Ready to supercharge your AI agents?

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

spec-kitty-runtime-next · priivacy-ai | DecimalAI

Agent Toolingby priivacy-ai

spec-kitty-runtime-next

Drive the canonical spec-kitty next --mission <handle> control loop for mission advancement. Load agent profiles at init, apply action-scoped doctrine context at each step boundary, and pull specific tactics/directives on demand. Triggers: "run the next step", "what should runtime do next", "advance the mission", "what is the next task", "continue the workflow", "what step comes next". Does NOT handle: setup or repair requests, purely editorial glossary or doctrine maintenance, or direct code re

Never made a case worseMaintained

SkillScore

SkillScore91/100

Test results 91

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

23%91%of test cases passed +68 pts

Without skill5 of 22

With skill20 of 22

15 fixed5 passed either way2 still failing0 broke

Measured on gemini-3.6-flash9/9/2026v419 comparable

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskI want to check what action the runtime recommends for mission 'data-pipeline' without advancing its state or claiming that the previous action succeeded. Which exact command should I run?

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 priivacy-ai-spec-kitty-runtime-next
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("priivacy-ai-spec-kitty-runtime-next")
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 priivacy-ai-spec-kitty-runtime-next

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/priivacy-ai-spec-kitty-runtime-next/SKILL.md https://app.decimal.ai/s/priivacy-ai-spec-kitty-runtime-next/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/priivacy-ai-spec-kitty-runtime-next/SKILL.md

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

Other ways to add it

Claude Code docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[claude-agent-sdk]"
decimalai skills add priivacy-ai-spec-kitty-runtime-next

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("priivacy-ai-spec-kitty-runtime-next")
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/priivacy-ai-spec-kitty-runtime-next/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/priivacy-ai-spec-kitty-runtime-next/SKILL.md").read_text()
options = ClaudeAgentOptions(system_prompt=f"You are a helpful agent.\n\n{skill}", max_turns=6)

async def main():
    async for message in query(prompt="Hello!", options=options):
        print(message)

# In a notebook or async code: await main()
asyncio.run(main())

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

Other ways to add it

Claude Agent SDK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[openai-agents]"
decimalai skills add priivacy-ai-spec-kitty-runtime-next

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("priivacy-ai-spec-kitty-runtime-next")
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/priivacy-ai-spec-kitty-runtime-next/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/priivacy-ai-spec-kitty-runtime-next/SKILL.md").read_text()
agent = Agent(name="support", instructions=f"You are a helpful agent.\n\n{skill}")
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")

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

Other ways to add it

OpenAI Agents docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[openai]"
decimalai skills add priivacy-ai-spec-kitty-runtime-next

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("priivacy-ai-spec-kitty-runtime-next")
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/priivacy-ai-spec-kitty-runtime-next/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/priivacy-ai-spec-kitty-runtime-next/SKILL.md").read_text()
reply = client.chat.completions.create(
    model="gpt-5.4-mini",
    messages=[
        {"role": "system", "content": f"You are a helpful agent.\n\n{skill}"},
        {"role": "user", "content": "Hello!"},
    ],
).choices[0].message

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

Other ways to add it

OpenAI SDK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[anthropic]"
decimalai skills add priivacy-ai-spec-kitty-runtime-next

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("priivacy-ai-spec-kitty-runtime-next")
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/priivacy-ai-spec-kitty-runtime-next/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/priivacy-ai-spec-kitty-runtime-next/SKILL.md").read_text()
reply = client.messages.create(
    model="claude-haiku-5-5",
    max_tokens=4096,
    system=f"You are a helpful agent.\n\n{skill}",
    messages=[{"role": "user", "content": "Hello!"}],
)

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

Other ways to add it

Anthropic docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[google-genai]"
decimalai skills add priivacy-ai-spec-kitty-runtime-next

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("priivacy-ai-spec-kitty-runtime-next")
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/priivacy-ai-spec-kitty-runtime-next/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/priivacy-ai-spec-kitty-runtime-next/SKILL.md").read_text()
response = client.models.generate_content(
    model="gemini-3.5-flash",
    contents="Hello!",
    config=types.GenerateContentConfig(system_instruction=f"You are a helpful agent.\n\n{skill}"),
)

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

Other ways to add it

Gemini API docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[langchain]" langchain-openai
decimalai skills add priivacy-ai-spec-kitty-runtime-next

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("priivacy-ai-spec-kitty-runtime-next")
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/priivacy-ai-spec-kitty-runtime-next/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/priivacy-ai-spec-kitty-runtime-next/SKILL.md").read_text()
agent = create_agent("openai:gpt-5.4-mini", tools=[], system_prompt=f"You are a helpful agent.\n\n{skill}")
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

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

Other ways to add it

LangChain docs

CrewAI's own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" "crewai>=1.15.27"
decimalai skills add priivacy-ai-spec-kitty-runtime-next

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("priivacy-ai-spec-kitty-runtime-next")
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/priivacy-ai-spec-kitty-runtime-next/SKILL.md

Give it to your agent

from pathlib import Path
from crewai import Agent, Crew, Task

agent = Agent(
    role="Support", goal="Help the customer", backstory="A support agent.",
    llm=llm,                         # your own CrewAI LLM
    skills=[Path(".agents/skills")],
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()

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

Other ways to add it

CrewAI docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[adk]"
decimalai skills add priivacy-ai-spec-kitty-runtime-next

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("priivacy-ai-spec-kitty-runtime-next")
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/priivacy-ai-spec-kitty-runtime-next/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/priivacy-ai-spec-kitty-runtime-next/SKILL.md").read_text()
agent = LlmAgent(
    name="support",
    model="gemini-3.5-flash",
    instruction=lambda context: f"You are a helpful agent.\n\n{skill}",
)

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

Other ways to add it

Google ADK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[pydantic-ai]"
decimalai skills add priivacy-ai-spec-kitty-runtime-next

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("priivacy-ai-spec-kitty-runtime-next")
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/priivacy-ai-spec-kitty-runtime-next/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/priivacy-ai-spec-kitty-runtime-next/SKILL.md").read_text()
agent = Agent("openai:gpt-4o-mini", instructions=f"You are a helpful agent.\n\n{skill}")
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")

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

Other ways to add it

Pydantic AI docs

Deep Agents' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" deepagents
decimalai skills add priivacy-ai-spec-kitty-runtime-next

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("priivacy-ai-spec-kitty-runtime-next")
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/priivacy-ai-spec-kitty-runtime-next/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/priivacy-ai-spec-kitty-runtime-next/SKILL.md").read_text()
agent = create_deep_agent(model=model, system_prompt=f"You are a helpful agent.\n\n{skill}")
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

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

Other ways to add it

Deep Agents docs

Its own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" agent-framework
decimalai skills add priivacy-ai-spec-kitty-runtime-next

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("priivacy-ai-spec-kitty-runtime-next")
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/priivacy-ai-spec-kitty-runtime-next/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/priivacy-ai-spec-kitty-runtime-next/SKILL.md").read_text()
agent = Agent(client=client, instructions=f"You are a helpful agent.\n\n{skill}")
asyncio.run(agent.run("Hello!"))

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

Other ways to add it

Microsoft Agent Framework docs

Strands' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" strands-agents
decimalai skills add priivacy-ai-spec-kitty-runtime-next

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("priivacy-ai-spec-kitty-runtime-next")
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/priivacy-ai-spec-kitty-runtime-next/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/priivacy-ai-spec-kitty-runtime-next/SKILL.md").read_text()
agent = Agent(model=model, system_prompt=f"You are a helpful agent.\n\n{skill}")
agent("Hello!")

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

Other ways to add it

Strands docs

Adds every file the skill has, pinned so you can update it. Cursor, Copilot, Cline and Warp read this folder by themselves.

pip install "decimalai>=0.15"
decimalai skills add priivacy-ai-spec-kitty-runtime-next

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/priivacy-ai-spec-kitty-runtime-next/SKILL.md https://app.decimal.ai/s/priivacy-ai-spec-kitty-runtime-next/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/priivacy-ai-spec-kitty-runtime-next/SKILL.md

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

Other ways to add it

Cursor and other editors docs

Fetch the file and give its text to your model as instructions. No account or package needed.

Get the file

curl -fsSL https://app.decimal.ai/s/priivacy-ai-spec-kitty-runtime-next/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/priivacy-ai-spec-kitty-runtime-next.json

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

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v4, tested 9/9/2026
Source: priivacy-ai/spec-kitty ↗
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

spec-kitty-runtime-next

This skill teaches agents how to advance a Spec Kitty mission through the canonical runtime control loop, including doctrine-aware context loading at each step boundary.

When to Use This Skill

Use this skill when the user wants to:

Advance a mission to its next step
Understand what the runtime will do next
Unblock a stalled mission
Interpret runtime outcomes (step, blocked, decision_required, terminal)

How the Runtime-Next System Works

The spec-kitty next command is the single entry point for agent-driven mission execution. Each call returns a deterministic decision about what action the agent should take next.

Decision Algorithm

The runtime evaluates state in this order:

Mission state machine — Current phase and available transitions (from mission-runtime.yaml DAG)
WP iteration check — For implement and review steps, the CLI bridge manages WP-level iteration WITHOUT advancing the runtime. The runtime only advances when ALL WPs reach terminal/handoff lanes.
Guard conditions — Required artifacts, prerequisites, dependency graph
Priority ordering — Reviews before implementations, higher-priority WPs first, dependency-free WPs before dependent ones

WP Iteration Logic (Critical)

The CLI bridge (not the runtime) manages WP-level iteration:

If current step is implement or review
AND there are WPs in planned or in_progress lanes
THEN return a WP-level decision without advancing the runtime step
The runtime step only advances when ALL WPs are in terminal/handoff lanes (done, approved, or for_review)

This means multiple calls to spec-kitty next during implementation will return different WP IDs but the same step_id (e.g., "implement") until all WPs are done.

Mission Runtime YAML Schema

Missions define steps as a DAG (directed acyclic graph) with dependencies:

mission:
  key: software-dev
  name: Software Dev Kitty
  version: "2.1.0"

steps:
  - id: discovery
    title: Discovery & Research
    depends_on: []
    prompt_template: research.md

  - id: specify
    depends_on: [discovery]
    prompt_template: specify.md

  - id: plan
    depends_on: [specify]
    prompt_template: plan.md

  - id: tasks
    depends_on: [plan]

  - id: implement
    depends_on: [tasks]
    prompt_template: implement.md

  - id: review
    depends_on: [implement]
    prompt_template: review.md

  - id: accept
    depends_on: [review]
    prompt_template: accept.md

Decision Kinds

Every call to spec-kitty next returns exactly one decision kind:

Kind	Meaning	Agent Action
`step`	Normal action available	Read `prompt_file` and execute
`query`	Read-only current-state preview	Inspect state; do not execute a prompt or mark a result
`decision_required`	Runtime needs input	Answer with `--answer` and `--decision-id`
`blocked`	Guards failing, cannot proceed	Read `reason` + `guard_failures`, resolve blockers
`terminal`	Mission complete	Run `/spec-kitty.accept`; if it passes, merge, then: mission review → author or verify retrospective (`retrospect create`) → surface findings (`summary` aggregates; `synthesize` reviews proposals)

Decision Output Fields

{
  "kind": "step",
  "agent": "claude",
  "mission_slug": "042-test-mission",
  "mission": "software-dev",
  "mission_state": "implementing",
  "action": "implement",
  "wp_id": "WP02",
  "workspace_path": ".worktrees/042-test-mission-lane-b",
  "prompt_file": "/tmp/spec-kitty-next-claude-042-test-mission-implement-WP02.md",
  "reason": null,
  "guard_failures": [],
  "progress": {
    "total_wps": 5,
    "done_wps": 1,
    "approved_wps": 0,
    "in_progress_wps": 1,
    "planned_wps": 3,
    "for_review_wps": 0
  },
  "run_id": "abc123",
  "step_id": "implement",
  "decision_id": null,
  "question": null,
  "options": null
}

6 Guard Primitives

Guards block step transitions by returning failure descriptions:

Guard	Syntax	Checks
`artifact_exists`	`artifact_exists("spec.md")`	File exists relative to mission dir
`gate_passed`	`gate_passed("review_gate")`	Gate event in mission-events.jsonl
`all_wp_status`	`all_wp_status("approved_or_done")`	All WPs in a specific lane or named accepted-ready set
`any_wp_status`	`any_wp_status("for_review")`	At least one WP in lane
`input_provided`	`input_provided("architecture")`	Input exists in runtime model
`event_count`	`event_count("review", 1)`	Minimum event count threshold

Guards never raise exceptions — they return false on missing context.

Prompt File Generation

The runtime generates a temp file at: /tmp/spec-kitty-next-{agent}-{mission_slug}-{action}[-{wp_id}].md

Template actions (specify, plan, tasks): Mission context header + governance context + action-specific template content.

WP actions (implement, review): Full isolation-aware prompt containing:

WP header with workspace path
Governance context (paradigms, directives, tools)
WP Isolation Rules — DO only modify this WP's status, DO NOT change other WPs or react to their status changes
Working directory and review commands
WP file content (from tasks/WP##.md)
Completion instructions

Decision prompts: Question text, options, and the --answer command to run.

Run Persistence

Runtime state is persisted between calls:

.kittify/runtime/
├── feature-runs.json       # Index: {"mission-slug": {"run_id": "...", "run_dir": "..."}}
└── runs/
    └── <run_id>/
        └── state.json      # Runtime snapshot (current step, inputs, etc.)

Mission Detection

When --mission is omitted, the runtime detects the mission via (in order):

SPECIFY_MISSION environment variable
Git branch name (mission and lane branches both encode the mission slug)
Current directory path (walks up looking for ###-mission-name)
Single mission auto-detect (only if exactly one mission exists)
Error with guidance if ambiguous

NOTE: Always use --mission <slug> in multi-mission repositories.

Doctrine-Aware Step Execution

The runtime-next loop should load doctrine context iteratively — not all at once. Each step boundary is a context loading opportunity.

Agent Profile at Init

At the start of a session, resolve the active agent profile. This scopes your role, boundaries, and initialization context.

Load the profile using the Python API — do NOT read YAML files directly:

from charter.activation.doctrine_service_builder import build_activation_aware_doctrine_service

service = build_activation_aware_doctrine_service(project_root)

# resolve_profile()'s specializes_from lineage traversal is a repository
# operation, not available on the filtered `agent_profiles` dict — reach it
# through the pinned lineage/mutation accessor:
repo = service.agent_profile_repository
profile = repo.resolve_profile("<profile-id>")  # e.g. "implementer"

# Internalize identity — acknowledge this at session start
print(profile.initialization_declaration)

# Respect scope boundaries
profile.specialization.primary_focus       # What you actively do
profile.specialization.avoidance_boundary  # What you must NOT do
profile.collaboration.handoff_to           # Roles to defer to when out of scope

# Load only the directives this profile references (same `service`, gated dict)
for ref in profile.directive_references:
    directive = service.directives.get(f"DIRECTIVE_{ref.code}")

Discovery (if you don't know your profile-id):

spec-kitty agent profile list
spec-kitty agent profile show <profile-id>

Action-Scoped Context at Each Step

At each step boundary (when spec-kitty next returns a step decision), load governance context scoped to the current action — not the full doctrine:

# Load only what's relevant to this action (compact after first load)
spec-kitty charter context --action implement --json

The context system uses two depth levels:

Depth	When	Content
`bootstrap` (depth-2)	First load for this action	Full policy summary + reference list
`compact` (depth-1)	Subsequent loads	Resolved paradigms, directives, tools only

First-load state is tracked per action in .kittify/charter/context-state.json. This means implement and review each get their own first-load bootstrap independently.

Pull Specific Doctrine On Demand

When you need governance guidance mid-step (e.g., how to structure tests, which review criteria apply), pull the specific tactic or directive by ID rather than re-loading the full context:

from charter.activation.doctrine_service_builder import build_activation_aware_doctrine_service

service = build_activation_aware_doctrine_service(project_root)

# Pull a specific tactic when it becomes relevant
tactic = service.tactics.get("tdd-red-green-refactor")

# Pull a specific directive
directive = service.directives.get("TEST_FIRST")

The action index (actions/<action>/index.yaml) tells you which doctrine artifacts are relevant to the current step. Load the index to discover what to pull:

from charter.offering.missions.action_index import load_action_index

index = load_action_index(missions_root, "software-dev", "implement")
# index.directives → ["TEST_FIRST", ...]
# index.tactics → ["tdd-red-green-refactor", ...]
# index.procedures → [...]

Anti-Pattern: Upfront Context Dump

Do NOT load all doctrine into context at session start. This wastes tokens and dilutes relevance. Instead:

At init: Load agent profile + initialization declaration.
At each step boundary: Call charter context --action <action>.
When stuck or need guidance: Pull specific tactic/directive by ID.
When reviewing: Pull review-scoped doctrine, not implement-scoped.

Step 1: Load Runtime Context

Before invoking the runtime, gather the current state.

Commands:

# Check WP status for a mission
spec-kitty agent tasks status --mission <mission-slug>

# Check current context for an action
spec-kitty agent context resolve --action implement --mission <mission-slug> --json

What to look for:

Active mission slug and mission type
Current WP lane status (planned, claimed, in_progress, for_review, in_review, approved, done, blocked, canceled)
Whether there are WPs ready for implementation or review
Any blocked WPs that need attention first

Step 2: Run the Next Command

# Run the next step
spec-kitty next --agent <agent> --mission <mission-slug> --json

# After completing a step successfully
spec-kitty next --agent <agent> --mission <mission-slug> --result success --json

# After a step failed
spec-kitty next --agent <agent> --mission <mission-slug> --result failed --json

# After a step was blocked
spec-kitty next --agent <agent> --mission <mission-slug> --result blocked --json

Note: --mission is the sole selector. The legacy --feature alias has been removed (#1060); passing --feature now exits with No such option.

The --result flag tells the runtime the outcome of the previous step. If omitted, spec-kitty next returns current state without advancing (query mode). It does not report success for the previous step.

Step 3: Interpret the Result

See references/runtime-result-taxonomy.md for the complete taxonomy.

Kind	Next Action
`step`	Read and execute `prompt_file` (always non-empty and resolvable on disk)
`decision_required`	Answer with `--answer` and `--decision-id`
`blocked`	Read `reason` + `guard_failures`, resolve blockers
`terminal`	Run `/spec-kitty.accept` for final validation, then merge if acceptance passes

Always check guard_failures — this field may appear on any decision kind, not just blocked.

The kind="step" prompt-file contract is a hard runtime invariant (C1/C2). A kind="step" envelope MUST carry a prompt_file (or its consumer-side prompt_path alias) that is non-null, non-empty, and resolves on disk. If the runtime cannot produce an actionable step (no composed action, guard failure, blocked dependency, prompt build error, etc.), it returns kind="blocked" with a non-empty reason (and optional machine-readable code such as no_prompt_template). There is no third state: an agent loop should never observe a kind="step" decision with prompt_file == null.

Always check progress for completion. If progress.done_wps equals progress.total_wps but kind is not terminal, the mission is actually complete (known issue #335). The runtime may not detect completion when no prior run state exists. Treat this as terminal and run /spec-kitty.accept; if acceptance passes, run /spec-kitty.merge, then run mission review and the retrospective workflow.

Step 4: Handle decision_required

When the runtime needs input:

# The decision includes question, options, and decision_id
# Answer using:
spec-kitty next --agent <agent> --mission <mission-slug> \
  --result success --answer "<choice>" --decision-id "<decision_id>" --json

If the agent cannot determine the answer, escalate to the user with the question and options.

Step 5: Handle Blocked States

See references/blocked-state-recovery.md for detailed recovery patterns.

Quick diagnostic:

# Check WP status and dependency graph
spec-kitty agent tasks status --mission <mission-slug>

# Check specific WP dependencies
spec-kitty agent tasks list-dependents WP## --mission <mission-slug>

Common blockers:

Blocker	Recovery
Missing artifacts (spec.md, plan.md)	Run the planning workflow first
Upstream WP not done	Implement or review the upstream WP
Review feedback not addressed	Re-implement, address feedback, move to for_review
Stale agent (WP in doing, no activity)	Move WP to planned with `--force`
Circular dependencies	Break cycle in WP frontmatter, re-run finalize-tasks

Step 6: The Agent Loop

The complete agent loop pattern:

# 1. Start the loop
DECISION=$(spec-kitty next --agent claude --mission 042-mission --json)
KIND=$(echo "$DECISION" | jq -r '.kind')

# 2. Loop until terminal or unresolvable block
while [ "$KIND" = "step" ] || [ "$KIND" = "decision_required" ]; do

  # Workaround #335: check progress for completion even if kind != terminal
  DONE=$(echo "$DECISION" | jq -r '.progress.done_wps // 0')
  TOTAL=$(echo "$DECISION" | jq -r '.progress.total_wps // 0')
  if [ "$TOTAL" -gt 0 ] && [ "$DONE" -eq "$TOTAL" ]; then
    break  # Mission is actually complete
  fi

  if [ "$KIND" = "step" ]; then
    PROMPT=$(echo "$DECISION" | jq -r '.prompt_file')

    # Contract (C1/C2, post-#336 fix): kind=step always carries a
    # non-empty prompt_file resolvable on disk. If a prompt cannot be
    # resolved, the runtime emits kind=blocked with a populated reason.

    # Read and execute the prompt...
    RESULT="success"  # or "failed" or "blocked"
  elif [ "$KIND" = "decision_required" ]; then
    # Answer the question...
    RESULT="success"
  fi

  DECISION=$(spec-kitty next --agent claude --mission 042-mission --result "$RESULT" --json)
  KIND=$(echo "$DECISION" | jq -r '.kind')
done

# 3. Handle terminal state — canonical post-merge sequence
if [ "$KIND" = "terminal" ] || [ "$DONE" -eq "$TOTAL" ]; then
  # Run /spec-kitty.accept.
  # If acceptance passes, run /spec-kitty.merge.
  # After merge, follow the canonical post-merge sequence:
  #   a. Mission review: /spec-kitty-mission-review
  #   b. Author or verify retrospective:
  #      spec-kitty retrospect create --mission 042-mission  # if record absent
  #      OR verify: cat .kittify/missions/<mission_id>/retrospective.yaml
  #   c. Surface findings:
  #      spec-kitty retrospect summary                                   # read-only aggregation
  #      spec-kitty agent retrospect synthesize --mission 042-mission  # dry-run by default; --apply to mutate
  # Note: summary aggregates; synthesize applies proposals — neither authors records.
fi

The loop continues until:

terminal — mission complete, exit loop
query — read-only preview, no state mutation
blocked — cannot proceed without external resolution
decision_required — only if the agent cannot answer (escalate to user)

Important: Runtime Precedence Rules

Always use spec-kitty next rather than manually sequencing phases
Always pass --mission in multi-mission repositories
Respect mission state machine transitions — do not skip steps
Read the prompt_file — it contains the full context the agent needs
Check guard_failures on every decision, not just blocked ones
Reviews before implementations — the runtime prioritizes unblocking downstream work
WP isolation — only modify the WP you were assigned, ignore other WPs

Known Issues

#335 — Completed missions return step instead of terminal. When spec-kitty next is called on a mission with all WPs done but no prior runtime run state, it creates a new run starting at discovery instead of recognizing the mission is complete. Workaround: Check progress.done_wps == progress.total_wps as a secondary completion signal.

#336 — fixed. prompt_file is always non-empty and resolvable on disk on kind: step decisions. When no prompt is available, the runtime now emits a structured kind: blocked decision with a non-empty reason (and optional machine-readable code such as no_prompt_template). Agent loops no longer need to defensively null-check prompt_file; a kind: step decision with a null prompt is a runtime bug.

Standalone Invocations (Outside Missions)

Not all governed work happens inside an active mission. When a user asks for help with a task that has no active spec-kitty next loop — a code review, a quick implementation, an ad-hoc analysis — you should still invoke Spec Kitty's governance layer with standalone dispatch.

Spec Kitty never spawns a parallel LLM call. You are the host; Spec Kitty routes, assembles governance context, and records the trail.

When to use standalone dispatch

If the user says anything like "use spec kitty to ...", "hey spec kitty ...", or "spec kitty ", run standalone dispatch unless they are clearly asking for a full mission.

The governance injection loop

Get context:

spec-kitty dispatch "implement the login handler" --json
spec-kitty dispatch "review WP05" --profile reviewer --json

Response includes invocation_id, governance_context_text, and governance_context_available.

Inject governance: Read governance_context_text and treat it as binding governance context for your task. Follow any directives and constraints it contains. If governance_context_available is false, note this to the user but proceed with the task.
Execute: Do the work. Generate the code, analysis, or plan.
Close the Op (mandatory — dispatch leaves it open):
```
spec-kitty profile-invocation complete \
  --invocation-id <invocation_id> \
  --outcome <done|failed|abandoned>
```
Use the real outcome: done for completed work, failed for work that did not succeed, abandoned for dropped work. Never leave an Op open deliberately — spec-kitty doctor ops reports and sweeps orphans.

Trail produced

Every standalone invocation writes a Tier 1 JSONL file to:

kitty-ops/<invocation_id>.jsonl

Viewable at any time with spec-kitty invocations list --json. No SaaS connection required.

For full CLI surface documentation, see src/charter/offering/skills/spec-kitty/SKILL.md.

References

references/runtime-result-taxonomy.md -- Decision kinds, output fields, and precedence rules
references/blocked-state-recovery.md -- 6 blocked state patterns with diagnosis and recovery

About this skill

Automatic

AI Engineer pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

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

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

priivacy-ai / spec-kitty

src/doctrine/skills/spec-kitty-runtime-next/SKILL.md

View on GitHub ↗

License MITImported 9/9/2026Version v4Bundled 2 files

Illustrative Want to see what priivacy-ai/spec-kitty-runtime-next would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

priivacy-ai/spk-run-nextDrive the canonical spec-kitty next control loop and route query, step, blocked, decision_required, and terminal results.Close match+55 pts pass-rate lift

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

spec-kitty-runtime-next

When to Use This Skill

How the Runtime-Next System Works

Decision Algorithm

WP Iteration Logic (Critical)

Mission Runtime YAML Schema

Decision Kinds

Decision Output Fields

6 Guard Primitives

Prompt File Generation

Run Persistence

Mission Detection

Doctrine-Aware Step Execution

Agent Profile at Init

Action-Scoped Context at Each Step

Pull Specific Doctrine On Demand

Anti-Pattern: Upfront Context Dump

Step 1: Load Runtime Context

Step 2: Run the Next Command

Step 3: Interpret the Result

Step 4: Handle decision_required

Step 5: Handle Blocked States

Step 6: The Agent Loop

Important: Runtime Precedence Rules

Known Issues

Standalone Invocations (Outside Missions)

When to use standalone dispatch

The governance injection loop

Trail produced

References

SkillSafety

Source

Other skills for the same job

Related skills

More in the registry