takopi — security grade SAFE, quality 67/100

Security audit verdict: SAFE · quality 67/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by banteg · Codex Skill · ★ 1.0k

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is takopi safe to install? View the security audit →

About takopi

takopi 🐙 he just wants to help-pi telegram bridge for codex, claude code, opencode, pi. manage multiple projects and worktrees, stream progress, and resume sessions anywhere. features projects and worktrees: work on multiple repos/branches simultaneously, branches are git worktrees stateless resume: continue in chat or copy the resume line to pick up in terminal progress streaming: commands, tools, file changes, elapsed time parallel runs across agent sessions, per-agent-session queue with Codex steering/cancel controls works with telegram features like voice notes and scheduled messages file transfer: send files to the repo or fetch files/dirs back group chats and topics: map group topics to repo/branch contexts works with existing anthropic and openai subscriptions requirements for installation () python 3.14+ () at least one engine on PATH: , , , or install setup run and follow the setup wizard.

agentbridgeclaudecodexopencodetelegramworktree

Quick Facts

Stars1,038
Forks132
LanguagePython
CategoryCodex Skill
LicenseMIT
Quality Score66.9244892866153/100
Open Issues42
Last Updated2026-05-25
Created2025-12-29
Platformsclaude-code, codex, python
Est. Tokens~105k

Compatible Skills

These tools work well together with takopi for enhanced workflows:

  • ccgram — semantic(0.33)+complementary+same_lang+similar_pop+shared_platform (57%)
  • overstory — semantic(0.19)+complementary+similar_pop+shared_platform (47%)
  • 3dsmax-mcp — semantic(0.19)+complementary+same_lang+shared_platform (46%)
  • Claude-to-IM — semantic(0.17)+complementary+similar_pop+shared_platform (46%)

takopi alternative? Top 6 similar tools

Looking for a takopi alternative? If you're comparing takopi with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • agentsys by agent-sh · ⭐ 984

    AI writes code. This automates everything else · 24 plugins · 49 agents · 44 skills · for Claude Code, OpenCod

  • agnix by agent-sh · ⭐ 422

    The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plug

  • aizen by vivy-company · ⭐ 298

    Bring order to your projects, environments, and day-to-day work.

  • context-engineering-kit by NeoLabHQ · ⭐ 1.4k

    Hand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor,

  • OpenContext by 0xranx · ⭐ 1.2k

    A personal context store for AI agents and assistants—reuse your existing coding agent CLI (Codex/Claude/OpenC

  • ClaudeR by IMNMV · ⭐ 337

    Connect RStudio to Claude Code, Codex, Gemini, and other LLM agents via MCP. Multi-agent orchestration, automa

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Python Agent Tools

Frequently Asked Questions

What is takopi?

takopi is he just wants to help-pi!. It is categorized as a Codex Skill with 1.0k GitHub stars.

What programming language is takopi written in?

takopi is primarily written in Python. It covers topics such as agent, bridge, claude.

How do I install or use takopi?

You can find installation instructions and usage details in the takopi GitHub repository at github.com/banteg/takopi. The project has 1.0k stars and 132 forks, indicating an active community.

What license does takopi use?

takopi is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to takopi?

The top alternatives to takopi on Agent Skills Hub include agentsys, agnix, aizen. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Codex Skill tools