mozaiks: Skill for Claude Code

.agents/skills/control-plane-refinement-change/SKILL.md

control-plane-refinement-change is a skill for Claude Code, Codex from BlocUnited-LLC/mozaiks. It costs 33 tokens per session (1,085 once invoked), scanned A, original, MIT.

A guide for reviewing or changing how a software control plane routes refinement work, configuration, checkpoints, and generated files.

In plain words
What is it for?
Updating control-plane configuration, refinement routing, checkpoint handling, artifact paths, contributor guidance, and workflow sequences.
Why use it?
It helps keep related settings, workflow re-entry, and artifact ownership consistent when refinement behavior changes.

Skill for Claude CodeCodex

Written for Claude Code: argument-hint in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is BlocUnited-LLC/mozaiks's own configuration. It tells Claude Code and Codex how to work on mozaiks itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mozaiks configures →

Reuse

Borrowing it

Nothing to install: this file belongs to BlocUnited-LLC/mozaiks. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/BlocUnited-LLC/mozaiks/main/.agents/skills/control-plane-refinement-change/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/BlocUnited-LLC/mozaiks

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for control-plane-refinement-change

README.md
[![agentmods](https://agentmods.dev/badge/skills/blocunited-llc/mozaiks/control-plane-refinement-change/github.svg)](https://agentmods.dev/skills/blocunited-llc/mozaiks/control-plane-refinement-change)
Your own site
<a href="https://agentmods.dev/skills/blocunited-llc/mozaiks/control-plane-refinement-change"><img src="https://agentmods.dev/badge/skills/blocunited-llc/mozaiks/control-plane-refinement-change/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for control-plane-refinement-change

Your own site · 80×15
<a href="https://agentmods.dev/skills/blocunited-llc/mozaiks/control-plane-refinement-change"><img src="https://agentmods.dev/badge/skills/blocunited-llc/mozaiks/control-plane-refinement-change.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,085 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00033 $0.01085
Opus 5 $0.00016 $0.00543
Sonnet 5 $0.00007 $0.00217
Haiku 4.5 $0.00003 $0.00109

Measured 9d ago against content hash b0d3e66e7851, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

control-plane-refinement-change scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/control-plane-refinement-change/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Before starting: git fetch origin && gh pr list --state open && git log origin/main --oneline -3 — if another agent has an open PR touching the same files you need, wait for it to merge or branch off it instead of main.

Use this skill when a change touches control-plane or refinement behavior.

Typical triggers:

  • app/config/ai.json control-plane settings in the canonical contract or the first-party repo path factory_app/app/config/ai.json
  • factory_app/control_plane/config/control_plane.yaml
  • checkpoint or re-entry behavior
  • refinement classification and patch|design|feature|core routing
  • routing.artifacts[] or artifact-family ownership
  • affected_declarative_families on referenced workflow_sequence entries
  • Studio refinement triggers or build sequence re-entry after a change request
  • factory_app/app/modules/factory_control_plane/

Inspect first:

  • app/config/ai.json in the canonical contract and the first-party repo path factory_app/app/config/ai.json
  • factory_app/app/config/ai.json
  • factory_app/control_plane/config/control_plane.yaml
  • factory_app/workflows/extended_orchestration/extension_registry.json
  • docs/architecture/workflows/refinement-control-plane.md
  • docs/architecture/orchestration-and-decomposition.md
  • docs/architecture/workflows/control-plane-harness-architecture.md
  • factory_app/app/modules/factory_control_plane/module.yaml
  • factory_app/app/modules/factory_control_plane/backend/handler.py
  • the narrowest matching tests before editing:
    • tests/test_control_plane_loader.py
    • tests/test_refinement_router.py
    • tests/test_pack_config_paths.py
    • tests/test_build_lifecycle_hooks.py

Current truth:

  • refinement is checkpoint/control-plane re-entry, not a dedicated RefinementWorkflow
  • the first-party harness runtime lives in mozaiksai/control_plane/
  • factory_app/control_plane/ is the declarative first-party pack
  • factory_app/app/modules/factory_control_plane/ is a Studio identity stub only
  • the control plane classifies change scope and routes to declared workflow_sequence re-entry points and checkpoints
  • the referenced workflow_sequence owns downstream workflow order and affected_declarative_families

Keep these distinct:

  • workflow_sequence / workflow_sequences[] = cross-workflow rebuild or revision route
  • transitions[] = route-time user choice or deterministic context seed
  • entrypoints[] = external route entry into a sequence or transition
  • transition_graph.yaml = workflow-local AG2 agent routing
  • routing.artifacts[] = artifact-kind ownership and change-class routing in control_plane.yaml
  • checkpoints[] = control-plane decision points above workflows and above workflow-local handoffs

Routing rules:

  • control_plane.yaml routes declare workflow_sequence only
  • workflow_sequence ids must exist in extended_orchestration/extension_registry.json
  • sequence-owned affected_declarative_families stay on the sequence, not in control_plane.yaml
  • when present, patch, design, feature, and core classes must stay aligned across config, docs, and tests

Companion routing:

  • Add factory-build-workflow-change as a companion skill when the change also alters factory_app/workflows/extended_orchestration/extension_registry.json, workflow_sequence composition, transitions[], entrypoints[], or other cross-workflow routing surfaces.

Do not:

  • invent a dedicated RefinementWorkflow
  • bypass build-sequence re-entry with ad hoc workflow routing
  • confuse transitions with refinement routing or checkpoints with workflow-local handoffs
  • route to undeclared workflow_sequence ids
  • change artifact families or affected_declarative_families without updating tests
  • put hosted product logic into OSS control-plane guidance or pack policy

Focused testing guidance:

  • control-plane pack loading and route validation:
    • python -m pytest tests/test_control_plane_loader.py -q
  • refinement routing and affected_declarative_families derivation:
    • python -m pytest tests/test_refinement_router.py -q
  • workflow pack path and sequence resolution:
    • python -m pytest tests/test_pack_config_paths.py -q
  • build-sequence lifecycle and journey-instance hook payloads:
    • python -m pytest tests/test_build_lifecycle_hooks.py -q

Read the full file on GitHub · 107 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 107 lines · 33 tokens per session scan A b0d3e66e7851

Subscribe to this mod's changes

control-plane-refinement-change is a skill published in the GitHub repository BlocUnited-LLC/mozaiks (25 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 1,085 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

building-pydantic-ai-agents

Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), structured output, streaming, testing, and multi-agent patterns. Use when the user mentions Pydantic AI, imports pydanticai, or asks to build an AI agent, add tools/capabilities, defer capability loading, stream output, define agents…

pydantic/pydantic-ai · 85 tokens

migrating-langchain-to-pydantic-ai

Migrate Python LangChain or LangGraph applications to Pydantic AI. Use for LangChain agents, chains, LCEL, or direct LangGraph graphs, persistence, interrupts, and streaming. Do not use for migrations centered on createdeepagent or Deep Agents harness features.

pydantic/pydantic-ai · 69 tokens

agentfield-use

Whenever you have a discrete task to perform — one the user delegated, or one that arose inside your own work — check FIRST whether an installed AgentField agent covers it, and offload to it by default when one does. Coverage, not task size, is the test: even a small job goes to a covering agent. The check is cheap …

Agent-Field/agentfield · 259 tokens

agentfield

Design and ship a multi-agent system on AgentField. Use when the user asks to build, scaffold, design, or run an agent, reasoner network, multi-agent backend, or 'an agent that does X' — whenever the work would otherwise be a single LLM call or a flat LangChain/CrewAI/AutoGen chain. The skill produces composite…

Agent-Field/agentfield · 127 tokens

agentfield-personal

Build and install a personal AI agent on this machine's AgentField: real source in /agentfield-agents, packaged with agentfield-package.yaml, installed with af install, started with af run, registered on the local control plane, and visible in AgentField Desktop with a keys form and an auto-start toggle. Use when the…

Agent-Field/agentfield · 134 tokens

hephaestus-network

Use when the user types $hephaestus-network, /hep-network, or /agentlas-network, mentions @Hephaestus, or asks Agentlas to staff a durable goal from registered Local, owner Cloud, and public Hub agents or teams. The active host LLM staffs each turn; the exact roster remains goal-bound until explicit completion.

agentlas-ai/Agentlas-OS · 75 tokens