Ready to supercharge your AI agents?

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

Developing PenguinHarness · prism-shadow | DecimalAI

Codingby prism-shadow

Developing PenguinHarness

Use when developing PenguinHarness itself — changing packages/{core,server,web,cli,desktop,landing,docs,skills}, the built-in model catalog, the installers or the release workflow; writing or auditing changelog entries; writing a blog post or capturing release screenshots; deciding what to do about data already on disk; or auditing prose that reads like a leaked authoring session. Covers the two-repo symlink layout, the CI-parity verification chain, the record-and-ship contract, where blog media

Never made a case worseMaintained

SkillScore

SkillScore91/100

Test results 91

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

14%91%of test cases passed +77 pts

Without skill3 of 22

With skill20 of 22

17 fixed3 passed either way2 still failing0 broke

Measured on gemini-3.6-flash11/6/2026v4

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskI'm updating CONTRIBUTING.md and a couple of markdown files under .agents/. What is the fastest verification command I should run to test my diff?

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 prism-shadow-penguin-harness-dev
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("prism-shadow-penguin-harness-dev")
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 prism-shadow-penguin-harness-dev

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/prism-shadow-penguin-harness-dev/SKILL.md https://app.decimal.ai/s/prism-shadow-penguin-harness-dev/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/prism-shadow-penguin-harness-dev/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 prism-shadow-penguin-harness-dev

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("prism-shadow-penguin-harness-dev")
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/prism-shadow-penguin-harness-dev/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/prism-shadow-penguin-harness-dev/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 prism-shadow-penguin-harness-dev

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("prism-shadow-penguin-harness-dev")
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/prism-shadow-penguin-harness-dev/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/prism-shadow-penguin-harness-dev/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 prism-shadow-penguin-harness-dev

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("prism-shadow-penguin-harness-dev")
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/prism-shadow-penguin-harness-dev/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/prism-shadow-penguin-harness-dev/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 prism-shadow-penguin-harness-dev

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("prism-shadow-penguin-harness-dev")
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/prism-shadow-penguin-harness-dev/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/prism-shadow-penguin-harness-dev/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 prism-shadow-penguin-harness-dev

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("prism-shadow-penguin-harness-dev")
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/prism-shadow-penguin-harness-dev/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/prism-shadow-penguin-harness-dev/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 prism-shadow-penguin-harness-dev

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("prism-shadow-penguin-harness-dev")
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/prism-shadow-penguin-harness-dev/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/prism-shadow-penguin-harness-dev/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 prism-shadow-penguin-harness-dev

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("prism-shadow-penguin-harness-dev")
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/prism-shadow-penguin-harness-dev/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 prism-shadow-penguin-harness-dev

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("prism-shadow-penguin-harness-dev")
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/prism-shadow-penguin-harness-dev/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/prism-shadow-penguin-harness-dev/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 prism-shadow-penguin-harness-dev

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("prism-shadow-penguin-harness-dev")
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/prism-shadow-penguin-harness-dev/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/prism-shadow-penguin-harness-dev/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 prism-shadow-penguin-harness-dev

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("prism-shadow-penguin-harness-dev")
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/prism-shadow-penguin-harness-dev/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/prism-shadow-penguin-harness-dev/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 prism-shadow-penguin-harness-dev

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("prism-shadow-penguin-harness-dev")
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/prism-shadow-penguin-harness-dev/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/prism-shadow-penguin-harness-dev/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 prism-shadow-penguin-harness-dev

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("prism-shadow-penguin-harness-dev")
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/prism-shadow-penguin-harness-dev/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/prism-shadow-penguin-harness-dev/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 prism-shadow-penguin-harness-dev

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/prism-shadow-penguin-harness-dev/SKILL.md https://app.decimal.ai/s/prism-shadow-penguin-harness-dev/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/prism-shadow-penguin-harness-dev/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/prism-shadow-penguin-harness-dev/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/prism-shadow-penguin-harness-dev.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: v4, tested 11/6/2026
Source: prism-shadow/penguin-harness ↗
License: Apache-2.0

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

Developing PenguinHarness

PenguinHarness is a TypeScript monorepo: an Agent SDK (packages/core), an HTTP server (packages/server), a Web App (packages/web), a CLI (packages/cli), an Electron shell (packages/desktop), the landing and docs sites, and the shipped plugin library — one npm package per plugin under the repo root's plugins/, each declaring what it carries in src/index.ts, which its build turns into the ifaces.json core's loader reads; the server is the host package that depends on them all. It consumes LLM providers through @prismshadow/mmsp (MMSP, formerly @prismshadow/agenthub) and implements no provider clients of its own.

This page is the part that applies to every change. The reference files carry the detail, read them when the task reaches them:

Read	When
`reference/verification.md`	A test fails oddly, CI reads green when it should not, or the user asks you to run the suite on another machine
`reference/changelog.md`	Writing or auditing a changelog entry
`reference/model-catalog.md`	Touching the server's model catalog, pricing, provider groups, which environment variable a keyless row reads, or glyphs
`reference/authoring.md`	Writing a blog post, auditing prose, or proposing a simplification
The `penguin-harness-writing` skill	Writing or revising a blog post, a docs page or landing copy: a gateway model writes every word, through its prompts and checks
`reference/release.md`	Preparing a release: the branch order, what changes, the announcement, the blog post and its screenshots
`reference/testing.md`	Writing or changing any test: scenarios first, behaviour only, one fake per boundary, branch coverage, speed, CI time as a cost
`reference/ai-slop.md`	Every change a user sees or reads: UI, styles, UI strings, docs, landing, blog, changelog — the rules, the scanner, the catalogue of tells

No AI slop — every time something is rendered or written

Whatever you add to the UI or the copy, check it before you call it done: decide before you decorate; one accent, one voice; hierarchy from scale and space; subtract first; specific beats punchy; decoration must mean something. No gradients, glows, emoji, pill spam, cards in cards, coloured keywords or "it's not just X — it's Y". Reuse the theme tokens and lib/tone.ts; status is a labelled pill or an icon plus a tooltip, never a bare coloured dot; sections are ruled, not boxed. Run node .agents/skills/penguin-harness-dev/reference/ai-slop/scan.mjs <what you touched> and triage every hit. reference/ai-slop.md has the repo's own decisions and the full catalogue.

A copy request changes words, in place. When the owner asks for new copy, swap the words inside the existing layout: removing or restyling a section, element, type size, number or animation needs the owner's explicit say, and a feature demo is the real software (a capture of the running Web App or a live gallery frame), never an imitation UI or a scripted replay.

Repo shape — read before your first edit

Two repositories sit side by side: the implementation repo (penguin-harness) and the design repo (penguin-harness-design). Three paths inside the implementation repo are symlinks into the design repo and are gitignored here:

design/ → the design repo, so specs are reachable as design/specs/…
AGENTS.md → design/AGENTS.md
CLAUDE.md → AGENTS.md

Editing AGENTS.md, CLAUDE.md or anything under specs/ edits the design repo's files. Commit them there, on their own branch, in their own PR. They can never appear in an implementation-repo PR. A fresh clone has none of the three links; recreate them by hand. A clone with no design repo beside it — the normal state for a remote or throwaway environment — has nothing to link to, so it carries no AGENTS.md at all and these skills are its whole contract.

Both repos take changes through branch + PR against main, squash-merged. Do not push to main, and gh pr create --base main — not dev, whatever a sibling repo does.

Branches are feat/<topic>, fix/<topic>, docs/<topic> in both repos. Some older branches here read docs-<topic> instead: a remote branch literally named docs once held that ref namespace and made the slashed form unpushable. It is gone — if a push is ever rejected as a directory/file conflict again, git ls-remote --heads origin names the branch responsible.

Independent changes each get their own git worktree under ../penguin-harness-wt/<topic>/ so several can run in parallel.

Keep searches inside the worktree you are working in. Scanning the home directory or the whole disk is rarely worth it: it is slow, and what it turns up outside the tree is usually another checkout's copy of the file you are already looking at. When a path does not resolve, prefer narrowing — reason about the package layout, ask git ls-files, follow the conventions above — over widening the root. The only paths outside the worktree worth reading are the siblings named here: ../penguin-harness-design for specs, ../penguin-harness-wt/* for another topic's tree, and ../agenthub for MMSP where it is checked out (the checkout keeps the library's former name). Reach them by name; never find them by scanning. Say all of this to every subagent you dispatch — widening the search root is the first move a subagent makes when a path does not resolve.

Tests prove behaviour, not the source

Before a test, write its scenarios (Given / When / Then) in the file header; one it per scenario, named as the behaviour. Assert only what the caller can observe — and look first for what must not happen (a retry that must not duplicate, a refusal that must not write). Never test a constant, a copied table, a UI string against its dictionary, or which private helper ran. Fake only at the system's edge with the package's shared helpers (one fetch fake, one mock LLM, createTestApp, real temp dirs, fake timers); do not vi.mock the package's own modules. Every branch a change adds is taken by a scenario; pruning never lowers branch coverage. No real sleeps, no per-test servers. CI time is a cost paid three times (Linux, macOS, Windows): keep each test well under a second, and check your PR's job durations after CI. reference/testing.md has the rules and the checklist.

Verify what you changed

Node must be >= 24. In each worktree, pnpm install --frozen-lockfile first.

The full chain CI runs is pnpm build, pnpm format:check, pnpm typecheck, pnpm test, sh scripts/test-installer.sh. Do not reach for pnpm test by reflex — it is nine packages and ~2500 tests, minutes per run, and for a docs-only diff it proves nothing the narrow run does not. Pick the narrowest evidence that would actually fail for this change's regression:

pnpm --filter @prismshadow/penguin-server exec vitest run test/model-catalog.test.ts # one file, ~2s
pnpm --filter @prismshadow/penguin-web test                                          # one package

Changed	Run
Markdown only — changelog, `.github/CONTRIBUTING.md`, `.agents/`, README	`pnpm format:check`
`packages/docs/content/`, blog posts under `packages/landing/content/`	`format:check` + the `docs` and `landing` package tests (search index, blog fixtures)
`plugins/**` (repo root)	that plugin's `build` (a change to `src/index.ts` reaches the library only through the `ifaces.json` it writes) and its own `test` where it has one, the server's `plugin-library.test.ts` (every shipped package reads clean, the README tables), core's `goal-hooks.test.ts` / `continual-learning-hook.test.ts` / `plugin-porting.test.ts` when those scripts changed, `docs`'s `skills-sync.test.ts`, and `node scripts/check-plugin-versions.mjs origin/main`
The model catalog	server `model-catalog.test.ts` and `models.test.ts`, web `model-grouping.test.ts` and `protocol-path.test.ts`
The credential rule or a row's effective connection	core `model-connection.test.ts`, server `models.test.ts` and `models-balance.test.ts`
Request assembly, history rebuild, compaction, the system prompt, a tool's description or schema	core's three `prompt-cache-*` suites — read the section below before you touch what they report
One package's source	that package's `test`, plus `typecheck`
Exported core types, or anything downstream imports	`pnpm build` + `pnpm typecheck` before any test
Anything that opens, folds, resizes or animates in the Web App or `packages/ui`	the `ui` and `web` tests + frames captured mid-transition in all three themes (`penguin-harness-frontend`, "Motion"); a resting screenshot is not evidence
A remote test tree after `main` moved (a merge, a rebase)	rebuild `@prismshadow/penguin-server...` there first: a stale core `dist` reads as dozens of TS2305 "no exported member" errors in web and the gallery
`package.json`, the lockfile, `pnpm-workspace.yaml`	`pnpm install --frozen-lockfile` + `pnpm build`
Installers, `release.yml`	`sh scripts/test-installer.sh`

Always cheap, always worth it: git diff --check, and pnpm format + format:check on any diff at all.

Run the whole chain in exactly three cases: the change spans the repo widely enough that nothing narrower is credible, you are diagnosing a CI failure, or you are asked to. There are no coverage thresholds in this repo, so nothing forces a wider run than the behavior needs.

Tests run on this machine unless the user asks otherwise. Moving a suite to another host is something they request in so many words, not an optimisation to take on your own — see reference/verification.md for how, and for why a difference between two machines is a finding rather than something to paper over.

Once the evidence you chose passes, commit and push to the current branch without asking. Force-pushes and reverting someone else's commits still need confirmation.

When a test fails in a way that does not match your diff, when CI reads green too easily, or when a fake or an assertion looks like it proves nothing, read reference/verification.md before spending a second round on it.

A prompt-cache miss is a cost regression, and it has to be said out loud

A provider serves a cached prefix only while the next request repeats the previous one byte for byte from the front: the model id, the tools, the fast-mode parameters, the system prompt, the remaining prompt-affecting parameters, then the messages. Everything from the earliest divergence onward is re-read at full price, on every request of every running conversation — not only the one in front of you. A word added to a tool description costs far more than its own tokens.

Three suites in packages/core/test hold that line, and a failure means something different in each:

Failing	What it is telling you
`prompt-cache-invariants.test.ts`	Your change made a request stop extending its predecessor. This is the regression itself; the diagnostic names the tier that diverged and estimates the input that falls after it.
`prompt-cache-lifecycle.test.ts`	The same thing counted in provider tokens. A number that went down is money.
`prompt-cache-simulator.test.ts`	You changed the rule engine, not the harness. Only correct when the provider's documented rules changed — go and check the documentation, not the test.

Never re-baseline these to green. Editing an expected number, or adding a case to the list of misses that are there by design, is a decision about spending the user's money — not a fix. Put the tier that moved and what it costs in front of them and let them decide.

And say it in the reply, not only in a test log. A cache regression shows up in no other signal this repo produces: nothing is slower, nothing is wrong on screen, and CI goes green the moment the numbers are edited. If you do not raise it, it ships.

Record and ship

Every change ships a changelog entry, in both languages, in changelog/unreleased/: a YYYY-MM-DD-<slug>.md and YYYY-MM-DD-<slug>.zh.md pair mirroring section for section, inside the PR that makes the change. One without the other is unfinished, there is no index file, and reasoning belongs in the PR description rather than on disk.

A conclusion is not a deliverable. Do not package findings as a standalone page, artifact or report file: it detaches them from the diff they are about and no one opens it twice. A review's findings go in PR comments, on the lines they concern; everything else goes in the PR description and in the reply to whoever asked.

changelog/README.md is the full spec and reference/changelog.md has the shape plus the traps (the metadata block's fixed order, translated headings, #N numbers that are often issues rather than PRs, and the PR: field everyone forgets). Read one of them before writing an entry rather than pattern-matching a neighbouring one.

Backward compatibility is the user's call, not yours

When a change touches data or configuration already on disk — Traces, system_config.yaml, .project_config.toml, installed skills, web.db, localStorage keys — do not pick a strategy. State plainly what breaks if nothing is done, offer the options (permanent dual-format tolerance / one-time migration / a documented reset path / accept the break and say so), and let the user decide.

Whatever is decided, compatibility code is a standing cost: name how long it stays, who removes it, and what has to be true first, at the code site and in a dedicated changelog/unreleased/YYYY-MM-DD-backward-compatibility.md. Other entries in that batch reference that file instead of re-telling it. A batch with no compatibility handling has no such file.

Core never special-cases a model, provider or gateway

packages/core/src contains no model ids, provider ids, vendor hostnames or endpoints, and no catalog data. Model knowledge lives in the server's catalog (packages/server/src/model-catalog/, published as the browser-safe @prismshadow/penguin-server/model-catalog, which the Web App, the CLI and the gallery import) and reaches core only through the Project config the server seeds — [providers.<id>], [[models]], default_model — or through host hooks (AgentAssembly). Nor does any package keep environment or refusal logic: which variable a keyless model reads, and which base URL is refused without a key, is MMSP's rule. Core passes the file's key, base URL and client type to MMSP verbatim, and every preview asks MMSP's @prismshadow/mmsp/credentials (the catalog's env-keys.ts). The one exception is App attribution: llm/app-attribution.ts (attributionHeaders) names the gateways whose headers GenerativeModel attaches. A change that wants core to know a model or a vendor belongs in the catalog and the config it seeds instead; a core test that needs a Project writes a fixture (test/seeded-project.ts), never the catalog.

One concern per module

Logic with its own reason to change — an identification scheme (App attribution), a migration, a derivation rule (which variable a keyless row reads), a protocol mirror (MMSP's routing table) — gets a file of its own beside its caller, never a section appended to a large neighbour. A change that moves or reshapes a large file splits it along its concerns, keeping the import graph acyclic: a module cycle that reads a binding at load time fails with a TDZ ReferenceError. The case that set the rule: #1167 first put App attribution at the top of generative-model.ts.

The message protocol is closed by default

AMSP records are closed by default. No new field, type or enum value unless the fact is unrepresentable by existing records and underivable by readers; prefer recording earlier or streaming an existing record over a new field. Say so in the PR. The architecture spec's message-format section states the rule, and packages/amsp/src/records/types.ts repeats it at its head.

About this skill

Automatic

Coding pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v8 — 11/6/2026

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

prism-shadow / penguin-harness

.agents/skills/penguin-harness-dev/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 11/6/2026Version v4Bundled 1 file · scripts

Illustrative Want to see what prism-shadow/penguin-harness-dev 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

Developing PenguinHarness

No AI slop — every time something is rendered or written

Repo shape — read before your first edit

Tests prove behaviour, not the source

Verify what you changed

A prompt-cache miss is a cost regression, and it has to be said out loud

Record and ship

Backward compatibility is the user's call, not yours

Core never special-cases a model, provider or gateway

One concern per module

The message protocol is closed by default

SkillSafety

Source

Related skills

More in the registry