dock-chat

dock-chat is a command for Claude Code from Jacksunwei/claude-telegram-buddy. It costs 12 tokens per session (323 once invoked), scanned A, original, Apache-2.0.

A command that connects the full coding-agent conversation to Telegram, a messaging app, so you can control the agent from your phone.

In plain words
What is it for?
Docking a session to Telegram, labeling it with its repository and branch, and routing replies through the phone.
Why use it?
It lets you continue conversations and approvals away from the terminal.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the telegram-buddy plugin — 4 commands shipped together

Good fit Docking a session to Telegram, labeling it with its repository and branch, and routing replies through the phone.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/jacksunwei/claude-telegram-buddy/dock-chat
Install

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.

Clone the repo
git clone --depth 1 https://github.com/Jacksunwei/claude-telegram-buddy

Made for: Claude Code.

Or install telegram-buddy, the plugin that ships this one along with the rest of its 4 commands.

Wrote 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.

agentmods badge for dock-chat

README.md
[![agentmods](https://agentmods.dev/badge/commands/jacksunwei/claude-telegram-buddy/dock-chat.svg)](https://agentmods.dev/commands/jacksunwei/claude-telegram-buddy/dock-chat)
Your own site
<a href="https://agentmods.dev/commands/jacksunwei/claude-telegram-buddy/dock-chat"><img src="https://agentmods.dev/badge/commands/jacksunwei/claude-telegram-buddy/dock-chat.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 323 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00012 $0.00323
Opus 5 $0.00006 $0.00161
Sonnet 5 $0.00002 $0.00065
Haiku 4.5 $0.00001 $0.00032

Measured 7d ago against content hash 47dc71fb9283, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

dock-chat 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 7d 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.

plugin/commands/dock-chat.md · 11 lines

What it actually says

Compute a short human-readable label for this session — combine the repo basename (from pwd and git rev-parse --show-toplevel if in a git repo, else just basename $(pwd)) and the current branch (git rev-parse --abbrev-ref HEAD if in a git repo, otherwise omit). Format: <repo> · <branch> (or just <repo> if no git, or just directory: <basename> as a last resort).

Then call mcp__plugin_telegram-buddy_telegram-buddy__dock_chat with session_id='${CLAUDE_SESSION_ID}' and label='<the label you computed>'. Report what it returns verbatim.

From that point on, the harness enforces the docking contract via PostToolBatch / Stop hooks (per docs/05). You should still follow the contract proactively: do NOT end any turn with a final assistant message — every turn that would normally produce a user-visible reply must instead call wait_for_user(session_id='${CLAUDE_SESSION_ID}', message_to_user=<your message>) and treat its return value as the user's next message. The hook-based enforcement will redirect you if you forget, but it's friendlier to all sides if you just route correctly the first time.

Changes

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.

  1. 7d ago First seen · 11 lines · 12 tokens per session scan A 47dc71fb9283

Subscribe to this mod's changes

dock-chat is a command published in the GitHub repository Jacksunwei/claude-telegram-buddy (3 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 12 tokens to every session and 323 once invoked, about $0.0001 per session on Opus 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.