ccgram: Telegram tmux/herdr/agterm bridge for Claude Code, Codex CLI, and Pi Agent

by alexei-led · Claude Skill · ★ 286

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

Featured in: Telegram Bot

How to install ccgram

uv tool install ccgram          # recommended
pipx install ccgram             # pipx

Taken from the project's README on GitHub.

Security audit verdict: SAFE · quality 66/100

None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.

The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.

🧪 Tested by Agent Skills Hub

One of 20 tools we ran end to end on the same task for our Telegram Bot page (2026-10-10).

Our pick (To drive Claude Code from your phone): One of two bots of 14 that both refuse to start without your Telegram ID and send Claude's permission prompts to you in Telegram, so a risky command still waits for your tap. The other is six-ddc/ccbot, which it grew out of; ccgram had commits this week, ccbot's last was in July.

Result: Serves nobody until you list your Telegram ID · Claude's permission prompts come to you in Telegram · an allowed user can switch a session to YOLO, which skips the prompts

See the lines → · See the whole test →

agtermai-codingclaude-codeclicodexcodex-clideveloper-toolsgeminigemini-cliherdr

Quick Facts

Stars286
Forks88
LanguagePython
CategoryClaude Skill
LicenseMIT
Quality Score66/100
Open Issues19
Last Updated2026-11-04
Created2026-02-10
Platformsclaude-code, cli, codex, gemini, python
Est. Tokens~18k

About ccgram

CCGram — Control AI Coding Agents from Telegram Control AI coding agents from your phone. CCGram bridges Telegram to tmux — monitor output, respond to prompts, and manage multiple sessions without touching your computer. Supports Claude Code, Codex CLI, Gemini CLI, Pi, and plain shell sessions. Why CCGram? AI coding agents run in your terminal.

Compatible Skills

These tools work well together with ccgram for enhanced workflows:

  • SirChatalot — semantic(0.23)+complementary+rare_topics+same_lang+similar_pop+shared_platform (58%)
  • ClaudeBot — semantic(0.39)+complementary+rare_topics+similar_pop+shared_platform (58%)

ccgram alternative? Top 6 similar tools

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

  • ductor by PleasePrompto · ⭐ 448

    Control Claude Code, Codex CLI and Gemini CLI from Telegram. Live streaming, persistent memory, cron jobs, web

  • codexmate by SakuraByteCore · ⭐ 355

    Find, browse, and export conversations across AI coding tools. A local-first CLI + Web dashboard for Codex, Cl

  • squarebox by SquareWaveSystems · ⭐ 73

    A curated set of modern CLI/TUI tools and AI coding assistants in a container. Batteries included.

  • agent-deck by asheshgoplani · ⭐ 1.2k

    Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.

  • open-docs by bgauryy · ⭐ 513

    This repository contains documentation created to better understand the open project

  • toktrack by mag123c · ⭐ 197

    Ultra-fast token & cost tracker for LLM Token Usage (e.g. Claude Code)

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular Python Agent Tools

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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 Claude Skill tools