andrey342/baton
Run a written plan part by part from one chat in the Claude desktop app: nested sessions implement, a fresh reviewer checks, the chat supervises and delivers. A Claude Code plugin with no code.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code
$ npx degit andrey342/baton/skills ./rig-baton/skills 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 andrey342/baton/skills/event .claude/skills/event $ npx degit andrey342/baton/skills/plan .claude/skills/plan $ npx degit andrey342/baton/skills/run .claude/skills/run $ npx degit andrey342/baton/skills/setup .claude/skills/setup $ npx degit andrey342/baton/skills/status .claude/skills/status
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (5)
Similar rigs
gorock007/jarvis
Jarvis: one lead agent you talk to, a fleet of workers that builds. Runs in Superset or tmux, with Claude Code, Codex, OpenCode or any agent CLI as workers.
Minimalist 167 tok · · Q15
bharath-gp/agents-yoke
Coding agents working in tandem. Choose your agents and they will work together to achieve your goals.
Pragmatist 3.6k tok · · Q3
hashgraph-online/hol-guard
Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.
Minimalist 397 tok · · Q0
MohammadMD1383/claude-plugins
Claude Code plugin marketplace: focused, open-source plugins for Claude Code
Minimalist 583 tok · · Q0