Borrowing it
Nothing to install: this file belongs to Imolatte/claude-cli-telegram. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Imolatte/claude-cli-telegram/main/CLAUDE.mdgit clone --depth 1 https://github.com/Imolatte/claude-cli-telegramWrote 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/instructions/imolatte/claude-cli-telegram/claude-md)<a href="https://agentmods.dev/instructions/imolatte/claude-cli-telegram/claude-md"><img src="https://agentmods.dev/badge/instructions/imolatte/claude-cli-telegram/claude-md/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/instructions/imolatte/claude-cli-telegram/claude-md"><img src="https://agentmods.dev/badge/instructions/imolatte/claude-cli-telegram/claude-md.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 | $0.00345 | $0.00345 |
| Opus 5.5 | $0.00138 | $0.00138 |
| Sonnet 5.5 | $0.00069 | $0.00069 |
| Haiku 4.5 | $0.00034 | $0.00034 |
Grade A, and why
claude-cli-telegram CLAUDE.md scanned grade A with 0 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 1mo 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
TG Claude - Telegram Bridge for Claude Code
What This Is
Node.js bot that turns Mac into remote Claude Code terminal via Telegram. Not an API wrapper - runs real CLI with full tool access.
Architecture
User (Telegram) -> Bot (Node.js) -> Claude Code CLI -> tools -> response -> User
Key Files
worker/- Claude Code session management, message processingapproval-hook.mjs- PreToolUse hook, sends approval buttons to Telegramstop-hook.mjs- Stop hook, notifies on session endnotify-hook.mjs- Notification hookmode.mjs- Mode management (auto/confirm)bot-system-prompt.md- System prompt injected into every Claude sessionconfig.json- Bot token, allowed users, settings (NEVER commit)launcher.sh- Process manager
Rules
- Telegram HTML formatting only - no Markdown. Use
<b>,<code>,<pre>tags - No Markdown tables - Telegram doesn't render them
- Concise responses - phone screen, not desktop
- bot-system-prompt.md is the system prompt for Telegram sessions - edit there, not here
- config.json contains secrets - always in .gitignore
- test.txt in root is test artifact, can be deleted
Stack
- Node.js 20+ (ESM, .mjs)
- grammY (Telegram bot framework)
- Claude Code CLI (spawned as child process)
- No database - sessions in memory, config in JSON
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.
- 1mo ago First seen · 34 lines · 345 tokens per session scan A 8fdf5673a9b9
claude-cli-telegram CLAUDE.md is an instructions file published in the GitHub repository Imolatte/claude-cli-telegram (36 stars, last pushed 1mo ago), licensed MIT. It adds 345 tokens to every session, about $0.0014 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.