l4ci/rota
Run autonomous rounds of AI coding agents: an orchestrator assigns issues to Claude Code and Codex workers in their own worktrees, gates and merges their PRs, and keeps project memory in .rota/.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code
$ npx degit l4ci/rota/.claude ./rig-rota # 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 l4ci/rota/skills/rota-brainstorm .claude/skills/rota-brainstorm $ npx degit l4ci/rota/skills/rota-capture .claude/skills/rota-capture $ npx degit l4ci/rota/skills/rota-debug .claude/skills/rota-debug $ npx degit l4ci/rota/skills/rota-decide .claude/skills/rota-decide $ npx degit l4ci/rota/skills/rota-learn .claude/skills/rota-learn $ npx degit l4ci/rota/skills/rota-orchestrate .claude/skills/rota-orchestrate $ npx degit l4ci/rota/skills/rota-pause .claude/skills/rota-pause $ npx degit l4ci/rota/skills/rota-plan .claude/skills/rota-plan $ npx degit l4ci/rota/skills/rota-qa .claude/skills/rota-qa $ npx degit l4ci/rota/skills/rota-refactor .claude/skills/rota-refactor $ npx degit l4ci/rota/skills/rota-release .claude/skills/rota-release $ npx degit l4ci/rota/skills/rota-review .claude/skills/rota-review $ npx degit l4ci/rota/skills/rota-ship .claude/skills/rota-ship $ npx degit l4ci/rota/skills/rota-spike .claude/skills/rota-spike $ npx degit l4ci/rota/skills/rota-vision .claude/skills/rota-vision $ npx degit l4ci/rota/skills/rota-work .claude/skills/rota-work
$ curl -fsSL --create-dirs -o .claude/agents/rota-explorer.md https://raw.githubusercontent.com/l4ci/rota/main/.claude/agents/rota-explorer.md $ curl -fsSL --create-dirs -o .claude/agents/rota-implementer.md https://raw.githubusercontent.com/l4ci/rota/main/.claude/agents/rota-implementer.md $ curl -fsSL --create-dirs -o .claude/agents/rota-reasoner.md https://raw.githubusercontent.com/l4ci/rota/main/.claude/agents/rota-reasoner.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 (16)
rota-brainstormrota-capturerota-debugrota-deciderota-learnrota-orchestraterota-pauserota-planrota-qarota-refactorrota-releaserota-reviewrota-shiprota-spikerota-visionrota-work
Subagents (3)
| rota-explorer model: haiku | Read-only discovery for rota workers: searching, reading and summarising code. Use for broad lookups; it must not edit files. |
| rota-implementer model: sonnet | Writes code and tests for rota workers from a clear brief. Use for implementation that needs no new design. |
| rota-reasoner model: opus | Hard reasoning for rota workers: design, a tricky debugging hypothesis, an architecture call. Use sparingly. |
Similar rigs
obra/superpowers
An agentic skills framework & software development methodology that works.
Skill Collector 3.0k tok ·
anthropics/skills
Public repository for Agent Skills
Skill Collector 1.3k tok ·
anthropics/claude-code
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
Skill Collector 1.4k tok ·
JuliusBrussee/caveman
🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
Skill Collector 16.5k tok ·