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 permgps · Agent Tool · ★ 72
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is herdr-telegram-agents safe to install? View the security audit →
Telegram Agents for Herdr One Telegram forum topic per live Herdr agent: status in the icon and messages both ways. A Herdr plugin for watching and controlling coding agents from a Telegram forum group. Each live agent gets a topic. Questions and completion posts arrive there; replies and command buttons go back to the agent. The bot can also ring an operator in a private chat when an agent needs an answer. Install You need Herdr 0.7.5 or newer, a bot token from @BotFather, and a Telegram supergroup with Topics enabled. The install step needs and on macOS or Linux, or PowerShell 5.1+ on Windows. Herdr downloads a checksum-verified release binary. Published targets are macOS and Linux on amd64 and arm64, and Windows on amd64. The plugin needs no Go toolchain on the machine where it is installed. Setup Create a bot with @BotFather and a supergroup with Topics enabled. In a Herdr pane, run . Enter the token in the popup, open its bot link, press Start, and add the bot to the group with Manage topics, Delete messages, and Pin messages. The account that selects the group becomes an operator. 4
| Stars | 72 |
| Forks | 9 |
| Language | Go |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 67.8634298184171/100 |
| Open Issues | 3 |
| Last Updated | 2026-10-01 |
| Created | 2026-09-02 |
| Platforms | claude-code, go |
| Est. Tokens | ~16k |
These tools work well together with herdr-telegram-agents for enhanced workflows:
Looking for a herdr-telegram-agents alternative? If you're comparing herdr-telegram-agents with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Telegram ↔ tmux/herdr/agterm bridge for Claude Code, Codex CLI, and Pi Agent. Monitor output, respond to promp
Automatically name Herdr tabs and panes from your current work, Git branch, terminal activity, and Claude Code
Credential-scoped AI usage, context, and cache in Herdr for Claude, Codex, Grok, Agy, OpenCode, Pi, omp, Devin
Credential-scoped AI quota, context, and cache in Herdr for Claude, Codex, Grok, Agy, OpenCode, Pi, omp, Devin
CLI that picks Cursor, Claude Code, Codex, or OpenCode + model/effort for a task, then launches it. Powered by
Self-hosted PWA to control Claude Code, Codex, GitHub Copilot or any terminal from your phone or desktop. Sing
Explore other popular agent tool tools:
herdr-telegram-agents is Drive your coding agents from Telegram like from the terminal. A topic per agent, live status in the topic icon, two-way chat with inline buttons for choices.. It is categorized as a Agent Tool with 72 GitHub stars.
herdr-telegram-agents is primarily written in Go. It covers topics such as claude-code, coding-agents, go.
You can find installation instructions and usage details in the herdr-telegram-agents GitHub repository at github.com/permgps/herdr-telegram-agents. The project has 72 stars and 9 forks, indicating an active community.
herdr-telegram-agents is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to herdr-telegram-agents on Agent Skills Hub include ccgram, herdr-auto-title, herdr-agent-usage. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: