rtk-ai/rtk
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
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 rtk-ai/rtk/.claude ./rig-rtk # 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 rtk-ai/rtk/.claude/skills/code-simplifier .claude/skills/code-simplifier $ npx degit rtk-ai/rtk/.claude/skills/design-patterns .claude/skills/design-patterns $ npx degit rtk-ai/rtk/.claude/skills/issue-triage .claude/skills/issue-triage $ npx degit rtk-ai/rtk/.claude/skills/performance .claude/skills/performance $ npx degit rtk-ai/rtk/.claude/skills/pr-review .claude/skills/pr-review $ npx degit rtk-ai/rtk/.claude/skills/pr-triage .claude/skills/pr-triage $ npx degit rtk-ai/rtk/.claude/skills/repo-recap .claude/skills/repo-recap $ npx degit rtk-ai/rtk/.claude/skills/rtk-tdd .claude/skills/rtk-tdd $ npx degit rtk-ai/rtk/.claude/skills/rtk-triage .claude/skills/rtk-triage $ npx degit rtk-ai/rtk/.claude/skills/security-guardian .claude/skills/security-guardian $ npx degit rtk-ai/rtk/.claude/skills/ship .claude/skills/ship $ npx degit rtk-ai/rtk/.claude/skills/tdd-rust .claude/skills/tdd-rust
$ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/rtk-ai/rtk/develop/.claude/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/debugger.md https://raw.githubusercontent.com/rtk-ai/rtk/develop/.claude/agents/debugger.md $ curl -fsSL --create-dirs -o .claude/agents/rtk-testing-specialist.md https://raw.githubusercontent.com/rtk-ai/rtk/develop/.claude/agents/rtk-testing-specialist.md $ curl -fsSL --create-dirs -o .claude/agents/rust-rtk.md https://raw.githubusercontent.com/rtk-ai/rtk/develop/.claude/agents/rust-rtk.md $ curl -fsSL --create-dirs -o .claude/agents/system-architect.md https://raw.githubusercontent.com/rtk-ai/rtk/develop/.claude/agents/system-architect.md $ curl -fsSL --create-dirs -o .claude/agents/technical-writer.md https://raw.githubusercontent.com/rtk-ai/rtk/develop/.claude/agents/technical-writer.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 *)"
]
}
} Skills (12)
code-simplifierdesign-patternsissue-triageperformancepr-reviewpr-triagerepo-recaprtk-tddrtk-triagesecurity-guardianshiptdd-rust
Subagents (6)
| code-reviewer model: sonnet | Use this agent when you need comprehensive code quality assurance, security vulnerability detection, or performance optimization analysis. This agent should be invoked PROACTIVELY after completing log |
| debugger model: sonnet | Use this agent when encountering errors, test failures, unexpected behavior, or when RTK doesn't work as expected. This agent should be used proactively whenever you encounter issues during developmen |
| rtk-testing-specialist model: sonnet | RTK testing expert - snapshot tests, token accuracy, cross-platform validation |
| rust-rtk model: sonnet | Expert Rust developer for RTK - CLI proxy patterns, filter design, performance optimization |
| system-architect model: sonnet | Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing perfo |
| technical-writer model: sonnet | Create clear, comprehensive CLI documentation for RTK with focus on usability, performance claims, and practical examples |
Slash commands (17)
/clean-worktree/clean-worktrees/diagnose/rtk-commit-message-style/rtk-no-history-rewrite/rtk-rust-safety-net/rtk-test-before-merge/tech/audit-codebase/tech/clean-worktree/tech/clean-worktrees/tech/codereview/tech/remove-worktree/tech/worktree-status/tech/worktree/test-routing/worktree-status/worktree
Similar rigs
FlorianBruniaux/ccboard
Monitor Claude Code sessions, costs, config, hooks, agents & MCP servers from a single Rust binary — TUI (9 tabs) + Web interface with live process tracking, budget alerts, and 30-day forecasting
Fort Knox 11.3k tok ·
IvanKuzyshyn/dotfiles
Dotfiles optimized for speed, coffee, and questionable life choices. 😜
Pragmatist 3.0k tok ·
braden-w/claude-config
My personal Claude Code configuration - coding preferences, conventions, and read-only permissions for safe codebase exploration
Minimalist 776 tok ·
tylerjkells/claude-dotfiles
—
Pragmatist 579 tok ·