agentsea/flashbacker
Claude Code state management with session continuity and AI personas, subagents and agent discussion
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 agentsea/flashbacker/templates/.claude ./rig-flashbacker # 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.
$ curl -fsSL --create-dirs -o .claude/agents/analyzer.md https://raw.githubusercontent.com/agentsea/flashbacker/main/templates/.claude/agents/analyzer.md $ curl -fsSL --create-dirs -o .claude/agents/api-designer.md https://raw.githubusercontent.com/agentsea/flashbacker/main/templates/.claude/agents/api-designer.md $ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/agentsea/flashbacker/main/templates/.claude/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/backend.md https://raw.githubusercontent.com/agentsea/flashbacker/main/templates/.claude/agents/backend.md $ curl -fsSL --create-dirs -o .claude/agents/cli-master.md https://raw.githubusercontent.com/agentsea/flashbacker/main/templates/.claude/agents/cli-master.md $ curl -fsSL --create-dirs -o .claude/agents/code-critic.md https://raw.githubusercontent.com/agentsea/flashbacker/main/templates/.claude/agents/code-critic.md $ curl -fsSL --create-dirs -o .claude/agents/data-engineer.md https://raw.githubusercontent.com/agentsea/flashbacker/main/templates/.claude/agents/data-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/database-architect.md https://raw.githubusercontent.com/agentsea/flashbacker/main/templates/.claude/agents/database-architect.md $ curl -fsSL --create-dirs -o .claude/agents/debt-hunter.md https://raw.githubusercontent.com/agentsea/flashbacker/main/templates/.claude/agents/debt-hunter.md $ curl -fsSL --create-dirs -o .claude/agents/devops.md https://raw.githubusercontent.com/agentsea/flashbacker/main/templates/.claude/agents/devops.md $ curl -fsSL --create-dirs -o .claude/agents/docker-master.md https://raw.githubusercontent.com/agentsea/flashbacker/main/templates/.claude/agents/docker-master.md $ curl -fsSL --create-dirs -o .claude/agents/fix-master.md https://raw.githubusercontent.com/agentsea/flashbacker/main/templates/.claude/agents/fix-master.md $ curl -fsSL --create-dirs -o .claude/agents/frontend.md https://raw.githubusercontent.com/agentsea/flashbacker/main/templates/.claude/agents/frontend.md $ curl -fsSL --create-dirs -o .claude/agents/gpt5-cursor.md https://raw.githubusercontent.com/agentsea/flashbacker/main/templates/.claude/agents/gpt5-cursor.md $ curl -fsSL --create-dirs -o .claude/agents/hallucination-hunter.md https://raw.githubusercontent.com/agentsea/flashbacker/main/templates/.claude/agents/hallucination-hunter.md $ curl -fsSL --create-dirs -o .claude/agents/john-carmack.md https://raw.githubusercontent.com/agentsea/flashbacker/main/templates/.claude/agents/john-carmack.md $ curl -fsSL --create-dirs -o .claude/agents/mentor.md https://raw.githubusercontent.com/agentsea/flashbacker/main/templates/.claude/agents/mentor.md $ curl -fsSL --create-dirs -o .claude/agents/performance.md https://raw.githubusercontent.com/agentsea/flashbacker/main/templates/.claude/agents/performance.md $ curl -fsSL --create-dirs -o .claude/agents/platform-engineer.md https://raw.githubusercontent.com/agentsea/flashbacker/main/templates/.claude/agents/platform-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/product.md https://raw.githubusercontent.com/agentsea/flashbacker/main/templates/.claude/agents/product.md $ curl -fsSL --create-dirs -o .claude/agents/qa.md https://raw.githubusercontent.com/agentsea/flashbacker/main/templates/.claude/agents/qa.md $ curl -fsSL --create-dirs -o .claude/agents/refactorer.md https://raw.githubusercontent.com/agentsea/flashbacker/main/templates/.claude/agents/refactorer.md $ curl -fsSL --create-dirs -o .claude/agents/security.md https://raw.githubusercontent.com/agentsea/flashbacker/main/templates/.claude/agents/security.md $ curl -fsSL --create-dirs -o .claude/agents/typescript-master.md https://raw.githubusercontent.com/agentsea/flashbacker/main/templates/.claude/agents/typescript-master.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 *)"
]
}
} Subagents (24)
| analyzer | Use for systematic investigation, root cause analysis, and evidence-based troubleshooting |
| api-designer | Use for REST/GraphQL API design, OpenAPI specifications, integration patterns, and API architecture with proven industry standards |
| architect | Use for system architecture design, scalability planning, dependency mapping, and long-term technical strategy |
| backend | Use for API design, database architecture, reliability engineering, and server-side development |
| cli-master | Use for CLI design, command-line interfaces optimized for both human and AI agent interaction. Takes ARGUMENTS - specify domain (human-first/machine-first/balanced) and requirements. |
| code-critic | Use for ruthless code quality enforcement, architectural integrity, and technical excellence validation |
| data-engineer | Use for ETL pipelines, data modeling, analytics architecture, streaming systems, and data processing with proven engineering patterns |
| database-architect | Use for database design, query optimization, schema evolution, and data architecture decisions with proven design patterns |
| debt-hunter | Use for technical debt detection, code quality analysis, and systematic codebase cleanup with CLI scanning capabilities |
| devops | Use for infrastructure automation, CI/CD pipelines, deployment strategies, and reliability engineering |
| docker-master | Use for Docker, Docker Compose, Swarm orchestration, networking, volumes, and containerization with expert-level knowledge |
| Fix Master | Surgical code fixes with systematic methodology for precise bug resolution |
| frontend | Use for UI/UX design, accessibility compliance, frontend performance, and user-centered development |
| gpt-5 model: sonnet | Use this agent when you need to use gpt-5 for deep research, second opinion or fixing a bug. Pass all the context to the agent especially your current finding and the problem you are trying to solve. |
| hallucination-hunter | Use for AI code validation, semantic correctness analysis, and detection of non-functional implementations that appear to work |
| john-carmack | Use for performance-critical systems analysis, game engine principles, functional programming discipline, and deterministic performance optimization |
| mentor | Use for educational guidance, knowledge transfer, step-by-step tutorials, and skill development |
| performance | Use for bottleneck identification, optimization strategies, performance profiling, and metrics-driven analysis |
| platform-engineer | Use for Kubernetes, infrastructure-as-code, observability, developer experience, and platform engineering with verified patterns |
| product | Use for feature prioritization, user research, market analysis, and product strategy development |
| qa | Use for comprehensive testing strategies, quality assurance, edge case identification, and defect prevention |
| refactorer | Use for code simplification, technical debt reduction, maintainability improvements, and clean code advocacy |
| security | Use for threat modeling, vulnerability assessment, security hardening, and compliance validation |
| typescript-master | Use for advanced TypeScript development, type system mastery, and production-ready code architecture. Always takes arguments - specify domain (backend/frontend/cli) and requirements. |
Slash commands (18)
/fb/agents-list/fb/create-issue/fb/create-tasks/fb/debt-hunter/fb/discuss/fb/fix-master-enhanced/fb/fix-master/fb/hallucination-hunter/fb/how/fb/persona-list/fb/persona/fb/remember/fb/save-session/fb/session-start/fb/tasks-status/fb/update-tasks/fb/work-task/fb/working-plan
Similar rigs
eugeek/claude-config-tdd
Claude Code config with TDD workflow, plan -> tests -> red -> implementation -> green -> review -> shipment
Orchestrator 5.8k tok ·
IntuitivePhella/AI-PhellOS
Portable AI development workflow template and CLI for spec-driven, test-aware software delivery with Codex, Claude Code, and other coding agents.
Orchestrator 3.1k tok ·
AgentWorkforce/relay
Infrastructure for coding agents
Orchestrator 8.5k tok ·
ThinhHoang1/claude-code-agent-team
An AI dev team for Claude Code agent teams: 8 role agents, a HANDOFF protocol and 3 hook quality gates — with the TeammateIdle infinite-loop bug fixed and regression-tested.
Orchestrator 1.6k tok ·