是反模式  |   |                  |
+------------------+   +------------------+   +------------------+   +------------------+

四者缺一不可：

去掉 git → 失去回滚与审计；
去掉 repo-map → 大仓库里 LLM 找不到正确文件（SWE-Bench Lite 上 repo-map 让 Aider 70.3% 命中正确文件 [aider.chat/2024/05/22/swe-bench-lite.html]）；
用错 edit format → 出现“lazy coding”、SEARCH 块找不到、JSON 句法破坏（udiff 在 GPT-4 Turbo 上把 refactor 基准从 20% 拉到 61% [aider.chat/2023/12/21/unified-diffs.html]）；
放弃 REPL → 退化为自主 agent，但 Aider 在 SWE-Bench 上恰好证明“人在环 + 多次尝试”比纯自主链路更稳。

2.2 LLM 看到的上下文分三层（优先级递减）

层	内容	谁能改
系统提示 + 编辑格式说明	Aider 固化	Aider
只读上下文	repo-map + `/read` 文件 + CONVENTIONS.md	你（通过 `--read`）
读写上下文	`/add` 的文件	LLM 只能编辑这里的文件

铁律：LLM 只允许编辑 /add-ed 的文件。这是 Aider 的安全边界。模型“改错了文件”几乎总是因为该文件没 /add 或你 /add 了太多无关文件。

2.3 上下文预算（25k 信号阈）

"Above about 25k tokens of context, most models start to become distracted." [aider.chat/docs/troubleshooting/edit-errors.html]

把这条当硬约束：超过 25k tokens，编辑准确率断崖式下降。/tokens 持续监控。

2.4 Repo-map 不是 RAG

repo-map 是 tree-sitter 提取的符号清单（类、函数、签名），用 PageRank 在源文件依赖图上排序，塞给 LLM 当地图。这不是 embedding 检索。

为什么不用 embeddings：

LLM 能读签名，但读不懂向量。
不需要维护索引/重建/失效；代码改了下次自动重生成。
/map 可以打印出来人工审计，向量做不到。

预算是动态的：你不 /add 任何文件时，map 占用大；/add 了正确文件后，map 自动缩小，省下的 token 给真正的代码。

2.5 编辑格式是“模型适配问题”，不是“用户偏好”

格式	谁用	强项	弱项
`whole`	弱模型 / GPT-3.5 / 应急回退	解析最稳，无 merge 错误	贵；4k 输出上限会截断
`diff` (SEARCH/REPLACE)	GPT-4o, Sonnet, 多数强模型	token 高效	SEARCH 块必须字节匹配
`diff-fenced`	Gemini 系列	路径放在 fence 内	非主流
`udiff`	GPT-4 Turbo (1106)	模仿 patch 程序的严格性，降低 laziness	提示更重
`patch`	GPT-4.1 (OpenAI patch 协议)	多动作鲁棒	模型特定
`editor-diff` / `editor-whole`	architect 模式的 editor 子模型	提示更瘦，专注编辑	仅在 architect 下有意义

Aider 已经对常见模型选好默认值；只有出现编辑错误时才覆盖。

⇒ 不要把代码编辑包进 JSON tool-call。所有模型在 Aider 的实测里都因此变差，包括 Sonnet（详见 §5 案例 6 与引文）。

3. SOP 工作流

Phase 1 — Bootstrap（每次会话开始）

# 0. 在 git 仓库根目录。stash 或 commit 在途修改。
git status

# 1. 选模型（榜单当前前列：gpt-5, claude-3.7-sonnet, o3-pro, gemini-2.5-pro）
#    [aider.chat/docs/leaderboards/]

# 2. 最小启动 — 让 repo-map 帮 LLM 自己找路
aider

# 3. 范围已知 — 直接预加 + 风格文件
aider src/auth.py tests/test_auth.py --read CONVENTIONS.md

# 4. 强思考 + 廉价编辑（architect 模式）
aider --architect --model o1-preview --editor-model gpt-4o

# 5. 自动测试回路
aider --test-cmd "pytest -x" --auto-test

# 6. 巨型 monorepo
cd packages/feature-foo && aider --subtree-only
# 并维护 .aiderignore

Phase 2 — 收敛范围（`/add` 纪律）

不知道改哪个文件？
  → /ask which files implement <feature>?     (LLM 用 repo-map 回答)
  → /add 它命名的文件（只加这些）

知道改哪个文件？
  → 启动时 CLI 直接传，或 /add path/to/file.py

需要参考但不允许改的文件（schema, config, conventions）？
  → /read path/to/ref.md

铁律重申：少 /add，敢 /drop。/tokens 看现状。

Phase 3 — 讨论再动手（`/ask` → `/code`）

> /ask 当前的 auth 怎么实现？如果改成 JWT 会有什么破坏？
< [模型基于 repo-map + 已 /add 的文件作答]

> /ask 那我们用 PyJWT 还是 authlib？给出权衡。
< [...]

> /code 按刚才讨论的方案，把 sessions 改成 JWT。
< [模型给出 diff]
[Aider 自动应用 → 自动 git commit]

> /test pytest
< [失败时模型看到输出并尝试修复]

"Break your goal down into bite sized steps. Do them one at a time." [aider.chat/docs/usage/tips.html]

Phase 4 — Architect 模式（reasoning ≠ editing）

何时开启：你最好的 reasoner 编辑能力差（典型：o1-preview 单独跑 79.7%，搭配 Sonnet 当 editor 拉到 82.7% [aider.chat/2024/09/26/architect.html]）。

组合	Polyglot Pass@2	备注
o1-preview (architect) + o1-mini (editor, whole)	85%	SOTA 当时；慢，不适合交互
o1-preview + Sonnet	82.7%	"entirely practical"
Sonnet + Sonnet	80.5%	比单跑 77.4% 高
GPT-4o + GPT-4o	75.2%	比单跑 71.4% 高

启用：--architect 或 /architect。Aider 自动把 editor 切到 editor-diff / editor-whole。

Phase 5 — 验证（lint / test / run）

/lint                  # 默认 --auto-lint 已开
/test pytest -x        # 失败时输出回填到 chat
/run npm run typecheck # 输出可选择性回填
/diff                  # 看上一轮的 diff

"Aider will try and fix any errors if the command returns a non-zero exit code." [aider.chat/docs/usage/lint-test.html]

formatter 注意：把会重写文件并返回非零的 formatter 包装在双跑脚本里（第一遍 format，第二遍验证）。

Phase 6 — 上下文卫生

症状	操作
`/tokens` > 25k	`/drop` 不再需要的文件
话题切换	`/clear`（保留文件，清历史）
想全新开始	`/reset`（丢文件 + 清历史）
模型反复改错文件	`/ls` 检查；`/drop` 多余的；`/add` 缺的
反复 edit format 错误	`/clear`；换模型；`--edit-format whole` 兜底

Phase 7 — 收尾

git log --oneline 看一次会话的提交链。
想压成一个 feature commit：git rebase -i HEAD~N（先保留中间 commit 当 undo 栈，最后压）。
提 PR — 提交信息已经是 Conventional Commits 风格。

4. 操作模型（命令速查）

源：[aider.chat/docs/usage/commands.html]

/add <files>      把文件加入 chat（LLM 可编辑）
/read <file>      加为只读（LLM 不能编辑）
/drop <files>     从 chat 移除
/ls               列出已知文件 + 标注哪些在 chat 里
/ask <q>          只讨论，不动文件
/code <req>       明确要求改代码（不加前缀也行）
/architect <req>  双模型 architect+editor
/model <name>     切换主模型
/clear            清 chat 历史（保留文件）
/reset            丢文件 + 清历史
/tokens           当前 token 占用
/map              打印当前 repo-map
/diff             上一轮的 diff
/undo             回退最近一次 Aider commit
/commit           为 chat 外的改动生成 commit
/run <cmd>        跑命令，可选回填输出（别名 !）
/test <cmd>       跑测试，失败时回填
/web <url>        抓网页转 markdown 进 chat
/copy             复制最后一条回复
/help <q>         关于 Aider 本身的问题

CLI 关键标志：

--model X                 主模型
--editor-model Y          editor 子模型（architect 用）
--edit-format whole|diff|udiff|patch
--editor-edit-format ...  editor 子模型的格式
--architect               进入 architect 模式
--read FILE               只读上下文（可多次）
--map-tokens N            repo-map 预算；N=0 关闭
--subtree-only            仅本子目录 + 子树
--auto-lint / --no-auto-lint
--test-cmd CMD --auto-test
--no-auto-commits         关掉自动提交（不建议）
--no-git                  完全脱 git（失去安全保障）
--message "..."           一次性非交互模式（脚本/agent 用）
--yes                     全部确认（脚本/agent 用）

配置文件：.aider.conf.yml（持久 CLI 默认）、.aiderignore（排除 repo-map 路径）、CONVENTIONS.md（用 --read 加载）。

5. 困境决策案例 (Examples / Scenarios)

案例 1 — “模型一直改错文件”

触发：LLM 改的不是你想改的文件，或编造路径。

诊断：LLM 只能安全编辑 /add 的文件。要么目标没 /add，要么 /add 太多导致干扰。

决策规则：

/ls 看现状。
缺目标 → /add path/to/target.py。
太多文件（>4–5 或 tokens > 25k）→ /drop 无关的。
不知道哪个文件 → /ask which file implements X?，让 repo-map 替你答。

为什么有效：/add-ed 文件就是写集合（write-set）。repo-map 只是可读地图，不是写集合。

案例 2 — “大仓库里上下文炸了”

触发：tokens 涨到 25–50k+，响应被截断，模型在 monorepo 上明显变笨。

决策规则（从最便宜的做起）：

步	动作
1	`/tokens` 看占用分布
2	`/drop` 不再需要的文件
3	`/clear` 清聊天历史（保留文件）
4	`--map-tokens 1024`（或弱模型 `0`）
5	monorepo：进子目录 + `--subtree-only`；加 `.aiderignore`
6	拆任务：每个子任务一个会话

关键认知：不要“为了保险全 /add”。SWE-Bench 数据，只靠 repo-map Aider 仍然 70.3% 选对文件 [aider.chat/2024/05/22/swe-bench-lite.html]。

案例 3 — “diff 格式不停 hallucinate / SEARCH 块找不到”

触发：Aider 报 “SEARCH block not found in file”。

诊断：模型给的 SEARCH 文本和文件字节不匹配（空白、前次失败后状态漂移、纯臆造）。

决策规则：

/tokens — 接近 25k 时合规率下降。
/drop + /clear 减负。
升级模型；弱模型“更容易违背系统提示” [aider.chat/docs/troubleshooting/edit-errors.html]。
兜底格式：--edit-format whole。贵但稳。
试 --architect —— 双步流程对“执行编辑指令”的依从性更高。

历史教训：GPT-4 Turbo 上 unified-diff 把 refactor 基准从 20% 拉到 61%，并把 “lazy comment” 砍到 1/3 [aider.chat/2023/12/21/unified-diffs.html]。说明 格式工程的边际收益经常高于换模型。

案例 4 — “architect 模式值得花这个钱吗？”

触发：硬推理任务；你有 o1/o3（强 reasoner，但编辑差）。

决策规则：

情况	建议
reasoner 编辑也干净（GPT-4o, Sonnet）	不开 architect。单跑就行
reasoner 编辑差（o1-preview 单跑 79.7%）	开 architect：o1-preview + Sonnet → 82.7%
追 SOTA、能等	o1-preview + DeepSeek/o1-mini whole → 85%（慢，"probably not practical for interactive use"）
例行编辑	单跑更快更省

反直觉点：连 Sonnet 自配 editor 也涨（77.4 → 80.5%）。但 +3pp 是否值翻倍的 token 成本，取决于场景。

案例 5 — “Sonnet 写超长被 4k 截断”

触发：Claude 3.5 Sonnet 回复在编辑中段截断。

诊断：Sonnet 倾向写太多——整文件 SEARCH/REPLACE 而不是最小 diff [aider.chat/2024/07/01/sonnet-not-lazy.html]。

决策规则：

升级 Aider；它已经支持 “multiple 4k token responses... seamlessly combines them” 并加了精简提示。修复后 Sonnet 的 refactor 基准 55.1 → 64.0%。
还截断时，手动追加：“Make minimal SEARCH/REPLACE blocks. Do not quote unchanged sections.”

案例 6 — “该用 JSON tool-call 包代码吗？”

触发：自建 agent 包 Aider 时考虑结构化 tool-call。

决策规则：不要把代码包进 JSON tool-call。

"All of the models did worse on the benchmark when asked to return code in a structured JSON response." [aider.chat/2024/08/14/code-in-json.html]

即便用 OpenAI strict mode 强制 JSON 合法，JSON 里的代码本身也劣化（更多 SyntaxError / IndentationError）。若 harness 必须 tool-call，把代码塞单一字符串字段，并预期质量损失。

6. 反模式与边界

不要用 Aider 的场景

场景	替代
从零起项目（无 git history、无现有代码）	Cursor 一类，或纯 LLM 对话
跨千个文件的机械重构	先用 sed / AST 工具 / IDE 重构；Aider 收尾语义部分
不能用 git 的工作流（Perforce-only、二进制资产）	别用 Aider；它的安全保障建立在 git 之上
需要 IDE/浏览器感知（实时 diagnostics、devtools）	Cline / Continue / Cursor — Aider 看不到 IDE
完全自主的 ticket→PR	OpenHands / Devin — Aider 是人在环设计

常见错误

多 /add 求保险——反而干扰模型。/drop 才是常态操作。
忽略 repo-map——以为“模型不知道”就乱加文件。/map 看一下它已经知道什么。
architect 模式用弱 editor——再好的 reasoner，editor 不会写格式也白搭。Sonnet / DeepSeek / GPT-4o 才是合格 editor。
不 /clear——长会话历史漂移会让模型“记住错的东西”。话题切换就清。
关 auto-commit “保历史干净”——失去 /undo 栈。正确做法是事后 git rebase -i 压。
CONVENTIONS.md 不写——风格（用 httpx 不用 requests、加 type hints）反复纠正不如一次写进 --read CONVENTIONS.md；formatter 返回非零会搞砸 auto-lint，用双跑脚本包一下。

Aider 有意不做的事（硬边界）

不渲染 IDE（保持终端纯净）。
不维护 embedding 索引（repo-map 按需重生成）。
默认不自主（人在环是设计哲学，Paul 论证过这是生产力优势）。
一会话一仓库（跨仓库需要更高层编排）。
无跨会话长期记忆（持久化靠 CONVENTIONS.md、.aider.conf.yml、git history 本身）。

7. 生态对照

	Aider	Cline	Cursor	Continue	OpenHands
表面	终端 REPL	VS Code 扩展	闭源 IDE（VS Code fork）	VS Code + JetBrains 扩展	Web UI + Docker 沙箱
开源	Apache 2.0	是	否	是	MIT
编辑原语	diff/udiff/whole 文本 + git commit	tool-call + 每步人审	内嵌 Composer 多文件	Edit/Chat/Agent/Autocomplete	自主 plan→edit→test→PR
上下文	tree-sitter repo-map + 选择性 /add	按需 tool-call 读	全仓库索引	RAG	agentic 读
人审	每轮（`/undo` 兜底）	每个 tool-call	每次 Composer apply	每次 edit	无
Git 集成	原生（每编辑一 commit）	通过终端工具	手动	手动	沙箱里 PR
BYOM	是（100+，经 LiteLLM）	是	受限	是	是

来源：[frontman.sh/blog/best-open-source-ai-coding-tools-2026]、[cline.bot/blog/top-9-cursor-alternatives-in-2025]、[opensourcealternatives.to]、[shakudo.io/blog/best-ai-coding-assistants]。

何时选 Aider 而非其他

你住在终端：tmux + vim/emacs + Aider 是经典栈，零 IDE 切换。
你要 git-clean 历史：per-edit commit 自动产出可审计提交链。
你在写 agent：--message、--yes、配置文件 → 子进程驱动友好。
你关心编辑格式工程：Aider 在 udiff、architect、JSON-vs-text 上有最多公开实验数据。
你要确定性上下文：tree-sitter 地图可 /map 检查、可复现、无向量库依赖。
任务已收敛：你知道 2–5 个目标文件。

反过来选别的

Cline：要 VS Code 内每个编辑 / shell 命令的逐步确认。Aider 是事后 /undo；Cline 是事前 approve。
Cursor：要内嵌 diff 浮层、ghost-text 自动补全、视觉化文件上下文指示。
Continue：要跨 IDE（VS Code + JetBrains）一致体验，要 autocomplete + chat + agent 一体。
OpenHands：要自主ticket→PR；issue 进、PR 出。Aider 没瞄准这场景。

Aider 留给 agent-coder 的研究遗产

即便你选别的前端，Aider 的公开实验是这些决定的参考：编辑格式选择（GPT-4 Turbo refactor 20%→61%）、repo-map 战胜 RAG（SWE-Bench Lite 70.3%）、architect+editor 拆分（79.7%→85%）、JSON-vs-text 劣化、lazy-coding 缓解——具体数据见前文各节。

引用源

[aider.chat/docs/usage.html] [aider.chat/docs/usage/tips.html] [aider.chat/docs/usage/modes.html] [aider.chat/docs/usage/commands.html] [aider.chat/docs/usage/conventions.html] [aider.chat/docs/usage/lint-test.html]
[aider.chat/docs/repomap.html] [aider.chat/docs/more/edit-formats.html] [aider.chat/docs/git.html] [aider.chat/docs/faq.html]
[aider.chat/docs/troubleshooting/edit-errors.html] [aider.chat/docs/troubleshooting/token-limits.html]
[aider.chat/docs/leaderboards/]
[aider.chat/2023/12/21/unified-diffs.html] [aider.chat/2024/04/09/gpt-4-turbo.html] [aider.chat/2024/05/22/swe-bench-lite.html] [aider.chat/2024/07/01/sonnet-not-lazy.html] [aider.chat/2024/08/14/code-in-json.html] [aider.chat/2024/09/26/architect.html]
[aider.chat/HISTORY.html]
[github.com/Aider-AI/aider]（生态对照来源见 §7）

When it activates

Automatically, when a task matches. Use when editing code in an existing git repo via an LLM, when you need to converge a change to 2-5 files, pick an edit format that fits the model, run architect+editor mode, or wire an auto-test loop.

About this skill

Automatic

Coding pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

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

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

agentsope / skillalchemy

skills/agentsop-aider/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1Bundled 5 files

Illustrative Want to see what agentsope/agentsop-aider 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

Aider SOP — 终端结对编程的操作系统

1. 何时激活本技能

2. 核心心智模型

2.1 四个原语

2.2 LLM 看到的上下文分三层（优先级递减）

2.3 上下文预算（25k 信号阈）

2.4 Repo-map 不是 RAG

2.5 编辑格式是“模型适配问题”，不是“用户偏好”

3. SOP 工作流

Phase 1 — Bootstrap（每次会话开始）

Phase 2 — 收敛范围（/add 纪律）

Phase 3 — 讨论再动手（/ask → /code）

Phase 4 — Architect 模式（reasoning ≠ editing）

Phase 5 — 验证（lint / test / run）

Phase 6 — 上下文卫生

Phase 7 — 收尾

4. 操作模型（命令速查）

5. 困境决策案例 (Examples / Scenarios)

案例 1 — “模型一直改错文件”

案例 2 — “大仓库里上下文炸了”

案例 3 — “diff 格式不停 hallucinate / SEARCH 块找不到”

案例 4 — “architect 模式值得花这个钱吗？”

案例 5 — “Sonnet 写超长被 4k 截断”

案例 6 — “该用 JSON tool-call 包代码吗？”

6. 反模式与边界

不要用 Aider 的场景

常见错误

Aider 有意不做的事（硬边界）

7. 生态对照

何时选 Aider 而非其他

反过来选别的

Aider 留给 agent-coder 的研究遗产

引用源

When it activates

SkillSafety

Source

Related skills

More in the registry

Phase 2 — 收敛范围（`/add` 纪律）

Phase 3 — 讨论再动手（`/ask` → `/code`）