Borrowing it
Nothing to install: this file belongs to Jacksunwei/claude-telegram-buddy. 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/Jacksunwei/claude-telegram-buddy/main/CLAUDE.mdgit clone --depth 1 https://github.com/Jacksunwei/claude-telegram-buddyWrote 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/jacksunwei/claude-telegram-buddy/claude-md)<a href="https://agentmods.dev/instructions/jacksunwei/claude-telegram-buddy/claude-md"><img src="https://agentmods.dev/badge/instructions/jacksunwei/claude-telegram-buddy/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/jacksunwei/claude-telegram-buddy/claude-md"><img src="https://agentmods.dev/badge/instructions/jacksunwei/claude-telegram-buddy/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 | $0.01341 | $0.01341 |
| Opus 5 | $0.00671 | $0.00671 |
| Sonnet 5 | $0.00268 | $0.00268 |
| Haiku 4.5 | $0.00134 | $0.00134 |
Grade A, and why
claude-telegram-buddy CLAUDE.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
The hooks read sentinel files directly and never call the MCP server. This decoupling is intentional — hooks must keep working when the MCP server is gone. The `PermissionRequest` and `PostToolUse` hooks wired in `plugin How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this is
A Claude Code plugin that hands off an active session to Telegram so the user can step away from the desk. The repo is a single-plugin marketplace — .claude-plugin/marketplace.json is at the repo root, the actual plugin source lives in plugin/. Two modes coexist on the same MCP server:
- dock-approvals routes only
PermissionRequestprompts to Telegram as inline-keyboard buttons. - dock-chat routes every assistant turn to Telegram; replies become Claude's next prompt. Hook-enforced (see below).
Architecture you can't infer from one file
Multi-tenant single-host bridge (port 52891)
Every Claude Code session that subscribes runs its own MCP server (plugin/server/server.py). The first MCP server to bind 127.0.0.1:52891 wins the bind race and becomes the host — it routes Telegram I/O for every subscribed session, not just its own. Other servers stand by; they retry the bind every 30s, so when the host process exits the next probe finds the port free and a standby promotes automatically.
Practical consequence: the MCP tools (dock_approvals, dock_chat, wait_for_user, etc.) live in every session's MCP server, but the actual getUpdates polling and sendMessage calls happen only in the one process that owns the port. Tool calls in non-host sessions HTTP-POST to http://127.0.0.1:52891/{approve,chat-message,...} to reach the host.
Sentinel files as the source of truth
Under $TMPDIR/telegram-buddy/sessions/:
<session_id>— subscription marker, written bydock_approvalsANDdock_chat, removed byundock. Presence means "route this session's PermissionRequests to Telegram."<session_id>.docked— chat-dock marker, written ONLY bydock_chat. Presence means "the dock contract applies to this session" — the hooks read this file to decide whether to fire.
Sentinels survive the MCP server dying, so a newly-elected host instantly knows the full subscriber + dock state without any handoff protocol.
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 · 75 lines · 1,341 tokens per session scan A 87f97da3e025
claude-telegram-buddy CLAUDE.md is an instructions file published in the GitHub repository Jacksunwei/claude-telegram-buddy (3 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 1,341 tokens to every session, about $0.0067 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
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.