marcusgoll/Spec-Flow
Turn product ideas into production launches with Spec-Driven Development. Repeatable Claude Code workflows with quality gates, token budgets, and auditable artifacts.
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code
$ npx degit marcusgoll/Spec-Flow/.claude ./rig-spec-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.
$ npx degit marcusgoll/Spec-Flow/.claude/skills/analysis-phase .claude/skills/analysis-phase $ npx degit marcusgoll/Spec-Flow/.claude/skills/anti-duplication .claude/skills/anti-duplication $ npx degit marcusgoll/Spec-Flow/.claude/skills/audit-claude-md .claude/skills/audit-claude-md $ npx degit marcusgoll/Spec-Flow/.claude/skills/breaking-change-detector .claude/skills/breaking-change-detector $ npx degit marcusgoll/Spec-Flow/.claude/skills/caching-strategy .claude/skills/caching-strategy $ npx degit marcusgoll/Spec-Flow/.claude/skills/clarification-phase .claude/skills/clarification-phase $ npx degit marcusgoll/Spec-Flow/.claude/skills/create-agent-skills .claude/skills/create-agent-skills $ npx degit marcusgoll/Spec-Flow/.claude/skills/create-hooks .claude/skills/create-hooks $ npx degit marcusgoll/Spec-Flow/.claude/skills/create-meta-prompts .claude/skills/create-meta-prompts $ npx degit marcusgoll/Spec-Flow/.claude/skills/create-slash-commands .claude/skills/create-slash-commands $ npx degit marcusgoll/Spec-Flow/.claude/skills/create-subagents .claude/skills/create-subagents $ npx degit marcusgoll/Spec-Flow/.claude/skills/debug-phase .claude/skills/debug-phase $ npx degit marcusgoll/Spec-Flow/.claude/skills/dependency-conflict-resolver .claude/skills/dependency-conflict-resolver $ npx degit marcusgoll/Spec-Flow/.claude/skills/design-tokens .claude/skills/design-tokens $ npx degit marcusgoll/Spec-Flow/.claude/skills/domain-memory .claude/skills/domain-memory $ npx degit marcusgoll/Spec-Flow/.claude/skills/dry-run .claude/skills/dry-run $ npx degit marcusgoll/Spec-Flow/.claude/skills/epic-meta-prompting .claude/skills/epic-meta-prompting $ npx degit marcusgoll/Spec-Flow/.claude/skills/epic-scoping .claude/skills/epic-scoping $ npx degit marcusgoll/Spec-Flow/.claude/skills/epic-sprints .claude/skills/epic-sprints $ npx degit marcusgoll/Spec-Flow/.claude/skills/epic-walkthrough .claude/skills/epic-walkthrough $ npx degit marcusgoll/Spec-Flow/.claude/skills/error-recovery .claude/skills/error-recovery $ npx degit marcusgoll/Spec-Flow/.claude/skills/finalize-phase .claude/skills/finalize-phase $ npx degit marcusgoll/Spec-Flow/.claude/skills/git-workflow-enforcer .claude/skills/git-workflow-enforcer $ npx degit marcusgoll/Spec-Flow/.claude/skills/hallucination-detector .claude/skills/hallucination-detector $ npx degit marcusgoll/Spec-Flow/.claude/skills/implementation-phase .claude/skills/implementation-phase $ npx degit marcusgoll/Spec-Flow/.claude/skills/mockup-extraction .claude/skills/mockup-extraction $ npx degit marcusgoll/Spec-Flow/.claude/skills/multi-agent-voting .claude/skills/multi-agent-voting $ npx degit marcusgoll/Spec-Flow/.claude/skills/optimization-phase .claude/skills/optimization-phase $ npx degit marcusgoll/Spec-Flow/.claude/skills/parallel-execution-optimizer .claude/skills/parallel-execution-optimizer $ npx degit marcusgoll/Spec-Flow/.claude/skills/planning-phase .claude/skills/planning-phase $ npx degit marcusgoll/Spec-Flow/.claude/skills/production-deployment-phase .claude/skills/production-deployment-phase $ npx degit marcusgoll/Spec-Flow/.claude/skills/project-initialization-phase .claude/skills/project-initialization-phase $ npx degit marcusgoll/Spec-Flow/.claude/skills/regression-test-generator .claude/skills/regression-test-generator $ npx degit marcusgoll/Spec-Flow/.claude/skills/roadmap-integration .claude/skills/roadmap-integration $ npx degit marcusgoll/Spec-Flow/.claude/skills/session-boundary .claude/skills/session-boundary $ npx degit marcusgoll/Spec-Flow/.claude/skills/shadcn-integration .claude/skills/shadcn-integration $ npx degit marcusgoll/Spec-Flow/.claude/skills/specification-phase .claude/skills/specification-phase $ npx degit marcusgoll/Spec-Flow/.claude/skills/staging-deployment-phase .claude/skills/staging-deployment-phase $ npx degit marcusgoll/Spec-Flow/.claude/skills/staging-validation-phase .claude/skills/staging-validation-phase $ npx degit marcusgoll/Spec-Flow/.claude/skills/task-breakdown-phase .claude/skills/task-breakdown-phase
$ curl -fsSL --create-dirs -o .claude/agents/ROUTING.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.claude/agents/ROUTING.md $ curl -fsSL --create-dirs -o .claude/agents/initializer.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.claude/agents/domain/initializer.md $ curl -fsSL --create-dirs -o .claude/agents/worker.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.claude/agents/domain/worker.md $ curl -fsSL --create-dirs -o .claude/agents/api-contracts.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.claude/agents/implementation/api-contracts.md $ curl -fsSL --create-dirs -o .claude/agents/backend.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.claude/agents/implementation/backend.md $ curl -fsSL --create-dirs -o .claude/agents/database.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.claude/agents/implementation/database.md $ curl -fsSL --create-dirs -o .claude/agents/frontend.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.claude/agents/implementation/frontend.md $ curl -fsSL --create-dirs -o .claude/agents/platform.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.claude/agents/implementation/platform.md $ curl -fsSL --create-dirs -o .claude/agents/qa-test.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.claude/agents/implementation/qa-test.md $ curl -fsSL --create-dirs -o .claude/agents/contracts-sdk-reference.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.<redacted>-sdk-reference.md $ curl -fsSL --create-dirs -o .claude/agents/database-architect-reference.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.<redacted>-architect-reference.md $ curl -fsSL --create-dirs -o .claude/agents/platform-reference.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.<redacted>-reference.md $ curl -fsSL --create-dirs -o .claude/agents/test-architect-reference.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.claude/agents/implementation/references/test-architect-reference.md $ curl -fsSL --create-dirs -o .claude/agents/test-architect.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.claude/agents/implementation/test-architect.md $ curl -fsSL --create-dirs -o .claude/agents/skill-auditor.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.claude/agents/infrastructure/skill-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/slash-command-auditor.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.claude/agents/infrastructure/slash-command-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/subagent-auditor.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.claude/agents/infrastructure/subagent-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/clarify-agent.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.claude/agents/phase/clarify-agent.md $ curl -fsSL --create-dirs -o .claude/agents/clarify.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.claude/agents/phase/clarify.md $ curl -fsSL --create-dirs -o .claude/agents/epic.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.claude/agents/phase/epic.md $ curl -fsSL --create-dirs -o .claude/agents/finalize-agent.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.claude/agents/phase/finalize-agent.md $ curl -fsSL --create-dirs -o .claude/agents/finalize.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.claude/agents/phase/finalize.md $ curl -fsSL --create-dirs -o .claude/agents/help-agent.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.claude/agents/phase/help-agent.md $ curl -fsSL --create-dirs -o .claude/agents/optimize-agent.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.claude/agents/phase/optimize-agent.md $ curl -fsSL --create-dirs -o .claude/agents/optimize.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.claude/agents/phase/optimize.md $ curl -fsSL --create-dirs -o .claude/agents/plan-agent.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.claude/agents/phase/plan-agent.md $ curl -fsSL --create-dirs -o .claude/agents/plan.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.claude/agents/phase/plan.md $ curl -fsSL --create-dirs -o .claude/agents/project-architect.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.claude/agents/phase/project-architect.md $ curl -fsSL --create-dirs -o .claude/agents/ship-agent.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.claude/agents/phase/ship-agent.md $ curl -fsSL --create-dirs -o .claude/agents/ship-prod.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.claude/agents/phase/ship-prod.md $ curl -fsSL --create-dirs -o .claude/agents/ship-staging.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.claude/agents/phase/ship-staging.md $ curl -fsSL --create-dirs -o .claude/agents/spec-agent.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.claude/agents/phase/spec-agent.md $ curl -fsSL --create-dirs -o .claude/agents/spec.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.claude/agents/phase/spec.md $ curl -fsSL --create-dirs -o .claude/agents/tasks-agent.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.claude/agents/phase/tasks-agent.md $ curl -fsSL --create-dirs -o .claude/agents/tasks.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.claude/agents/phase/tasks.md $ curl -fsSL --create-dirs -o .claude/agents/validate-agent.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.claude/agents/phase/validate-agent.md $ curl -fsSL --create-dirs -o .claude/agents/validate.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.claude/agents/phase/validate.md $ curl -fsSL --create-dirs -o .claude/agents/init-project-agent.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.claude/agents/project/init-project-agent.md $ curl -fsSL --create-dirs -o .claude/agents/prototype-discover-agent.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.claude/agents/project/prototype-discover-agent.md $ curl -fsSL --create-dirs -o .claude/agents/roadmap-brainstorm-agent.md https://raw.githubusercontent.com/marcusgoll/Spec-Flow/main/.claude/agents/project/roadmap-brainstorm-agent.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,974 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(~/.aws/**)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(.env)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/.env.*)",
"Read(**/*.key)",
"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(npm publish:*)",
"Bash(wget *)",
"Bash(git rebase *)",
"Bash(gh pr merge *)",
"Bash(git commit *)"
]
}
} Skills (46)
analysis-phaseanti-duplicationaudit-claude-mdbreaking-change-detectorcaching-strategyclarification-phasecreate-agent-skillscreate-hookscreate-meta-promptscreate-slash-commandscreate-subagentsdebug-phasedependency-conflict-resolverdesign-tokensdomain-memorydry-runepic-meta-promptingepic-scopingepic-sprintsepic-walkthrougherror-recoveryfinalize-phasegit-workflow-enforcerhallucination-detectorimplementation-phasemockup-extractionmulti-agent-votingoptimization-phaseparallel-execution-optimizerplanning-phaseproduction-deployment-phaseproject-initialization-phaseregression-test-generatorroadmap-integrationsession-boundaryshadcn-integrationspecification-phasestaging-deployment-phasestaging-validation-phasetask-breakdown-phasetask-status-synctheme-consistencyultrathinkworkflow-detectionworktree-contextx-announcement
Subagents (67)
| ROUTING | — |
| initializer model: sonnet | Stage Manager agent that expands prompts into structured domain memory. Does NOT implement - only prepares. |
| worker model: sonnet | Disciplined implementation agent that picks ONE feature, implements, tests, updates domain memory, and exits. |
| contracts-sdk model: sonnet | Manages API contracts and SDK generation. Use when modifying OpenAPI/GraphQL/protobuf specs, generating client SDKs, checking schema drift, coordinating API versioning, or enforcing contract-first wor |
| backend-dev model: sonnet | Implements FastAPI backend features using TDD and contract-first development. Use for backend implementation tasks, API endpoint creation, database models, service layer, background jobs, SQLAlchemy m |
| database-architect model: sonnet | Use when designing schemas, authoring migrations, adding indexes, optimizing queries, or validating data integrity. Specializes in zero-downtime patterns, rollback safety, and production data protecti |
| frontend-dev model: sonnet | Implements Next.js 15 frontend features using TDD, design-first workflow, and accessibility-by-default. Use for UI/UX implementation, component creation, page development, design system integration, H |
| platform model: sonnet | Use when managing contracts, CI/CD pipelines, SDK generation, webhooks, feature flags, deployment quotas, or shared infrastructure. Implements Complicated-Subsystem Team pattern (Team Topologies) - ow |
| qa-test model: sonnet | Test creation and coverage specialist for TDD workflows. Use when implementing test-only tasks, adding test coverage, or when "/quick" routes to testing domain. Handles pytest (Python), Jest/Vitest (N |
| contracts-sdk-reference | — |
| database-architect-reference | — |
| platform-reference | — |
| test-architect-reference | — |
| test-architect model: sonnet | Use this agent when:\n1. Starting implementation of a new feature (during /implement phase)\n2. Practicing Test-Driven Development (TDD) workflow\n3. Converting acceptance criteria from tasks.md into |
| skill-auditor model: sonnet | Expert skill auditor for Claude Code Skills. Use when auditing, reviewing, or evaluating SKILL.md files for best practices compliance. MUST BE USED when user asks to audit a skill. |
| slash-command-auditor model: sonnet | Expert slash command auditor for Claude Code slash commands. Use when auditing, reviewing, or evaluating slash command .md files for best practices compliance. MUST BE USED when user asks to audit a s |
| subagent-auditor model: sonnet | Expert subagent auditor for Claude Code subagents. Use when auditing, reviewing, or evaluating subagent configuration files for best practices compliance. MUST BE USED when user asks to audit a subage |
| clarify-agent | — |
| clarify-phase-agent model: sonnet | Execute clarification phase to resolve specification ambiguities. Use when spec contains [NEEDS CLARIFICATION] markers, vague requirements, or undefined technical details. Calls /clarify command in is |
| epic model: sonnet # Complex reasoning, planning, mu | Epic orchestrator for multi-sprint workflows (>16h, multiple subsystems). Use when features span multiple subsystems, require parallel execution, or involve complex dependency graphs. Auto-invoked by |
| finalize-agent | — |
| finalize-phase-agent model: sonnet | Executes finalization phase after successful deployment. Updates CHANGELOG, README, archives feature specs, syncs roadmap, and closes workflow state. Use after /ship-prod, /deploy-prod, or /build-loca |
| help-agent | — |
| optimize-agent | — |
| optimize-phase-agent model: sonnet | Execute comprehensive quality optimization phase including code review, performance analysis, security scanning, and accessibility audits. Use after implementation phase completes to ensure production |
| plan-agent | — |
| plan-phase-agent model: sonnet # Requires complex reasoning for | Planning phase orchestrator for /plan slash command. Use when feature spec is complete and architecture/implementation plan needs to be created. Extracts reuse opportunities, identifies blockers, retu |
| project-architect model: sonnet # Complex reasoning required for | System design specialist for project-level architecture documentation. Generates 8 comprehensive project docs for greenfield and brownfield projects. Triggered by /init-project command. |
| ship-agent | — |
| ship-prod-phase-agent model: sonnet | Orchestrates production deployment by promoting validated staging builds to production. Spawned by /ship command to trigger production workflow, create GitHub releases, and update roadmap status. |
| ship-staging-phase-agent model: sonnet # Complex orchestration requirin | Orchestrates staging deployment by creating PRs, monitoring CI, auto-merging, and verifying deployment. Spawned by /ship command for staging-prod deployment model. |
| spec-agent | — |
| spec-phase-agent model: sonnet # Complex reasoning required: tra | Executes specification phase via /specify slash command. Creates feature specs, user stories, and acceptance criteria from user requirements. Use when orchestrator initiates Phase 0 (Specification) to |
| tasks-agent | — |
| tasks-phase-agent model: sonnet # Complex reasoning for task cate | Executes task breakdown phase to decompose feature specs into TDD implementation tasks. Use after /spec and /plan phases complete. Automatically invoked by /feature workflow. Creates tasks.md with 20- |
| validate-agent | — |
| analyze-phase-agent model: sonnet | Validates cross-artifact consistency and implementation readiness. Use after planning phase completes to check spec/plan/tasks alignment, identify critical issues, and confirm readiness. Auto-triggers |
| init-project-agent | — |
| prototype-discover-agent | — |
| roadmap-brainstorm-agent | — |
Slash commands (42)
/_archived/implement-epic-legacy/core/epic/core/feature/core/help/core/implement-epic/core/init/core/quick/core/ultrathink/deployment/budget/deployment/ship/deployment/validate-staging/infrastructure/audit-workflow/infrastructure/heal-workflow/infrastructure/workflow-health/internal/announce-release/internal/create-prompt/internal/release/internal/studio/meta/audit-claude-md/meta/context/meta/create-custom-tooling/meta/create/meta/run-prompt/meta/workflow-repair/phases/clarify/phases/debug/phases/finalize/phases/implement/phases/optimize/phases/plan/phases/spec/phases/tasks/phases/validate/project/constitution/project/init-preferences/project/init-project/project/init-tokens/project/prototype/project/roadmap/quality/fix-ci/quality/gate/quality/review
Similar rigs
glittercowboy/taches-cc-resources
A collection of my favorite custom Claude Code resources to make life easier.
Skill Collector 732 tok ·
Rohankundra2009/claude-agents-forge
Build and run production-ready Claude Code agents with full agent specs, including turn limits, permissions, memory, and tool orchestration.
Orchestrator 1.3k tok ·
runnithan/claudex-setup
Portable Claude Code and Codex configuration: slash commands, subagents, hooks, skills, and a transcript-to-lessons pipeline. Installable as a plugin.
Fort Knox 3.2k tok ·
Mationetap/claude-agents-forge
Production-hardened agent system for Claude Code — uses the full agent spec (maxTurns, permissionMode, disallowedTools, Task() orchestration, memory scopes, MCP integration)
Orchestrator 1.3k tok ·