telegram
Telegram
Send, read, and respond to Telegram messages via the Claudicle daemon adapter. Thin skill layer on top of the existing python-telegram-bot v22 polling adapter at ~/.claudicle/daemon/adapters/telegram_adapter.py.
When to Use This Skill
- Sending a Telegram message from a Claude Code session
- Checking for unhandled Telegram messages in the inbox
- Processing Telegram messages through the
/telegram-respondcognitive pipeline - Managing Telegram memory context (working memory, user models, soul state)
Prerequisites
python-telegram-botv21+ installed (pip install python-telegram-bot)TELEGRAM_BOT_TOKENin~/.config/env/secrets.env- Bot:
@claudicle_bot(ID: 8646522411) - Tom's Telegram ID:
633125581
Environment Variables
| Variable | Default | Description |
|---|---|---|
TELEGRAM_BOT_TOKEN |
-- | Bot token from @BotFather |
CLAUDICLE_TELEGRAM_ALLOWED_USERS |
-- | Comma-separated user IDs allowed to DM (empty = deny all) |
CLAUDICLE_TELEGRAM_ALLOWED_CHATS |
-- | Comma-separated chat IDs for groups (empty = all) |
CLAUDICLE_TELEGRAM_RESPOND_TO_DMS |
true |
Respond to private messages (filtered by allowed users) |
CLAUDICLE_TELEGRAM_RESPOND_TO_MENTIONS |
true |
Respond to @mentions in groups |
Quick Start
# Start the listener (background daemon)
python3 ~/.claudicle/adapters/telegram/telegram_listen.py --bg
# Check for unhandled messages
cd ~/.claude/skills/telegram/scripts && python3 telegram_check.py
# Send a message
cd ~/.claude/skills/telegram/scripts && python3 telegram_send.py 633125581 "Hello from Claudicle!"
# Process inbox through cognitive pipeline
/telegram-respond
Available Scripts
telegram_send.py -- Send a Telegram message
python3 ~/.claudicle/adapters/telegram/telegram_post.py CHAT_ID "Hello!"
python3 telegram_send.py CHAT_ID "Reply to this" --reply-to 42
python3 telegram_send.py CHAT_ID --stdin # Read text from stdin
python3 telegram_send.py --help
telegram_check.py -- Check inbox for unhandled messages
python3 telegram_check.py # Unhandled telegram:* entries
python3 telegram_check.py --all # All entries (including handled)
python3 telegram_check.py --limit 5 # Last 5
python3 telegram_check.py --mark-read MSG_ID # Mark entry as handled
python3 telegram_check.py --mark-all-read # Mark all as handled
Reads from ~/.claudicle/daemon/inbox.jsonl (shared with Slack/Discord).
telegram_memory.py -- Memory context CLI
python3 telegram_memory.py load-context 633125581
python3 telegram_memory.py user-model tg:633125581
python3 telegram_memory.py soul-state
Thin CLI over ~/.claudicle/adapters/shared/claudicle_memory.py.
Listener Management
The listener is the existing Claudicle adapter script (not duplicated):
python3 ~/.claudicle/adapters/telegram/telegram_listen.py --bg # Start
python3 ~/.claudicle/adapters/telegram/telegram_listen.py --status # Check
python3 ~/.claudicle/adapters/telegram/telegram_listen.py --stop # Stop
Channel Format
telegram:{chat_id} -- e.g., telegram:633125581 (private), telegram:-100123456789 (group)
Architecture
Claude Code session
|
|-- /telegram-respond (cognitive pipeline: 6 XML tags)
|-- telegram_send.py (wraps Bot API send_message)
|-- telegram_check.py (reads shared inbox.jsonl)
|-- telegram_memory.py (thin CLI over claudicle_memory)
|
v
~/.claudicle/adapters/telegram/ (existing, not duplicated)
telegram_listen.py (polling daemon)
telegram_post.py (CLI post)
_telegram_utils.py (split_message, config)
|
v
~/.claudicle/adapters/shared/claudicle_memory.py (3-tier memory routing)
Security
- DM access is DENY-by-default. Set
CLAUDICLE_TELEGRAM_ALLOWED_USERS=633125581to allow Tom. - User input is sanitized for XML tags before cognitive pipeline processing.
WebFetchremoved from allowed tools in daemon mode subprocess.
More from tdimino/claude-code-minoan
travel-requirements-expert
Plan a trip, create an itinerary, or research a destination through a structured 5-phase workflow---discovery questions, Exa/Firecrawl research, expert detail gathering, and a day-by-day requirements spec. This skill should be used when a user says "plan a trip," "create an itinerary," "help me visit [place]," or needs travel research with specific venues, safety protocols, and dietary accommodations.
67twilio-api
Use this skill when working with Twilio communication APIs for SMS/MMS messaging, voice calls, phone number management, TwiML, webhook integration, two-way SMS conversations, bulk sending, or production deployment of telephony features. Includes official Twilio patterns, production code examples from Twilio-Aldea (provider-agnostic webhooks, signature validation, TwiML responses), and comprehensive TypeScript examples.
65figma-mcp
Convert Figma designs into production-ready code using MCP server tools. Use this skill when users provide Figma URLs, request design-to-code conversion, ask to implement Figma mockups, or need to extract design tokens and system values from Figma files. Works with frames, components, and entire design files to generate HTML, CSS, React, or other frontend code.
61twitter
Twitter/X integration with three modes: official API v2 search/research via x-search (pay-per-use, $0.005/read), session-based posting/reading via bird CLI (free, browser cookies), and bookmark archival via Smaug. This skill should be used when searching tweets, researching topics on X, posting, monitoring accounts, or archiving bookmarks.
46nano-banana-pro
Generate and edit high-quality images using Google's Nano Banana Pro (Gemini 3 Pro Image) AI model. Use this skill when working with AI image generation or editing tasks including (1) Creating images from text prompts with professional quality, (2) Editing existing images with natural language instructions, (3) Multi-turn iterative image refinement, (4) Product photography and marketing visuals, (5) Creating infographics and diagrams with text, (6) Photorealistic and artistic image generation, (7) Batch image generation workflows, (8) Testing and troubleshooting Gemini image generation API. Supports up to 4K resolution, multiple aspect ratios, reference images, and advanced prompting techniques for cinema-quality results.
44architecture-md-builder
Build comprehensive ARCHITECTURE.md files following matklad's canonical guidelines — bird's-eye views, ASCII/Mermaid diagrams, codemaps, invariants, and layer boundaries. Triggers on document the architecture, create ARCHITECTURE.md, map this codebase, architectural overview.
42