agentrigs
+ submit rig
~ / rigs / kolega-ai / kolega-code

kolega-ai/kolega-code

Agentic coding in the terminal: the model writes its own multi-agent workflows (Gigacode). Provider-agnostic, local-first, 15+ model providers, MCP support.

↗ GitHub ★ 21 other updated 9d ago project Claude Code
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~601 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/kolega-ai/kolega-code

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 kolega-ai/kolega-code/kolega_code/_bundled_skills/skills/deep-research .claude/skills/deep-research
$ npx degit kolega-ai/kolega-code/kolega_code/_bundled_skills/skills/docx .claude/skills/docx
$ npx degit kolega-ai/kolega-code/kolega_code/_bundled_skills/skills/humanizer .claude/skills/humanizer
$ npx degit kolega-ai/kolega-code/kolega_code/_bundled_skills/skills/pdf .claude/skills/pdf
$ npx degit kolega-ai/kolega-code/kolega_code/_bundled_skills/skills/pptx .claude/skills/pptx
$ npx degit kolega-ai/kolega-code/kolega_code/_bundled_skills/skills/review .claude/skills/review
$ npx degit kolega-ai/kolega-code/kolega_code/_bundled_skills/skills/skill-authoring .claude/skills/skill-authoring
$ npx degit kolega-ai/kolega-code/kolega_code/_bundled_skills/skills/xlsx .claude/skills/xlsx

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 (8)

deep-researchdocxhumanizerpdfpptxreviewskill-authoringxlsx

Similar rigs

OpenCoworkAI/open-cowork
Open-source AI agent desktop app for Windows & macOS. One-click install Claude Code, MCP tools, and Skills — with sandbox isolation, multi-model support, and Feishu/Slack integration.
★ 2,172 project Claude Code 5 skills 25d ago
Pragmatist 382 tok ·
pheuter/claude-agent-desktop
Cross-platform desktop app for agentic chat powered by Claude Agent SDK.
★ 211 project Claude CodeCodex 5 skills 11mo ago
Pragmatist 1.1k tok ·
axoviq-ai/synthadoc
Synthadoc: An open-source LLM knowledge compilation engine that turns raw documents into structured, local-first wikis. A transparent, human-readable alternative to traditional RAG, which can be self-managed and self-improved without the us
★ 1,539 project Claude CodeCodexGemini CLI 10 skills 8d ago
Skill Collector 206 tok ·
tale-project/tale
Open-source project workspace for teams and AI agents. Assign tasks, coordinate agents in persistent sandboxes, and review results together. Self-hosted or managed cloud. MIT licensed.
★ 30 project Claude CodeCodexCopilot 2 mcp 8 skills 2 hooks 4d ago
YOLO Cowboy 16.5k tok ·
copied ✓