catlog22/maestro-flow
Intent-driven workflow orchestration for multi-agent AI development — adaptive lifecycle engine, self-reinforcing knowledge graph, and visual dashboard for Claude Code, Gemini, Codex & more
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code $ claude mcp add claude_dms3-chrome-devtools -- npx chrome-devtools-mcp@latest $ claude mcp add --transport http exa https://mcp.exa.ai/mcp $ npx degit catlog22/maestro-flow/.claude ./rig-maestro-flow # inspect, then merge into .claude/
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.
$ claude mcp add claude_dms3-chrome-devtools -- npx chrome-devtools-mcp@latest $ claude mcp add --transport http exa https://mcp.exa.ai/mcp
$ npx degit catlog22/maestro-flow/.claude/skills/maestro-help .claude/skills/maestro-help $ npx degit catlog22/maestro-flow/.claude/skills/skill-generator .claude/skills/skill-generator $ npx degit catlog22/maestro-flow/.claude/skills/skill-iter-tune .claude/skills/skill-iter-tune $ npx degit catlog22/maestro-flow/.claude/skills/skill-simplify .claude/skills/skill-simplify $ npx degit catlog22/maestro-flow/.claude/skills/skill-tuning .claude/skills/skill-tuning $ npx degit catlog22/maestro-flow/.claude/skills/team-arch-opt .claude/skills/team-arch-opt $ npx degit catlog22/maestro-flow/.claude/skills/team-coordinate .claude/skills/team-coordinate $ npx degit catlog22/maestro-flow/.claude/skills/team-issue .claude/skills/team-issue $ npx degit catlog22/maestro-flow/.claude/skills/team-lifecycle-v4 .claude/skills/team-lifecycle-v4 $ npx degit catlog22/maestro-flow/.claude/skills/team-perf-opt .claude/skills/team-perf-opt $ npx degit catlog22/maestro-flow/.claude/skills/team-review .claude/skills/team-review $ npx degit catlog22/maestro-flow/.claude/skills/team-swarm .claude/skills/team-swarm $ npx degit catlog22/maestro-flow/.claude/skills/team-testing .claude/skills/team-testing $ npx degit catlog22/maestro-flow/.claude/skills/workflow-skill-designer .claude/skills/workflow-skill-designer $ npx degit catlog22/maestro-flow/.codex/skills/maestro-companion .claude/skills/maestro-companion $ npx degit catlog22/maestro-flow/.codex/skills/maestro-fork .claude/skills/maestro-fork $ npx degit catlog22/maestro-flow/.codex/skills/maestro-guard .claude/skills/maestro-guard $ npx degit catlog22/maestro-flow/.codex/skills/maestro-impeccable .claude/skills/maestro-impeccable $ npx degit catlog22/maestro-flow/.codex/skills/maestro-init .claude/skills/maestro-init $ npx degit catlog22/maestro-flow/.codex/skills/maestro-issue .claude/skills/maestro-issue $ npx degit catlog22/maestro-flow/.codex/skills/maestro-knowhow .claude/skills/maestro-knowhow $ npx degit catlog22/maestro-flow/.codex/skills/maestro-knowledge .claude/skills/maestro-knowledge $ npx degit catlog22/maestro-flow/.codex/skills/maestro-learn .claude/skills/maestro-learn $ npx degit catlog22/maestro-flow/.codex/skills/maestro-merge .claude/skills/maestro-merge $ npx degit catlog22/maestro-flow/.codex/skills/maestro-next .claude/skills/maestro-next $ npx degit catlog22/maestro-flow/.codex/skills/maestro-odyssey .claude/skills/maestro-odyssey $ npx degit catlog22/maestro-flow/.codex/skills/maestro-overlay .claude/skills/maestro-overlay $ npx degit catlog22/maestro-flow/.codex/skills/maestro-ralph .claude/skills/maestro-ralph $ npx degit catlog22/maestro-flow/.codex/skills/maestro-session-manage .claude/skills/maestro-session-manage $ npx degit catlog22/maestro-flow/.codex/skills/maestro-spec .claude/skills/maestro-spec $ npx degit catlog22/maestro-flow/.codex/skills/maestro-update .claude/skills/maestro-update $ npx degit catlog22/maestro-flow/.codex/skills/maestro .claude/skills/maestro $ npx degit catlog22/maestro-flow/optional/skills/scholar-anti-ai-writing .claude/skills/scholar-anti-ai-writing $ npx degit catlog22/maestro-flow/optional/skills/scholar-citation-verify .claude/skills/scholar-citation-verify $ npx degit catlog22/maestro-flow/optional/skills/scholar-experiment .claude/skills/scholar-experiment $ npx degit catlog22/maestro-flow/optional/skills/scholar-ideation .claude/skills/scholar-ideation $ npx degit catlog22/maestro-flow/optional/skills/scholar-latex-organizer .claude/skills/scholar-latex-organizer $ npx degit catlog22/maestro-flow/optional/skills/scholar-publish .claude/skills/scholar-publish $ npx degit catlog22/maestro-flow/optional/skills/scholar-rebuttal-pro .claude/skills/scholar-rebuttal-pro $ npx degit catlog22/maestro-flow/optional/skills/scholar-review .claude/skills/scholar-review
$ curl -fsSL --create-dirs -o .claude/agents/cli-explore-agent.md https://raw.githubusercontent.com/catlog22/maestro-flow/master/.claude/agents/cli-explore-agent.md $ curl -fsSL --create-dirs -o .claude/agents/cross-role-reviewer.md https://raw.githubusercontent.com/catlog22/maestro-flow/master/.claude/agents/cross-role-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/impeccable-agent.md https://raw.githubusercontent.com/catlog22/maestro-flow/master/.claude/agents/impeccable-agent.md $ curl -fsSL --create-dirs -o .claude/agents/maestro-impeccable-asset-producer.md https://raw.githubusercontent.com/catlog22/maestro-flow/master/.claude/agents/maestro-impeccable-asset-producer.md $ curl -fsSL --create-dirs -o .claude/agents/maestro-impeccable-documenter.md https://raw.githubusercontent.com/catlog22/maestro-flow/master/.claude/agents/maestro-impeccable-documenter.md $ curl -fsSL --create-dirs -o .claude/agents/maestro-impeccable-finish-reviewer.md https://raw.githubusercontent.com/catlog22/maestro-flow/master/.claude/agents/maestro-impeccable-finish-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/maestro-impeccable-manual-edit-applier.md https://raw.githubusercontent.com/catlog22/maestro-flow/master/.claude/agents/maestro-impeccable-manual-edit-applier.md $ curl -fsSL --create-dirs -o .claude/agents/ralph-executor.md https://raw.githubusercontent.com/catlog22/maestro-flow/master/.claude/agents/ralph-executor.md $ curl -fsSL --create-dirs -o .claude/agents/role-design-author.md https://raw.githubusercontent.com/catlog22/maestro-flow/master/.claude/agents/role-design-author.md $ curl -fsSL --create-dirs -o .claude/agents/run-executor.md https://raw.githubusercontent.com/catlog22/maestro-flow/master/.claude/agents/run-executor.md $ curl -fsSL --create-dirs -o .claude/agents/team-supervisor.md https://raw.githubusercontent.com/catlog22/maestro-flow/master/.claude/agents/team-supervisor.md $ curl -fsSL --create-dirs -o .claude/agents/team-worker.md https://raw.githubusercontent.com/catlog22/maestro-flow/master/.claude/agents/team-worker.md $ curl -fsSL --create-dirs -o .claude/agents/ui-design-agent.md https://raw.githubusercontent.com/catlog22/maestro-flow/master/.claude/agents/ui-design-agent.md $ curl -fsSL --create-dirs -o .claude/agents/workflow-analyzer.md https://raw.githubusercontent.com/catlog22/maestro-flow/master/.claude/agents/workflow-analyzer.md $ curl -fsSL --create-dirs -o .claude/agents/workflow-codebase-mapper.md https://raw.githubusercontent.com/catlog22/maestro-flow/master/.claude/agents/workflow-codebase-mapper.md $ curl -fsSL --create-dirs -o .claude/agents/workflow-collab-planner.md https://raw.githubusercontent.com/catlog22/maestro-flow/master/.claude/agents/workflow-collab-planner.md $ curl -fsSL --create-dirs -o .claude/agents/workflow-debugger.md https://raw.githubusercontent.com/catlog22/maestro-flow/master/.claude/agents/workflow-debugger.md $ curl -fsSL --create-dirs -o .claude/agents/workflow-executor.md https://raw.githubusercontent.com/catlog22/maestro-flow/master/.claude/agents/workflow-executor.md $ curl -fsSL --create-dirs -o .claude/agents/workflow-external-researcher.md https://raw.githubusercontent.com/catlog22/maestro-flow/master/.claude/agents/workflow-external-researcher.md $ curl -fsSL --create-dirs -o .claude/agents/workflow-integration-checker.md https://raw.githubusercontent.com/catlog22/maestro-flow/master/.claude/agents/workflow-integration-checker.md $ curl -fsSL --create-dirs -o .claude/agents/workflow-nyquist-auditor.md https://raw.githubusercontent.com/catlog22/maestro-flow/master/.claude/agents/workflow-nyquist-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/workflow-phase-researcher.md https://raw.githubusercontent.com/catlog22/maestro-flow/master/.claude/agents/workflow-phase-researcher.md $ curl -fsSL --create-dirs -o .claude/agents/workflow-plan-checker.md https://raw.githubusercontent.com/catlog22/maestro-flow/master/.claude/agents/workflow-plan-checker.md $ curl -fsSL --create-dirs -o .claude/agents/workflow-planner.md https://raw.githubusercontent.com/catlog22/maestro-flow/master/.claude/agents/workflow-planner.md $ curl -fsSL --create-dirs -o .claude/agents/workflow-project-researcher.md https://raw.githubusercontent.com/catlog22/maestro-flow/master/.claude/agents/workflow-project-researcher.md $ curl -fsSL --create-dirs -o .claude/agents/workflow-research-synthesizer.md https://raw.githubusercontent.com/catlog22/maestro-flow/master/.claude/agents/workflow-research-synthesizer.md $ curl -fsSL --create-dirs -o .claude/agents/workflow-reviewer.md https://raw.githubusercontent.com/catlog22/maestro-flow/master/.claude/agents/workflow-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/workflow-roadmapper.md https://raw.githubusercontent.com/catlog22/maestro-flow/master/.claude/agents/workflow-roadmapper.md $ curl -fsSL --create-dirs -o .claude/agents/workflow-verifier.md https://raw.githubusercontent.com/catlog22/maestro-flow/master/.claude/agents/workflow-verifier.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} MCP servers (3)
| server | source | est. tokens |
|---|---|---|
| maestro env: MAESTRO_ENABLED_TOOLS | local / custom | 2.5k |
| Chrome DevTools MCP · "claude_dms3-chrome-devtools" | npm | 9.0k |
| Exa | remote · remote | 1.5k |
Skills (42)
maestro-helpskill-generatorskill-iter-tuneskill-simplifyskill-tuningteam-arch-optteam-coordinateteam-issueteam-lifecycle-v4team-perf-optteam-reviewteam-swarmteam-testingworkflow-skill-designermaestro-companionmaestro-forkmaestro-guardmaestro-impeccablemaestro-initmaestro-issuemaestro-knowhowmaestro-knowledgemaestro-learnmaestro-mergemaestro-nextmaestro-odysseymaestro-overlaymaestro-ralphmaestro-session-managemaestro-specmaestro-updatemaestroscholar-anti-ai-writingscholar-citation-verifyscholar-experimentscholar-ideationscholar-latex-organizerscholar-publishscholar-rebuttal-proscholar-reviewthesis-docxscholar-writing
Subagents (29)
| cli-explore-agent | Read-only code exploration via Bash + CLI semantic dual-source analysis, with schema-validated structured output. |
| cross-role-reviewer | Compares Decision Digests across role analysis files in a brainstorm session to surface conflicts, gaps, and synergies. Read-only — returns structured text for the orchestrator to apply. |
| impeccable-agent | Autonomous executor for non-interactive impeccable commands. Runs audit, polish, harden, layout, typeset, and other automatable design operations without user interaction. |
| maestro-impeccable-asset-producer model: inherit | Produces clean reusable raster assets from approved Impeccable mock references without redesigning the direction. |
| maestro-impeccable-documenter model: inherit | Records DESIGN.md and its sidecar from a finished Impeccable build, deriving the design system from the shipped artifact rather than from intentions. |
| maestro-impeccable-finish-reviewer model: inherit | Reviews a finished Impeccable build against its direction contract, the approved comp, and the chosen world's quality bar, returning an ordered list of material fixes. |
| maestro-impeccable-manual-edit-applier model: inherit | Applies leased Impeccable live manual copy-edit batches to source and returns canonical Apply results. |
| ralph-executor | Deprecated compatibility alias for run-executor |
| role-design-author | Generates multi-file role analysis for a brainstorm session — analysis.md index + per-feature files + optional findings under {output_dir}/{role}/. |
| run-executor | Single-step executor — run next birth packet / run brief(backtrack) + inline skill execution, unnamed nesting for multi-agent orchestration |
| team-supervisor | Resident pipeline supervisor agent. Message-driven lifecycle for cross-checkpoint quality observation and health monitoring. |
| team-worker | Unified worker agent for team pipelines. Executes role-specific logic loaded from a role_spec file within a built-in task lifecycle (discover, execute, report). |
| ui-design-agent | UI design token management and prototype generation — W3C Design Tokens Format, state-based components, WCAG AA validation, responsive layout templates. |
| workflow-analyzer | Evaluates technical topics, proposals, or decisions across multiple dimensions with evidence-based scoring and recommendations. |
| workflow-codebase-mapper | Analyzes existing codebase from a specific focus area, spawned in parallel |
| workflow-collab-planner | Collaborative planner working within pre-allocated task ID ranges |
| workflow-debugger | Hypothesis-driven debugging with structured evidence logging |
| workflow-executor | Implements single tasks atomically with verification and commit discipline |
| workflow-external-researcher | External research agent using Exa MCP for API details, design patterns, and technology evaluation |
| workflow-integration-checker | Cross-phase integration validation for milestone audits |
| workflow-nyquist-auditor | Test coverage audit with gap detection and test stub generation |
| workflow-phase-researcher | Researches implementation approach for a specific roadmap phase |
| workflow-plan-checker | Validates plan quality with up to 3 revision rounds |
| workflow-planner | Creates execution plans with task decomposition, waves, and dependencies |
| workflow-project-researcher | Domain research for project initialization, spawned with different focus angles |
| workflow-research-synthesizer | Merges multiple researcher outputs into a unified research summary |
| workflow-reviewer | Multi-dimensional code review agent — analyzes changed files for a single review dimension |
| workflow-roadmapper | Creates project roadmap with phased milestones from research and requirements |
| workflow-verifier | Goal-backward verification across three layers (existence, substance, connection) |
Slash commands (18)
/maestro-companion/maestro-fork/maestro-guard/maestro-impeccable/maestro-init/maestro-issue/maestro-knowhow/maestro-knowledge/maestro-learn/maestro-merge/maestro-next/maestro-odyssey/maestro-overlay/maestro-ralph/maestro-session-manage/maestro-spec/maestro-update/maestro
Permissions
deny (0)
—
ask (0)
—
allow (9)
Read
Glob
Grep
Bash(npm *)
Bash(node *)
Bash(tsc *)
Bash(git *)
Bash(ls *)
Bash(maestro *)
Similar rigs
primeapple/dotfiles
My personal dotfiles
Pragmatist 10.9k tok ·
MSmaili/dotfiles
Personal dotfiles configuration.
Pragmatist 15.6k tok ·
geril07/dotfiles
—
Skill Collector 24.7k tok ·
Prorise-cool/Claude-Code-Multi-Agent
Claude-Code-Multi-Agent驱动的新一代AI编程助手生态系统，基于Claude Code构建的智能代理协调工作空间，实现从需求到交付的全流程自动化开发
MCP Hoarder 66.5k tok ·