BabuNfr666/claude-effort-router
Let Claude Code pick the reasoning effort for each task - a plugin that routes hard work to high/max-effort subagents.
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 BabuNfr666/claude-effort-router/agents ./rig-claude-effort-router/agents $ npx degit BabuNfr666/claude-effort-router/skills ./rig-claude-effort-router/skills $ npx degit BabuNfr666/claude-effort-router/hooks ./rig-claude-effort-router/hooks
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 BabuNfr666/claude-effort-router/skills/deep .claude/skills/deep $ npx degit BabuNfr666/claude-effort-router/skills/dispatch .claude/skills/dispatch $ npx degit BabuNfr666/claude-effort-router/skills/max .claude/skills/max
$ curl -fsSL --create-dirs -o .claude/agents/deep-worker.md https://raw.githubusercontent.com/BabuNfr666/claude-effort-router/main/agents/deep-worker.md $ curl -fsSL --create-dirs -o .claude/agents/max-worker.md https://raw.githubusercontent.com/BabuNfr666/claude-effort-router/main/agents/max-worker.md
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 (3)
Subagents (2)
| deep-worker | High-effort worker for hard tasks - multi-file debugging, non-obvious bugs, architecture decisions, large refactors, tricky algorithms, security-sensitive changes. Use when a task needs careful multi- |
| max-worker | Maximum-effort worker for the hardest problems - bugs that resisted earlier attempts, concurrency or data-corruption issues, core architecture or migration design, subtle correctness proofs. Expensive |
Similar rigs
bassimeledath/dispatch
A Claude Code skill that 10x's your effective context window by dispatching tasks to background AI workers.
Minimalist 720 tok · · Q0
IvyYang1999/dispatch
Message channel between the agent sessions on one Mac (Claude Code, Codex, Grok Bot): find a session, deliver a message, get receipts and replies. CLI, MCP plugins, hook, desktop app.
Pragmatist 2.6k tok · · Q0
vmc-inner-circle/k-style-ui-ux
PRD 한 장으로 한국 앱 스타일 모바일 화면 초안을 15분 안팎에 만드는 Claude Code·Codex 플러그인
Minimalist 411 tok · · Q0
epilande/ccmux
🔮 Run all your AI coding agents in tmux: jump to the one that needs you, spawn them into worktrees, and hand work between them
Pragmatist 6.3k tok · · Q20