komluk/scaffolding
Spec-driven multi-agent orchestration plugin for Claude Code — 13 agents, 35 skills, per-phase model tiers, opt-in lifecycle hooks, and optional cross-device semantic memory.
field: AI / ML workflow: Planning & specsFrontend & designPR / code reviewResearchTesting & TDD runs claude in CI
stack: JavaScript
ARCHETYPE
YOLO Cowboy
Permissions? Never heard of 'em. Ships at the speed of `--dangerously-skip-permissions`.
GUARDRAILS
2/5
Blocks destructive commands · Pre-tool screening hook · details
Quality 11/100 Guardrails v2
Copy this rig
# review before running: this installs third-party code $ npx degit komluk/scaffolding/agents ./rig-scaffolding/agents $ npx degit komluk/scaffolding/commands ./rig-scaffolding/commands $ npx degit komluk/scaffolding/skills ./rig-scaffolding/skills $ npx degit komluk/scaffolding/hooks ./rig-scaffolding/hooks
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit komluk/scaffolding/skills/agent-comms .claude/skills/agent-comms $ npx degit komluk/scaffolding/skills/agent-memory .claude/skills/agent-memory $ npx degit komluk/scaffolding/skills/api-design .claude/skills/api-design $ npx degit komluk/scaffolding/skills/context-engineering .claude/skills/context-engineering $ npx degit komluk/scaffolding/skills/database-optimization .claude/skills/database-optimization $ npx degit komluk/scaffolding/skills/distill .claude/skills/distill $ npx degit komluk/scaffolding/skills/docker-templates .claude/skills/docker-templates $ npx degit komluk/scaffolding/skills/error-handling .claude/skills/error-handling $ npx degit komluk/scaffolding/skills/frontend-design .claude/skills/frontend-design $ npx degit komluk/scaffolding/skills/git-operations .claude/skills/git-operations $ npx degit komluk/scaffolding/skills/github-actions-template .claude/skills/github-actions-template $ npx degit komluk/scaffolding/skills/logging-standards .claude/skills/logging-standards $ npx degit komluk/scaffolding/skills/mcp-tools .claude/skills/mcp-tools $ npx degit komluk/scaffolding/skills/monitoring-observability .claude/skills/monitoring-observability $ npx degit komluk/scaffolding/skills/mui-styling .claude/skills/mui-styling $ npx degit komluk/scaffolding/skills/necessity-first .claude/skills/necessity-first $ npx degit komluk/scaffolding/skills/pattern-recognition .claude/skills/pattern-recognition $ npx degit komluk/scaffolding/skills/planning-methodology .claude/skills/planning-methodology $ npx degit komluk/scaffolding/skills/python-patterns .claude/skills/python-patterns $ npx degit komluk/scaffolding/skills/quality-validation .claude/skills/quality-validation $ npx degit komluk/scaffolding/skills/react-patterns .claude/skills/react-patterns $ npx degit komluk/scaffolding/skills/research-methodology .claude/skills/research-methodology $ npx degit komluk/scaffolding/skills/reverse-engineer-anything .claude/skills/reverse-engineer-anything $ npx degit komluk/scaffolding/skills/security-review-checklists .claude/skills/security-review-checklists $ npx degit komluk/scaffolding/skills/semantic-memory-mcp .claude/skills/semantic-memory-mcp $ npx degit komluk/scaffolding/skills/skill-authoring .claude/skills/skill-authoring $ npx degit komluk/scaffolding/skills/sofa-search .claude/skills/sofa-search $ npx degit komluk/scaffolding/skills/spec-design .claude/skills/spec-design $ npx degit komluk/scaffolding/skills/spec-develop .claude/skills/spec-develop $ npx degit komluk/scaffolding/skills/spec-research .claude/skills/spec-research $ npx degit komluk/scaffolding/skills/spec-review .claude/skills/spec-review $ npx degit komluk/scaffolding/skills/spec-workflow .claude/skills/spec-workflow $ npx degit komluk/scaffolding/skills/state-management .claude/skills/state-management $ npx degit komluk/scaffolding/skills/systematic-debugging .claude/skills/systematic-debugging $ npx degit komluk/scaffolding/skills/testing-strategy .claude/skills/testing-strategy $ npx degit komluk/scaffolding/skills/ui-ux-pro-max .claude/skills/ui-ux-pro-max $ npx degit komluk/scaffolding/skills/verification-before-completion .claude/skills/verification-before-completion $ npx degit komluk/scaffolding/skills/watch-patterns .claude/skills/watch-patterns $ npx degit komluk/scaffolding/skills/worktree-management .claude/skills/worktree-management
$ curl -fsSL --create-dirs -o .claude/agents/analyst.md https://raw.githubusercontent.com/komluk/scaffolding/main/agents/analyst.md $ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/komluk/scaffolding/main/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/coordinator.md https://raw.githubusercontent.com/komluk/scaffolding/main/agents/coordinator.md $ curl -fsSL --create-dirs -o .claude/agents/debugger.md https://raw.githubusercontent.com/komluk/scaffolding/main/agents/debugger.md $ curl -fsSL --create-dirs -o .claude/agents/developer.md https://raw.githubusercontent.com/komluk/scaffolding/main/agents/developer.md $ curl -fsSL --create-dirs -o .claude/agents/devops.md https://raw.githubusercontent.com/komluk/scaffolding/main/agents/devops.md $ curl -fsSL --create-dirs -o .claude/agents/gitops.md https://raw.githubusercontent.com/komluk/scaffolding/main/agents/gitops.md $ curl -fsSL --create-dirs -o .claude/agents/mcp-builder.md https://raw.githubusercontent.com/komluk/scaffolding/main/agents/mcp-builder.md $ curl -fsSL --create-dirs -o .claude/agents/optimizer.md https://raw.githubusercontent.com/komluk/scaffolding/main/agents/optimizer.md $ curl -fsSL --create-dirs -o .claude/agents/prompt-engineer.md https://raw.githubusercontent.com/komluk/scaffolding/main/agents/prompt-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/researcher.md https://raw.githubusercontent.com/komluk/scaffolding/main/agents/researcher.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/komluk/scaffolding/main/agents/reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/tech-writer.md https://raw.githubusercontent.com/komluk/scaffolding/main/agents/tech-writer.md
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"permissions": {
"deny": [
"Read(**/venv/**)",
"Read(**/.venv/**)",
"Read(**/node_modules/**)",
"Read(**/__pycache__/**)",
"Read(**/.mypy_cache/**)",
"Read(**/.pytest_cache/**)",
"Read(**/.ruff_cache/**)",
"Read(**/.git/objects/**)",
"Read(**/.scaffolding/conversations/**/tasks/*/output.jsonl)",
"Read(**/projects/*/conversations/**/tasks/*/output.jsonl)",
"Glob(**/venv/**)",
"Glob(**/.venv/**)",
"Glob(**/node_modules/**)",
"Grep(**/.scaffolding/conversations/**/tasks/*/output.jsonl)",
"Grep(**/projects/*/conversations/**/tasks/*/output.jsonl)"
]
},
"hooks": {
"PreToolUse": [
{
"matcher": "Task",
"hooks": [
{
"type": "command",
"command": "${CLAUDE_PLUGIN_ROOT}/hooks/block-subagent.sh"
}
]
},
{
"matcher": "Bash(git commit:*)",
"hooks": [
{
"type": "command",
"command": "${CLAUDE_PLUGIN_ROOT}/hooks/pre-commit-validation.sh"
}
]
},
{
"matcher": "Bash(git push*)",
"hooks": [
{
"type": "command",
"command": "${CLAUDE_PLUGIN_ROOT}/hooks/block-force-push.sh"
}
]
},
{
"matcher": "Edit|Write",
"hooks": [
{
"type": "command",
"command": "${CLAUDE_PLUGIN_ROOT}/hooks/file-staleness-check.sh"
},
{
"type": "command",
"command": "${CLAUDE_PLUGIN_ROOT}/hooks/block-env-write.sh"
}
]
},
{
"matcher": "Bash(rm *)",
"hooks": [
{
"type": "command",
"command": "${CLAUDE_PLUGIN_ROOT}/hooks/block-destructive-rm.sh"
}
]
}
]
}
} Skills (39)
agent-commsagent-memoryapi-designcontext-engineeringdatabase-optimizationdistilldocker-templateserror-handlingfrontend-designgit-operationsgithub-actions-templatelogging-standardsmcp-toolsmonitoring-observabilitymui-stylingnecessity-firstpattern-recognitionplanning-methodologypython-patternsquality-validationreact-patternsresearch-methodologyreverse-engineer-anythingsecurity-review-checklistssemantic-memory-mcpskill-authoringsofa-searchspec-designspec-developspec-researchspec-reviewspec-workflowstate-managementsystematic-debuggingtesting-strategyui-ux-pro-maxverification-before-completionwatch-patternsworktree-management
Subagents (13)
| analyst model: claude-opus-5-5 | Requirements analyst. MUST BE USED for ambiguous requests, requirements gathering, scope assessment, feasibility checks, and proposal writing. NOT for small, clearly-scoped changes (those go directly |
| architect model: claude-opus-5-5 | Technical architect. MUST BE USED for system design, API design, implementation planning, multi-file refactoring, and agent orchestration. Receives proposal.md from analyst and produces design.md + ta |
| coordinator model: claude-sonnet-5-5 | Analyzes tasks and decomposes them into a sequence of agent steps for execution. |
| debugger model: claude-opus-5-5 | Bug investigation specialist. MUST BE USED for bug reports, unexpected behavior, error diagnosis. PROACTIVELY performs systematic root cause analysis using progressive debugging techniques. |
| developer model: claude-sonnet-5-5 | Expert software engineer. Use proactively to implement features, fix bugs, write tests, style UI, and make code changes. MUST BE USED for all development tasks. Direct target for small, clearly-scoped |
| devops model: claude-sonnet-5-5 | Infrastructure specialist. MUST BE USED for CI/CD, Docker, deployment, infrastructure. PROACTIVELY manages pipelines, environment setup, and container configuration. |
| gitops model: claude-haiku-5-5 | Git operations specialist. MUST BE USED for branch management, conflict resolution, git history analysis, worktree recovery, commit, merge, push. Owns ALL git operations — other agents do NOT commit. |
| mcp-builder model: claude-sonnet-5-5 | MCP server specialist. MUST BE USED to design, build, and test MCP servers — stdio vs http transports, tool schema design, env-based secrets, and the Vault-launcher pattern. PROACTIVELY keeps secrets |
| optimizer model: claude-sonnet-5-5 | Performance specialist. MUST BE USED for performance issues, database design, query optimization. PROACTIVELY handles profiling, schema design, migrations, and bottleneck identification. |
| prompt-engineer model: claude-sonnet-5-5 | Prompt & guardrail engineering specialist. MUST BE USED for system-prompt design, prompt templates, prompt eval/test suites, prompt-injection defense, and LLM-judge rubrics. PROACTIVELY treats prompts |
| researcher model: claude-sonnet-5-5 | Documentation researcher. MUST BE USED for new API integration, library questions, best practices. PROACTIVELY gathers version-specific documentation and produces ResearchPacks with citations. |
| reviewer model: claude-opus-5-5 | Senior code reviewer, security specialist, and quality assurance expert. Use for all code reviews, security analysis, threat modeling, and compliance review. MUST BE USED for all reviews. |
| tech-writer model: claude-haiku-5-5 | Documentation owner. MUST BE USED for README, CHANGELOG, docs/ updates. PROACTIVELY manages all markdown files as sole authority for documentation. |
Hooks (29)
| event | matcher | runs |
|---|---|---|
| PreCompact | auto | echo '[Claude Code] Auto-compacting - context window full' |
| PreCompact | manual | echo '[Claude Code] Manual compact triggered' |
| PostToolUse | Edit|Write | ${CLAUDE_PLUGIN_ROOT}/hooks/post-edit-review.sh |
| PostToolUse | Edit|Write | ${CLAUDE_PLUGIN_ROOT}/hooks/post-edit-format.sh |
| PostToolUse | Edit|Write | ${CLAUDE_PLUGIN_ROOT}/hooks/file-staleness-update.sh |
| PostToolUse | Write | ${CLAUDE_PLUGIN_ROOT}/hooks/file-size-warn.sh |
| Stop | * | ${CLAUDE_PLUGIN_ROOT}/hooks/notify.sh |
| Stop | * | ${CLAUDE_PLUGIN_ROOT}/hooks/completion-nudge.sh |
| Stop | * | ${CLAUDE_PLUGIN_ROOT}/hooks/action-log.sh |
| Stop | * | ${CLAUDE_PLUGIN_ROOT}/hooks/memory-ingest.sh |
| SubagentStop | * | ${CLAUDE_PLUGIN_ROOT}/hooks/memory-ingest-mark.sh |
| Notification | * | ${CLAUDE_PLUGIN_ROOT}/hooks/notify.sh |
| PreToolUse | Task | ${CLAUDE_PLUGIN_ROOT}/hooks/block-subagent.sh |
| PreToolUse | Bash(git commit:*) | ${CLAUDE_PLUGIN_ROOT}/hooks/pre-commit-validation.sh |
| PreToolUse | Bash(git push*) | ${CLAUDE_PLUGIN_ROOT}/hooks/block-force-push.sh |
| PreToolUse | Edit|Write | ${CLAUDE_PLUGIN_ROOT}/hooks/file-staleness-check.sh |
| PreToolUse | Edit|Write | ${CLAUDE_PLUGIN_ROOT}/hooks/block-env-write.sh |
| PreToolUse | Bash(rm *) | ${CLAUDE_PLUGIN_ROOT}/hooks/block-destructive-rm.sh |
| SessionStart | compact | ${CLAUDE_PLUGIN_ROOT}/hooks/session-start-protocol.sh |
| SessionStart | startup | ${CLAUDE_PLUGIN_ROOT}/hooks/session-start-protocol.sh |
| SessionStart | startup | ${CLAUDE_PLUGIN_ROOT}/hooks/memory-project-id.sh |
| SessionStart | startup | ${CLAUDE_PLUGIN_ROOT}/hooks/auto-init-check.sh |
| SessionStart | startup | ${CLAUDE_PLUGIN_ROOT}/hooks/nfs-sync.sh pull |
| SessionStart | resume | ${CLAUDE_PLUGIN_ROOT}/hooks/session-start-protocol.sh |
| SessionStart | resume | ${CLAUDE_PLUGIN_ROOT}/hooks/memory-project-id.sh |
| SessionStart | resume | ${CLAUDE_PLUGIN_ROOT}/hooks/auto-init-check.sh |
| SessionStart | resume | ${CLAUDE_PLUGIN_ROOT}/hooks/nfs-sync.sh pull |
| UserPromptSubmit | * | ${CLAUDE_PLUGIN_ROOT}/hooks/memory-recall.sh |
| SessionEnd | * | ${CLAUDE_PLUGIN_ROOT}/hooks/action-log.sh |
Slash commands (20)
/context/create-skill/doctor/init-openspec/init-rules/init-scaffolding/learn/memory/sofa/specs/apply/specs/archive/specs/bulk-archive/specs/continue/specs/explore/specs/ff/specs/new/specs/onboard/specs/run/specs/sync/specs/verify
Permissions
deny (15)
Read(**/venv/**)
Read(**/.venv/**)
Read(**/node_modules/**)
Read(**/__pycache__/**)
Read(**/.mypy_cache/**)
Read(**/.pytest_cache/**)
Read(**/.ruff_cache/**)
Read(**/.git/objects/**)
Read(**/.scaffolding/conversations/**/tasks/*/output.jsonl)
Read(**/projects/*/conversations/**/tasks/*/output.jsonl)
Glob(**/venv/**)
Glob(**/.venv/**)
Glob(**/node_modules/**)
Grep(**/.scaffolding/conversations/**/tasks/*/output.jsonl)
Grep(**/projects/*/conversations/**/tasks/*/output.jsonl)
ask (0)
—
allow (26)
Bash
Read
Edit
Write
Glob
Grep
Task
TaskOutput
WebSearch
WebFetch
NotebookEdit
TodoWrite
AskUserQuestion
EnterPlanMode
ExitPlanMode
KillShell
mcp__*
WebFetch(domain:docs.anthropic.com)
WebFetch(domain:github.com)
WebFetch(domain:api.github.com)
WebFetch(domain:raw.githubusercontent.com)
WebFetch(domain:docs.python.org)
WebFetch(domain:learn.microsoft.com)
WebFetch(domain:react.dev)
WebFetch(domain:vitejs.dev)
WebFetch(domain:mui.com)
Similar rigs
mnzralee/claude-multi-agent-architecture
A production-ready, reusable template for building sophisticated multi-agent AI systems with Claude Code. This architecture enables hierarchical agent coordination, specialized task delegation, and comprehensive documentation workflows.
Fort Knox 4.3k tok · · Q59
vannt-dev/aiws-factory
AIWS – AI Software Factory: turns a requirement into tested code through gated phases (analysis → design + test spec → human approval → per-task implementation with unit tests → review → PR). Language-agnostic, Claude Code first.
Fort Knox 1.5k tok · · Q19
joaolozano-lendario/athena-os
A Claude Code Native System for Intelligent Workflow Architecture - Slash Commands for Smarter AI Workflows
Orchestrator 3.7k tok · · Q15
FCabiddu/pocket-it
Agent system for Claude Code: analyst, architect, task-writer, developer, reviewer, security and tester, with hooks and scripts that enforce the gates
Orchestrator 3.2k tok · · Q5