tg-ai
CLAUDE.md0 starsChanged 2 months agoMITView on GitHub
The rules for this repository are in AGENTS.md. Read it first. This file deliberately restates nothing. A rule that exists in two places drifts in one of them. This project sends messages from a real person's personal Telegram account. tg_send_message refuses to message strangers, and that refusal has no override flag. Do not add one. See AGENTS.md §3.
In this repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- llms-full.txtllms.txt
- llms.txtllms.txt
- site/llms-full.txtllms.txt
- site/llms.txtllms.txt
- docs-maintenanceSkill
- mcp-tool-authoringSkill
- telegram-safetySkill
- docs-maintenanceSkill
- mcp-tool-authoringSkill
- telegram-safetySkill
The file
Files
CLAUDE.md
The rules for this repository are in AGENTS.md. Read it first.
This file deliberately restates nothing. A rule that exists in two places drifts in one of them.
Session start
- AGENTS.md
- docs/00-index/status.md
- docs/README.md - route to the slice your task needs
The one thing to know before touching anything
This project sends messages from a real person's personal Telegram account.
tg_send_message refuses to message strangers, and that refusal has no override
flag. Do not add one. See
AGENTS.md §3.
Common commands
just # list every recipe
just check # everything CI enforces - run before reporting done
just tg-status # account, session, database, archive healthDoes it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

