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/factory-build-workflow-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/factory-build-workflow-change)<a href="https://agentmods.dev/skills/blocunited-llc/mozaiks/factory-build-workflow-change"><img src="https://agentmods.dev/badge/skills/blocunited-llc/mozaiks/factory-build-workflow-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/factory-build-workflow-change"><img src="https://agentmods.dev/badge/skills/blocunited-llc/mozaiks/factory-build-workflow-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 | $0.00045 | $0.02453 |
| Opus 5.5 | $0.00018 | $0.00981 |
| Sonnet 5.5 | $0.00009 | $0.00491 |
| Haiku 4.5 | $0.00005 | $0.00245 |
Grade A, and why
factory-build-workflow-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 — 180 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 the factory build workflow system.
Typical triggers:
factory_app/workflows/extended_orchestration/extension_registry.jsonworkflow_sequences[],transitions[], orentrypoints[]- build journey sequencing or branch routing
factory_app/workflows/AppGenerator/**factory_app/workflows/AgentGenerator/**factory_app/workflows/ExistingAppDiscovery/**- build lifecycle hooks in
factory_app/workflows/_shared/platform/build_lifecycle.py - artifact routing, generated artifact ownership, or workflow integration contracts
- shared workflow tools, hooks, reusable workflow UI, or cross-workflow build glue
- build control-plane or refinement integration that references
workflow_sequence
Inspect first:
ARCHITECTURE.mdAGENTS.mdCLAUDE.md.claude/rules/factory-build-workflows.md.claude/rules/build-refinement-truth.md.claude/rules/testing.mdfactory_app/workflows/extended_orchestration/extension_registry.jsondocs/architecture/workflows/workflow-routing-transitions.mddocs/architecture/orchestration-and-decomposition.mddocs/architecture/workflows/refinement-control-plane.md- the full affected workflow directory, especially:
orchestrator.yamltransition_graph.yamlagents.yamlstructured_outputs.yamltools.yamlcontext_variables.yamlmiddleware.yaml
- the relevant shared workflow surfaces when build lifecycle or shared tools change:
factory_app/workflows/_shared/platform/build_lifecycle.pyfactory_app/workflows/_shared/ui/**for reusable workflow React components- any affected
factory_app/workflows/_shared/**helper
- generated artifact contracts when AppGenerator or AgentGenerator is affected:
factory_app/build_context/AppGenerator/file_contracts.yaml- relevant workflow-converter or materialization contracts
Build input structure:
- Build contexts are named directories with one
context.yamlregistry. context.yamldeclares explicitassets[]; folder names are organization, not policy.- Factory prompt catalogs are
assets[]withkind: catalogunderfactory_app/build_context/{context_name}/. - Workflow runtime YAML (
agents.yaml,context_variables.yaml,structured_outputs.yaml,middleware.yaml) stays underfactory_app/workflows/{WorkflowName}/. - Hooks resolve factory build-context paths through
factory_app.workflows._shared.hook_utils.workflow_context_path(). - Do not recreate
factory_app/workflows/_shared/catalogs/. - Do not add one-off catalog family folders such as
patternbook/for a single workflow unless there is a real organization need and the file is still declared inassets[]. - Do not put large static prompt catalogs in
context_variables.yaml; hooks inject them deterministically. - Reusable workflow React components belong under
factory_app/workflows/_shared/ui/when multiple factory workflows consume them. - Shared workflow UI is not auto-registered; each consuming workflow must import and re-export/register it from its own
factory_app/workflows/{WorkflowName}/ui/index.js. - Do not import UI from a sibling workflow folder. Move shared UI into
_shared/ui/, or keep a workflow-specific wrapper in the owning workflow'sui/folder. - Reusable OSS build packs are named build contexts, not placeholder manifests. Add a pack only when
context.yamlcontains apack:descriptor plus useful capabilities/facades and declares realassets[]. - Pack instructions are
assets[]withkind: contract. - Pack template directories are
assets[]withkind: templates; they mirror generated app structure:templates/modules/...,templates/services/...,templates/ui/...,templates/config/.... YAML in template assets is generated app declarative output, not a build-context contracts lane. - Workspace build contexts use the same named-context shape under workspace-root
build_context/{context_name}/. - the narrowest matching tests before editing:
- sequence, transition, and entrypoint routing:
tests/test_pack_schema_models.py,tests/test_pack_config_paths.py,tests/test_existing_app_discovery_contracts.py - build lifecycle hooks:
tests/test_build_lifecycle_hooks.py - ExistingAppDiscovery:
tests/test_existing_app_discovery_contracts.py,tests/test_existing_app_discovery_native_migration.py - AppGenerator:
tests/test_appgenerator_canonical_generation.py,tests/test_appgenerator_module_contracts.py,tests/test_appgenerator_persistence_alignment.py - AgentGenerator:
tests/test_agentgenerator_workflow_converter.py,tests/test_agentgenerator_tool_planning.py,tests/test_agentgenerator_ui_quality_gate.py - artifact routing and control-plane linkage:
tests/test_control_plane_loader.py,tests/test_control_plane_tools.py,tests/test_hook_file_contract_context.py,tests/test_hook_domain_catalog_context.py,tests/test_build_lifecycle_hooks.py
- sequence, transition, and entrypoint routing:
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 24e88652973d
- 2mo ago First seen · 180 lines · 45 tokens per session scan A 9b603751f9ec
factory-build-workflow-change is a skill published in the GitHub repository BlocUnited-LLC/mozaiks (24 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 2,453 once invoked, about $0.0002 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.
factory-build-workflow-change compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| factory-build-workflow-changeBlocUnited-LLC/mozaiks | Skill | 24 | yesterday | MIT | A | 45 | 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 |