agentrigs
+ submit rig
~ / rigs / Tura-AI / tura

Tura-AI/tura

Build agent that uses 80% less token and delivers better results.

↗ GitHub ★ 651 agpl-3.0 updated 6d ago project Claude Code
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~38 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit Tura-AI/tura/agents ./rig-tura/agents
$ npx degit Tura-AI/tura/commands ./rig-tura/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/ARCHITECTURE.md https://raw.githubusercontent.com/Tura-AI/tura/main/agents/ARCHITECTURE.md
$ curl -fsSL --create-dirs -o .claude/agents/prompt.md https://raw.githubusercontent.com/Tura-AI/tura/main/agents/src/balanced/prompt.md
$ curl -fsSL --create-dirs -o .claude/agents/prompt.md https://raw.githubusercontent.com/Tura-AI/tura/main/agents/src/direct-text-only/prompt.md
$ curl -fsSL --create-dirs -o .claude/agents/prompt.md https://raw.githubusercontent.com/Tura-AI/tura/main/agents/src/direct/prompt.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 *)"
    ]
  }
}

Subagents (4)

ARCHITECTURE—
prompt—
prompt—
prompt—

Slash commands (3)

/generate_media/prompt/read_media/prompt/web_discover/prompt

Similar rigs

diegosvart/main-base-claude-code
Claude Code project template with inception agent, specialized subagents, and quality-enforced workflows. From idea to codebase in one structured discovery session.
★ 0 project Claude Code 5 agents 4 hooks 7mo ago
Orchestrator 52 tok ·
getnao/sylph
The open-source company brain. Run your entire company with AI agents, skills, and a self-improving context.
★ 196 project Claude CodeCodex 33 skills 16 agents 5mo ago
Orchestrator 3.5k tok ·
NazmusSayad/.dotfiles
My personal dotfiles, including configurations to customize and optimize my development environment for MacOS and Windows.
★ 90 setup Claude CodeCodex 17 skills 30 agents 8d ago
Orchestrator 1.6k tok ·
notque/vexjoy-agent
VexJoy AI Agent with Jev Intelligent Routing - /do routes plain-English requests to the right specialist agent and gates the work with reviews, tests, and a learning loop.
★ 425 project Claude Code 80 agents 64 hooks 13d ago
Orchestrator 2.5k tok ·
copied ✓