Feramirr/frc-claude-config
Shared Claude Code config for FRC Team 1868 — rules, agents, commands, and skills for robot development
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 Feramirr/frc-claude-config/agents ./rig-frc-claude-config/agents $ npx degit Feramirr/frc-claude-config/commands ./rig-frc-claude-config/commands
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/architect.md https://raw.githubusercontent.com/Feramirr/frc-claude-config/main/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/build-error-resolver.md https://raw.githubusercontent.com/Feramirr/frc-claude-config/main/agents/build-error-resolver.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/Feramirr/frc-claude-config/main/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/database-reviewer.md https://raw.githubusercontent.com/Feramirr/frc-claude-config/main/agents/database-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/doc-updater.md https://raw.githubusercontent.com/Feramirr/frc-claude-config/main/agents/doc-updater.md $ curl -fsSL --create-dirs -o .claude/agents/e2e-runner.md https://raw.githubusercontent.com/Feramirr/frc-claude-config/main/agents/e2e-runner.md $ curl -fsSL --create-dirs -o .claude/agents/frc-build-resolver.md https://raw.githubusercontent.com/Feramirr/frc-claude-config/main/agents/frc-build-resolver.md $ curl -fsSL --create-dirs -o .claude/agents/frc-code-reviewer.md https://raw.githubusercontent.com/Feramirr/frc-claude-config/main/agents/frc-code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/frc-safety-reviewer.md https://raw.githubusercontent.com/Feramirr/frc-claude-config/main/agents/frc-safety-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/frc-subsystem-architect.md https://raw.githubusercontent.com/Feramirr/frc-claude-config/main/agents/frc-subsystem-architect.md $ curl -fsSL --create-dirs -o .claude/agents/frc-vision-reviewer.md https://raw.githubusercontent.com/Feramirr/frc-claude-config/main/agents/frc-vision-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/go-build-resolver.md https://raw.githubusercontent.com/Feramirr/frc-claude-config/main/agents/go-build-resolver.md $ curl -fsSL --create-dirs -o .claude/agents/go-reviewer.md https://raw.githubusercontent.com/Feramirr/frc-claude-config/main/agents/go-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/Feramirr/frc-claude-config/main/agents/planner.md $ curl -fsSL --create-dirs -o .claude/agents/python-reviewer.md https://raw.githubusercontent.com/Feramirr/frc-claude-config/main/agents/python-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/refactor-cleaner.md https://raw.githubusercontent.com/Feramirr/frc-claude-config/main/agents/refactor-cleaner.md $ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/Feramirr/frc-claude-config/main/agents/security-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/tdd-guide.md https://raw.githubusercontent.com/Feramirr/frc-claude-config/main/agents/tdd-guide.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 *)"
]
}
} Subagents (18)
| architect model: opus | Use this agent PROACTIVELY when planning new features, refactoring large systems, making architectural decisions, evaluating technical trade-offs, designing system architecture, or when a significant |
| build-error-resolver model: opus | Use this agent PROACTIVELY when a build fails, TypeScript compilation errors occur, type errors are detected, or any compilation/build-related issue needs resolution. This agent should be triggered au |
| code-reviewer model: sonnet | Use this agent when code has been written, modified, or is about to be committed. MUST BE USED for all code changes. This agent should be proactively invoked immediately after writing or modifying any |
| database-reviewer model: sonnet | Use this agent PROACTIVELY when writing SQL queries, creating database migrations, designing schemas, modifying RLS policies, troubleshooting database performance, or working with Supabase/PostgreSQL. |
| doc-updater model: haiku | Use this agent PROACTIVELY whenever code changes are made that affect architecture, APIs, dependencies, or project structure. This includes: new features added, API routes changed, dependencies added |
| e2e-runner model: sonnet | Use this agent PROACTIVELY when end-to-end tests need to be generated, maintained, or executed. This includes after implementing new features, modifying UI components, fixing bugs that affect user flo |
| frc-build-resolver model: sonnet | Resolves FRC-specific build errors including GradleRIO, vendor dependencies (CTRE, REV, PhotonVision), WPILib version mismatches, and deployment issues. |
| frc-code-reviewer model: opus | Reviews FRC robot code for quality, safety, WPILib best practices, and command-based architecture patterns. Covers Java, C++, and Python. |
| frc-safety-reviewer model: opus | Focused safety audit for FRC robot code. Checks motor protection, mechanism limits, CAN bus health, brownout handling, and match-time safety. |
| frc-subsystem-architect model: opus | Designs and reviews FRC subsystem architecture following Oblarg's command-based best practices, AdvantageKit IO patterns, and modular design principles. |
| frc-vision-reviewer model: opus | Reviews FRC vision processing code including PhotonVision, AprilTag pose estimation, coprocessor integration (Jetson Orin/Nano, Raspberry Pi), Foxglove/MCAP logging, and NetworkTables communication. |
| go-build-resolver model: sonnet | Use this agent when Go builds fail, `go vet` reports issues, or linter warnings need resolution. This includes compilation errors, type mismatches, missing imports, module dependency problems, interfa |
| go-reviewer model: sonnet | Use this agent when Go code has been written, modified, or committed. MUST BE USED for all Go projects and Go code changes. This includes new Go files, modifications to existing Go files, or any pull |
| planner model: opus | Use this agent PROACTIVELY when users request feature implementation, architectural changes, or complex refactoring. Automatically activate this agent when the user describes a new feature to build, a |
| python-reviewer model: sonnet | Use this agent when Python code has been written, modified, or committed. MUST BE USED for Python projects. This includes after writing new Python functions, refactoring existing Python code, reviewin |
| refactor-cleaner model: sonnet | Use this agent PROACTIVELY when dead code, unused exports, duplicate code, or unused dependencies need to be cleaned up. This agent should be launched after feature work is complete, during dedicated |
| security-reviewer model: sonnet | Use this agent PROACTIVELY after writing or modifying code that handles user input, authentication, authorization, API endpoints, database queries, file uploads, payment processing, webhook handling, |
| tdd-guide model: sonnet | Use this agent PROACTIVELY when writing new features, fixing bugs, or refactoring code to enforce test-driven development methodology. It should be launched before implementation begins to ensure test |
Slash commands (4)
/frc-premerge/frc-review/frc-safety-audit/frc-subsystem-review
Plugins (2)
everything-claude-code@everything-claude-codeclangd-lsp@claude-plugins-official
Similar rigs
peopleforrester/claude-dotfiles
Configuration layer for Claude Code: 70 skills, 15 agents, 21 rules, 14 hooks, and 4 sandboxed permission profiles, all schema-validated in CI
Fort Knox 862 tok ·
RohiRIK/claude-code-config
Personal Claude Code global config — hooks, agents, skills, commands
YOLO Cowboy 2.8k tok ·
Yuutokata/claude-code-setup
🔄 One Claude Code setup for my desktop and MacBook, synced through git, with guardrails that keep secrets out.
Fort Knox 1.1k tok ·
VersoXBT/claude-initial-setup
75 skills, 14 agents, 15 commands for Claude Code. Plug-and-play starter kit covering TypeScript, Python, Go, Rust, React, Next.js, FastAPI, Django, Docker, CI/CD, security, testing, and more. Cross-AI support for Cursor, Copilot, and Codex
Orchestrator 5.1k tok ·