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 glebis/claude-skills --skill telegram-telethongit clone --depth 1 https://github.com/glebis/claude-skillsWrote 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/glebis/claude-skills/telegram-telethon)<a href="https://agentmods.dev/skills/glebis/claude-skills/telegram-telethon"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/telegram-telethon/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/glebis/claude-skills/telegram-telethon"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/telegram-telethon.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 220 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00107 | $0.05108 |
| Opus 5 | $0.00053 | $0.02554 |
| Sonnet 5 | $0.00021 | $0.01022 |
| Haiku 4.5 | $0.00011 | $0.00511 |
Grade A, and why
telegram-telethon 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.
How it starts
The opening of the file, as written. The whole thing — 519 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Behavior Guidelines
Draft vs Send: Follow User's Intent
| User says | Codex does | Clarify? |
|---|---|---|
| "драфт", "draft", "сделай драфт" | draft |
No |
| "отправь", "пошли", "send" | send |
No |
| "напиши сообщение" (ambiguous) | Ask what user wants | Yes |
Key Rules
- Explicit draft → draft: "драфт", "draft" → use
draftcommand immediately - Explicit send → send: "отправь", "пошли", "send" → use
sendcommand immediately - Ambiguous → clarify: If neither "draft" nor "send" verb present, ask: "Создать драфт или сразу отправить?"
Examples
User: "сделай драфт для lv: привет"
Codex: Uses draft --chat "lv" --text "привет" immediately
User: "отправь сообщение Маше: встретимся в 5?"
Codex: Uses send --chat "Маша" --text "встретимся в 5?" immediately
User: "напиши сообщение для Маши: встретимся в 5?" Codex: Asks "Создать драфт или сразу отправить?"
Telegram Telethon Skill
Full Telethon API wrapper with daemon mode and Codex integration. Supports interactive setup, background message monitoring, and automatic Codex session spawning per chat.
Package Layout
telegram-telethon/
├── SKILL.md # This file
├── pyproject.toml # Installable Python package
├── scripts/
│ ├── tg.py # Main CLI (messages, media, drafts, etc.)
│ └── tgd.py # Daemon controller
├── src/telegram_telethon/ # Importable package
│ ├── core/ # auth, config
│ ├── modules/ # messages, media
│ ├── daemon/ # runner, handlers, claude_bridge
│ └── utils/ # formatting
└── tests/ # pytest unit + integration tests
Scripts import from src/telegram_telethon. Install the package in editable mode so tg.py/tgd.py can resolve imports:
cd telegram-telethon
pip install -e .
# or with dev tools (pytest, coverage):
pip install -e ".[dev]"
What ships with it
38 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .claude-plugin/plugin.json 299 B
- .gitignore 167 B
- pyproject.toml 1.1 KB
- scripts/tg.py 37 KB runs code
- scripts/tgd.py 3.0 KB runs code
- src/telegram_telethon/__init__.py 385 B runs code
- src/telegram_telethon/core/__init__.py 0 B runs code
- src/telegram_telethon/core/auth.py 9.8 KB runs code
- src/telegram_telethon/core/config.py 8.6 KB runs code
- src/telegram_telethon/daemon/__init__.py 0 B runs code
- src/telegram_telethon/daemon/claude_bridge.py 9.4 KB runs code
- src/telegram_telethon/daemon/handlers.py 8.5 KB runs code
- src/telegram_telethon/daemon/runner.py 8.7 KB runs code
- src/telegram_telethon/modules/__init__.py 0 B runs code
- src/telegram_telethon/modules/lint.py 5.2 KB runs code
- src/telegram_telethon/modules/markdown.py 1.9 KB runs code
- src/telegram_telethon/modules/media.py 13 KB runs code
- src/telegram_telethon/modules/messages.py 22 KB runs code
- src/telegram_telethon/modules/publish.py 19 KB runs code
- src/telegram_telethon/modules/schedule.py 2.1 KB runs code
- src/telegram_telethon/utils/__init__.py 0 B runs code
- src/telegram_telethon/utils/formatting.py 5.1 KB runs code
- tests/__init__.py 0 B runs code
- tests/conftest.py 2.3 KB runs code
- tests/integration/__init__.py 0 B runs code
- tests/unit/__init__.py 0 B runs code
- tests/unit/test_auth.py 7.0 KB runs code
- tests/unit/test_claude_bridge.py 9.6 KB runs code
- tests/unit/test_config.py 6.6 KB runs code
- tests/unit/test_daemon_handlers.py 9.0 KB runs code
- tests/unit/test_drafts.py 6.7 KB runs code
- tests/unit/test_formatting.py 9.4 KB runs code
- tests/unit/test_lint.py 5.3 KB runs code
- tests/unit/test_markdown.py 3.8 KB runs code
- tests/unit/test_media.py 14 KB runs code
- tests/unit/test_messages.py 17 KB runs code
- tests/unit/test_publish.py 20 KB runs code
- tests/unit/test_schedule.py 3.4 KB runs code
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.
- 7d ago First seen · 519 lines · 107 tokens per session scan A 5070588a63cf
telegram-telethon is a skill published in the GitHub repository glebis/claude-skills (374 stars, last pushed 9d ago), licensed MIT. It adds 107 tokens to every session and 5,108 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.