-
Notifications
You must be signed in to change notification settings - Fork 3
Home
CodingScaffold helps teams move from “AI autocomplete” to reviewable agentic coding workflows. The README is the quick front door; this wiki explains the project in more depth and gives teams a shared rollout playbook.
CodingScaffold creates project-local guidance and lightweight configuration for:
- local-first model routing
- provider and credential discovery
- prompt-based model selection
- OpenCode and OpenClaude adapters
- reusable team skills
- agent orchestration profiles
- shared Markdown, Obsidian, or MemPalace-ready knowledge bases
- experienced-team onboarding manifests
- policy packs for provider, sharing, permission, and MCP defaults
- context budgeting and optional compression sidecars
- optional RouteLLM and Open Multi-Agent workflows
It does not collect secrets, does not require one model vendor, and does not force a hosted service into the workflow.
CodingScaffold itself can start without an LLM. Setup, hardware probe, credential templates,
adapter generation, and tools select-model command are local Python workflows. The first actual model
call happens later, inside the coding tool, when a developer runs an agent command such as
/first-session in OpenCode.
- Getting Started: install, run setup, refresh safely, and complete the first agentic coding session.
- Core Concepts: understand the main ideas before introducing it to a team.
- Model Selection and Providers: local-first routing, Azure/OpenAI/Anthropic abstraction, and auto mode.
- Skills and Agents: how teams turn good workflows into reusable assets.
- Knowledge Base: Markdown, Obsidian, MemPalace, and shared GitHub/GitLab memory.
- Context Hygiene: avoid oversized or stale context and add optional compression.
- Team Onboarding: connect new developers to shared knowledge, skills, agents, and policy.
- Policy Packs: local OpenCode policy defaults for company/unit/team rollout.
- Team Rollout: a practical adoption plan for a team workshop or internal pilot.
CodingScaffold is intentionally boring where that helps:
- Git is the sharing mechanism.
- Markdown is the source of truth.
- Local credentials stay local.
- Generated files are readable and editable by hand.
- Advanced orchestration is optional and comes after the team validates the workflow.