scaffolding

claude-scaffolding

Portable Claude Code configuration: 13 agents, 35 skills, 19 commands, 15 hooks, spec-driven workflows. Installs as a Claude Code plugin.

Overview

claude-scaffolding is a portable, markdown-only Claude Code configuration. It provides multi-agent orchestration, a library of reusable skills, guardrail hooks, and spec-driven workflows — everything ships as plain markdown and runs entirely on the Claude Code runtime, with no backend, database, or long-running process required.

Why use this

• Spec-driven workflows — OpenSpec-style specs keep work grounded and reproducible.
• 13 specialized agents — analyst, architect, developer, reviewer, debugger, prompt-engineer, mcp-builder, and more, each with a focused role.
• Parallel multi-agent orchestration — fan out work across agents and coordinate results.
• Opinionated guardrail hooks — 15 safety and lifecycle hooks block destructive commands, hard-deny disallowed subagents, and enforce conventions.
• Extensible & self-improving — /create-skill scaffolds your own scaffolding-compatible skills, and /learn closes the loop by distilling reusable insights from finished conversations.
• Zero backend required — pure markdown and Claude Code runtime; no database, server, or process to run.

What's new in 2.8.0

Everything below is opt-in or default-safe — existing installs behave exactly as before until you set a flag or invoke a new agent. See the CHANGELOG for the full list.

• Two new agents (roster 11 → 13): prompt-engineer (system prompts, guardrail rules, prompt evals, LLM-judge rubrics, injection defense) and mcp-builder (design/build/test MCP servers, tool schemas, transport, auth launchers).
• Six new hooks: soft auto-init advice (auto-init-check), opt-in auto-format (post-edit-format), opt-in desktop/terminal notifications (notify), opt-in completion nudge (completion-nudge), a hard block on the general-purpose/explore subagents (block-subagent), and a warn-only

  500-line file check (file-size-warn).

• Per-phase model tiers: analyst, architect, and reviewer declare model: opus + effort: high; developer stays inherit. The reviewer on a higher tier breaks same-model self-review and records a cross_model flag in its report. The plugin emits only literal sonnet/opus/haiku; backend mapping lives on the aiproxy/litellm side — see docs/model-tiers.md.
• /init-rules command: scaffolds opt-in, path-scoped nested CLAUDE.md rule files so per-area conventions lazy-load only where relevant, while routing stays always-loaded.
• Lighter routing prompt: critical rules emphasized with <important>, and forced delegation softened so trivial Q&A may be answered directly while real engineering work is still delegated.
• Skill performance: context: fork on four heavy skills (ui-ux-pro-max, mui-styling, logging-standards, monitoring-observability) and !`command` dynamic injection in the git/worktree/context-engineering skills.
• Experimental agent-teams mode behind CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 — see docs/agent-teams.md.

Opt-in flags

All flags are off by default; the plugin's behavior is unchanged unless you set them.

Flag	Default	Effect
SCAFFOLDING_AUTOFORMAT	off	=1 enables post-edit-format.sh — auto-formats the single edited file (ruff/black, prettier, dotnet format); never blocks.
SCAFFOLDING_NOTIFY	off	=1 enables notify.sh — desktop/terminal notification on turn-finish or input-needed.
SCAFFOLDING_COMPLETION_NUDGE	off	=1 advisory nudge to finish the delegation chain; =block enforces it (loop-guarded).
CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS	off	=1 enables the experimental agent-teams mode (see docs/agent-teams.md).

Install