Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Lihan-Zhong/claude-code-telegram-multibot --skill claude-code-telegram-multibotgit clone --depth 1 https://github.com/Lihan-Zhong/claude-code-telegram-multibotWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/lihan-zhong/claude-code-telegram-multibot/claude-code-telegram-multibot)<a href="https://agentmods.dev/skills/lihan-zhong/claude-code-telegram-multibot/claude-code-telegram-multibot"><img src="https://agentmods.dev/badge/skills/lihan-zhong/claude-code-telegram-multibot/claude-code-telegram-multibot/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/lihan-zhong/claude-code-telegram-multibot/claude-code-telegram-multibot"><img src="https://agentmods.dev/badge/skills/lihan-zhong/claude-code-telegram-multibot/claude-code-telegram-multibot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00133 | $0.04203 |
| Opus 5 | $0.00067 | $0.02101 |
| Sonnet 5 | $0.00027 | $0.00841 |
| Haiku 4.5 | $0.00013 | $0.00420 |
Grade C, and why
setup-telegram-multibot scanned grade C with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
4. **Optional but recommended: `jq`** for the `claude-tg-pair` helper. Install via your package manager (`conda install -c conda-forge jq`, `sudo apt install jq`, `brew install jq`). Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
2. **Plugin is enabled.** Check `~/.claude/settings.json` has `"telegram@claude-plugins-official": true` under `enabledPlugins`. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "https://api.telegram.org/bot$TOKEN/getMe" How it starts
The opening of the file, as written. The whole thing — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Telegram Multi-Bot Setup for Claude Code
This skill handles a non-default architecture: one Telegram bot per Claude Code project, instead of the plugin's default single-bot-per-user model. Each project directory has its own bot token, its own pairing state, and its own bot server process — they don't compete with each other, and switching projects in Telegram is just switching chats.
Critical architecture insight
The official claude-plugins-official/telegram plugin defaults to a single state dir at ~/.claude/channels/telegram/. But server.ts reads:
const STATE_DIR = process.env.TELEGRAM_STATE_DIR ?? join(homedir(), '.claude', 'channels', 'telegram')
The TELEGRAM_STATE_DIR environment variable overrides the default. Every state file (.env, bot.pid, access.json, approved/, inbox/) lives under that dir. By giving each project a unique TELEGRAM_STATE_DIR, you get full isolation: separate token, separate pairing, separate bot server process. They can run simultaneously without fighting.
Combined with a per-project bot token (one @BotFather bot per project), you get the "one chat per project" UX in Telegram.
Prerequisites
Before doing any of this, verify:
-
Org policy allows channels. Check
~/.claude/remote-settings.jsonfor"channelsEnabled": trueAND an entry forplugin:telegraminallowedChannelPlugins. If channels are blocked by org policy, the admin must enable it via Claude.ai Admin Settings → Claude Code → Channels. No way to override locally. -
Plugin is enabled. Check
~/.claude/settings.jsonhas"telegram@claude-plugins-official": trueunderenabledPlugins. -
bunis installed (the plugin's MCP server runs on bun). Checkwhich bun. -
Optional but recommended:
jqfor theclaude-tg-pairhelper. Install via your package manager (conda install -c conda-forge jq,sudo apt install jq,brew install jq).
One-time setup
Check if the baseline is already done:
~/.bashrccontains aclaude-tg()function (NOT just an alias)~/.claude-telegram/directory exists- If you already had the single-default-bot setup before this migration:
~/.claude-telegram/<basename-of-HOME>is a symlink to~/.claude/channels/telegram(preserves the existing bot for$HOMEwork)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 298 lines · 133 tokens per session scan C 3985bfee1a18
setup-telegram-multibot is a skill published in the GitHub repository Lihan-Zhong/claude-code-telegram-multibot (2 stars, last pushed 3mo ago), licensed MIT. It adds 133 tokens to every session and 4,203 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it C with 3 findings (asks for root, reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
opencode-ensemble
Use when coordinating multiple coding agents, delegating independent software work, managing OpenCode Ensemble teams, choosing teammate roles or models, reviewing teammate output, or deciding whether parallel execution is appropriate.
goal-loop
Loop engineering as gradient descent — a guided goal loop where an agent factory generates goal-specialized agents (implementer, verifier, diagnoser, judge) and iterates forward → loss → backward → update until the goal is provably met. Evidence is split into visible validation (the implementer's loss) and held-out…
metaprompt
Generate a complete, ready-to-use prompt for a target model and harness. Triggers: metaprompt, generate a prompt for, write me a prompt, create a system prompt, prompt engineer this, optimize this prompt.
file-todos
File-based TODO lifecycle for tracking review findings, managing technical debt, and organizing work items. Each TODO is a standalone markdown file with YAML frontmatter, named by convention: {id}-{status}-{priority}-{description}.md. Status transitions drive the lifecycle: pending (created from review) -> ready…
codex-judge
Cross-provider LLM judge using Codex (GPT-5) to evaluate implementations written by Claude. Internal skill invoked by the insistir lead during the review loop. Not user-facing.
magi
Use when the user asks for magi, Open-Magi, @Open-Magi, deliberation, three sages, or multi-agent research.