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.
curl -O https://raw.githubusercontent.com/BlocUnited-LLC/mozaiks/main/.agents/skills/control-plane-refinement-change/SKILL.mdgit clone --depth 1 https://github.com/BlocUnited-LLC/mozaiksWrote 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.
[](https://agentmods.dev/skills/blocunited-llc/mozaiks/control-plane-refinement-change)<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.
<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>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00033 | $0.01086 |
| Opus 5.5 | $0.00013 | $0.00434 |
| Sonnet 5.5 | $0.00007 | $0.00217 |
| Haiku 4.5 | $0.00003 | $0.00109 |
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 26d 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.
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, then branch from fresh origin/main.
Use this skill when a change touches control-plane or refinement behavior.
Typical triggers:
app/config/ai.jsoncontrol-plane settings in the canonical contract or the first-party repo pathfactory_app/app/config/ai.jsonfactory_app/control_plane/config/control_plane.yaml- checkpoint or re-entry behavior
- refinement classification and
patch|design|feature|corerouting routing.artifacts[]or artifact-family ownershipaffected_declarative_familieson referencedworkflow_sequenceentries- Studio refinement triggers or build sequence re-entry after a change request
factory_app/app/modules/factory_control_plane/
Inspect first:
app/config/ai.jsonin the canonical contract and the first-party repo pathfactory_app/app/config/ai.jsonfactory_app/app/config/ai.jsonfactory_app/control_plane/config/control_plane.yamlfactory_app/workflows/extended_orchestration/extension_registry.jsondocs/architecture/workflows/refinement-control-plane.mddocs/architecture/orchestration-and-decomposition.mddocs/architecture/workflows/control-plane-harness-architecture.mdfactory_app/app/modules/factory_control_plane/module.yamlfactory_app/app/modules/factory_control_plane/backend/handler.py- the narrowest matching tests before editing:
tests/test_control_plane_loader.pytests/test_refinement_router.pytests/test_pack_config_paths.pytests/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 packfactory_app/app/modules/factory_control_plane/is a Studio identity stub only- the control plane classifies change scope and routes to declared
workflow_sequencere-entry points and checkpoints - the referenced
workflow_sequenceowns downstream workflow order andaffected_declarative_families
Keep these distinct:
workflow_sequence/workflow_sequences[]= cross-workflow rebuild or revision routetransitions[]= route-time user choice or deterministic context seedentrypoints[]= external route entry into a sequence or transitiontransition_graph.yaml= workflow-local AG2 agent routingrouting.artifacts[]= artifact-kind ownership and change-class routing incontrol_plane.yamlcheckpoints[]= control-plane decision points above workflows and above workflow-local handoffs
Routing rules:
control_plane.yamlroutes declareworkflow_sequenceonlyworkflow_sequenceids must exist inextended_orchestration/extension_registry.json- sequence-owned
affected_declarative_familiesstay on the sequence, not incontrol_plane.yaml - when present,
patch,design,feature, andcoreclasses must stay aligned across config, docs, and tests
Companion routing:
- Add
factory-build-workflow-changeas a companion skill when the change also altersfactory_app/workflows/extended_orchestration/extension_registry.json,workflow_sequencecomposition,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_sequenceids - change artifact families or
affected_declarative_familieswithout 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_familiesderivation: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
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.
- 26d ago Changed 10965b5652ac
- 2mo ago First seen · 107 lines · 33 tokens per session scan A b0d3e66e7851
control-plane-refinement-change is a skill published in the GitHub repository BlocUnited-LLC/mozaiks (24 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 1,086 once invoked, about $0.0001 per session on Opus 5.5. 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.
control-plane-refinement-change compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| control-plane-refinement-changeBlocUnited-LLC/mozaiks | Skill | 24 | yesterday | MIT | A | 33 | Claude Code |
| building-pydantic-ai-agentspydantic/pydantic-ai | Skill | 21k | yesterday | MIT | A | 92 | Claude Code, Codex |
| pydantic-ai-harnesspydantic/pydantic-ai | Skill | 21k | yesterday | MIT | A | 197 | Claude Code, Codex |
| migrating-langchain-to-pydantic-aipydantic/pydantic-ai | Skill | 21k | yesterday | MIT | A | 100 | Codex |
| migrating-vercel-ai-sdk-and-eve-to-pydantic-aipydantic/pydantic-ai | Skill | 21k | yesterday | MIT | A | 107 | Codex |
| migrating-claude-agent-sdk-to-pydantic-aipydantic/pydantic-ai | Skill | 21k | yesterday | MIT | A | 90 | Codex |
| migrating-mastra-to-pydantic-aipydantic/pydantic-ai | Skill | 21k | yesterday | MIT | A | 73 | Codex |