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/awrshift/skill-telegram/skill-telegramnpx skills add awrshift/skill-telegram --skill skill-telegramgit clone --depth 1 https://github.com/awrshift/skill-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/skills/awrshift/skill-telegram/skill-telegram)<a href="https://agentmods.dev/skills/awrshift/skill-telegram/skill-telegram"><img src="https://agentmods.dev/badge/skills/awrshift/skill-telegram/skill-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 | $0.00143 | $0.01234 |
| Opus 5 | $0.00072 | $0.00617 |
| Sonnet 5 | $0.00029 | $0.00247 |
| Haiku 4.5 | $0.00014 | $0.00123 |
Grade A, and why
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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Telegram Skill — User API Integration
All operations via Telethon (user API, not bot API). One session file for everything.
Setup (first run)
- Get API credentials at https://my.telegram.org/apps → create app → copy
api_idandapi_hash - Set env vars in your
.env:TG_API_ID=your_api_id TG_API_HASH=your_api_hash - Install Telethon:
pip install telethon - Run setup diagnostic:
python3 scripts/tg_setup.py - Authenticate (first time):
python3 scripts/tg_setup.py --auth→ enter phone + code from Telegram
Session file is saved automatically. All subsequent operations reuse it.
Set TG_SESSION env var to point to your session file, or the skill auto-discovers it.
1. Read Messages (any chat)
# Saved Messages
python3 scripts/tg_read.py --saved-messages --limit 10
# Specific chat/person
python3 scripts/tg_read.py --chat username --limit 20
# Public channel
python3 scripts/tg_read.py --channel SEOBAZA --limit 5
# With explicit session file
python3 scripts/tg_read.py --saved-messages --limit 5 --session /path/to/tg_session.session
Output: JSON lines (one per message) with: id, date, text, has_voice, has_audio, has_photo, has_document, mime_type, file_size, duration.
2. Parse Channels
Fetch messages from public channels with text sanitization (anti-injection, emoji cleanup, link extraction, dedup hashing).
# Single channel
python3 scripts/tg_fetch_channels.py --channel SEOBAZA --limit 20
# Multiple channels
python3 scripts/tg_fetch_channels.py --channels SEOBAZA,seo_inside,serpstat --limit 10
# Since date
python3 scripts/tg_fetch_channels.py --channel SEOBAZA --since 2026-03-01
# Save to file
python3 scripts/tg_fetch_channels.py --channel SEOBAZA --output messages.jsonl
# Pretty JSON
python3 scripts/tg_fetch_channels.py --channel SEOBAZA --pretty
Output: JSONL with: channel, channel_id, id, date, text, text_sanitized, links, hash, views, forwards.
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.
- 3d ago First seen · 131 lines · 143 tokens per session scan A 01a5d6e97857
telegram is a skill published in the GitHub repository awrshift/skill-telegram (8 stars, last pushed 5mo ago), licensed MIT. It adds 143 tokens to every session and 1,234 once invoked, about $0.0007 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.
Other skills, from other repositories
bots
Use when multi-platform bot automation hub — Telegram, Twitter/X, and WhatsApp bots for automated engagement, content distribution, and revenue generation.
pr-babysit
The repeatable loop for watching a pull request until it is merged or closed, pairing webhook subscription with a scheduled self check-in so CI results, new pushes, and merge-conflict transitions are never missed; use when asked to watch, babysit, or autofix a PR, or right after creating one.
telegram-agent
Telegram CLI for AI agents. Use when the user needs to read or search Telegram, send or edit a message, download media, organise Saved Messages, monitor conversations, or automate a Telegram task. Triggers on “check my messages”, “send a message”, “search Telegram”, “read unread”, “listen to chat”, “download from…
limma
R limma package for microarray and RNA-seq. Use for linear models in differential expression.
bureaucracy-detector
Score any process, workflow, or meeting for bureaucrat-mode creep. Based on Paul Graham's bureaucrat mode anti-patterns and Chesky's war on fake work. Use when something feels slow and you want to know if it's necessary complexity or unnecessary bureaucracy.
ai-science-diffusion-generative-models
Code DDPM/DDIM diffusion samplers, linear/cosine noise schedules, and DDRM inverse-problem solving (denoising, inpainting, super-resolution) in NumPy/PyTorch. Use for forward/reverse diffusion, score matching, or DDIM sampling.