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 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/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/daxaur/openpaw/c-telegram"><img src="https://agentmods.dev/badge/skills/daxaur/openpaw/c-telegram.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 | $0.00022 | $0.00418 |
| Opus 5.5 | $0.00009 | $0.00167 |
| Sonnet 5.5 | $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 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
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.
- 1mo ago First seen · 67 lines · 22 tokens per session scan A 07492e89c600
c-telegram is a skill published in the GitHub repository daxaur/openpaw (173 stars, last pushed 5mo ago), licensed MIT. It adds 22 tokens to every session and 418 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
telegram-bot
Telegram bot development - chatbots, notifications, AI assistants, and group automation.
networking
A guide to Docker container networking, which controls how containers communicate with each other, the host computer, and other machines. It explains bridge, host, none, overlay, and macvlan network modes.
messaging
Send messages to users via WhatsApp and other connected channels. Use when asked to notify someone, send a message, reply to a contact, message a group, or proactively communicate through WhatsApp. Supports text, images, documents, audio, video, and stickers. Also provides group etiquette for observing group…
one-three-one-rule
1-3-1 decision briefs: problem, three options, one pick.
octo-drive
Octo Drive — spaces, folders, file upload/download, online-document mounts, share links, invites, IM-attachment transfer. Works with a bot token or a user API key; the CLI routes by token kind. Load after octo-shared.
octo-mail
OCTO Agent Mail operations for reading, searching, policy-aware sending, preparing drafts, and checking delivery status exclusively through octo-cli.