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 agentmods add skills/daxaur/openpaw/c-telegramnpx skills add daxaur/openpaw --skill c-telegramgit clone --depth 1 https://github.com/daxaur/openpawWrote 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/daxaur/openpaw/c-telegram)<a href="https://agentmods.dev/skills/daxaur/openpaw/c-telegram"><img src="https://agentmods.dev/badge/skills/daxaur/openpaw/c-telegram.svg" alt="Measured on agentmods" 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 | $0.00022 | $0.00418 |
| Opus 5 | $0.00011 | $0.00209 |
| Sonnet 5 | $0.00004 | $0.00084 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade A, and why
c-telegram 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 5d 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
Telegram Bridge
Full bidirectional Claude-from-Telegram. Send messages from your phone, get responses from Claude with all your skills available.
How It Works
The OpenPaw Telegram bridge (openpaw telegram) connects a Telegram bot to Claude via the Agent SDK. Every skill installed in ~/.claude/skills/ is available as a bot command.
Starting the Bridge
openpaw telegram
This starts a long-running process. Keep it open in a terminal or tmux session.
Bot Commands
Built-in:
/start— show status and available skills/model sonnet|opus|haiku— switch Claude model/skills— list installed skills/stop— cancel current operation/clear— reset conversation
Skill commands (auto-generated from your installed skills):
/email check my inbox/music play some jazz/notes add grocery list/calendar what's on tomorrow- (any installed skill becomes a /command)
Or just send a regular message — Claude will figure out which skill to use.
Setup
Run during openpaw setup or separately:
openpaw telegram setup
You'll need:
- A Telegram bot token (from @BotFather)
- Your Telegram user ID (from @userinfobot)
Config is saved to ~/.config/openpaw/telegram.json.
Security
- Only responds to whitelisted user IDs
- Bot token stored with 600 permissions (owner-only)
- All Claude operations run locally on your machine
Guidelines
- The bridge maintains conversation context per user
- Use
/clearto start fresh if Claude gets confused - Use
/stopto cancel long-running operations - Model can be switched anytime with
/model
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.
- 5d ago First seen · 67 lines · 22 tokens per session scan A 07492e89c600
c-telegram is a skill published in the GitHub repository daxaur/openpaw (167 stars, last pushed 3mo ago), licensed MIT. It adds 22 tokens to every session and 418 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 2026-08-30.
Other skills, from other repositories
telegram
Multi-bot Telegram bridge — routes messages between Telegram and Claude tmux sessions.
telegram-bot
Telegram bot development - chatbots, notifications, AI assistants, and group automation.
add-telegram-api-action
Adds a new Telegram Bot API method (action class and top-level functions). Use when implementing a new Telegram API endpoint, adding support for a specific method (e.g. sendVideoNote, getChatMemberCount), or creating a new action for the telegram-bot library.
setup-bot-handlers
Skill "setup-bot-handlers" from vendelieu/telegram-bot, covering setup bot handlers, two approaches, dsl handlers, typed update handlers and input listener.
add-ktnip-ksp-tests
Adds tests for the ktnip KSP processor. Use when adding tests for a new collector, testing processor behavior with new annotations, or verifying KSP code generation for the telegram-bot library.
add-telegram-update-field
Adds a new field to the Update type and wires it through ProcessedUpdate, UpdateType, ProcessUpdate, KSP (TypeConstants, TypeMapper), and FunctionalDSLUtils. Use when implementing support for a new Telegram update type (e.g. messagereaction, chatboost), adding a new update handler, or extending the bot to handle…