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 instructions/petrludwig-collab/agent2telegram/agents-mdgit clone --depth 1 https://github.com/petrludwig-collab/Agent2TelegramWrote 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/instructions/petrludwig-collab/agent2telegram/agents-md)<a href="https://agentmods.dev/instructions/petrludwig-collab/agent2telegram/agents-md"><img src="https://agentmods.dev/badge/instructions/petrludwig-collab/agent2telegram/agents-md.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 | $0.01286 | $0.01286 |
| Opus 5 | $0.00643 | $0.00643 |
| Sonnet 5 | $0.00257 | $0.00257 |
| Haiku 4.5 | $0.00129 | $0.00129 |
Grade B, and why
Agent2Telegram AGENTS.md scanned grade B with 1 finding 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 4d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
…and `chmod 600` it. To get the user's id: have them message the bot, then read it from How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — install playbook for an AI agent
This file is written for an AI coding agent (Codex, Claude Code…) tasked with installing Agent2Telegram on a fresh machine for a non‑technical user. Follow it as a recipe. Do not improvise around the security rules.
Your goal
Get the Agent2Telegram bridge running so the user can talk to their agent from Telegram, then verify it actually works and hand the user a short summary.
Hard rules (do not break)
- Never weaken security. The bridge lets a Telegram user run commands on this machine.
The
allowed_user_idslist must contain only the owner's real Telegram user id. Never set it to empty "to make it work", never add unknown ids, never disable the check. - Never print, paste, or commit the bot token. It is a secret. It lives only in
~/.config/agent2telegram/config.json(mode 0600) or theTELEGRAM_BOT_TOKENenv var. - Do not use
shell=Trueor interpolate user input into shell strings anywhere. - If a step needs a secret or a decision only the user can make (token, which agent, their Telegram id), ask the user — don't guess.
Prerequisites to check first
Run these and fix what's missing before installing:
python3 --version→ must be 3.10+. If missing, install Python 3.git --version→ needed to fetch the repo. Install if missing.- The agent CLI to bridge must be installed and logged in:
- Claude Code:
claude --versionand a priorclaudelogin. - Codex:
codex --versionand a priorcodexlogin. - Test it works headlessly, e.g.
claude -p "say hi"orcodex exec "say hi". If the agent CLI isn't installed/authenticated, stop and ask the user to do that (it requires an interactive login you can't complete for them).
- Claude Code:
Install steps
git clone https://github.com/petrludwig-collab/Agent2Telegram.git
cd Agent2Telegram
python3 -m pip install --user . # or: --user --break-system-packages
Configure
Prefer the interactive wizard if the user is present:
python3 -m agent2telegram setup
If you must configure non‑interactively, ask the user for (a) which agent and (b) the bot
token and their Telegram user id, then write ~/.config/agent2telegram/config.json:
{ "agent": "codex", "token": "<ASK THE USER>", "allowed_user_ids": [<ASK THE USER>] }
…and chmod 600 it. To get the user's id: have them message the bot, then read it from
getUpdates, or ask them to send /id to the bot once it's running.
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.
- 4d ago First seen · 97 lines · 1,286 tokens per session scan B f851d7a3336e
Agent2Telegram AGENTS.md is an instructions file published in the GitHub repository petrludwig-collab/Agent2Telegram (19 stars, last pushed today), licensed MIT. It adds 1,286 tokens to every session, about $0.0064 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
WhatsAppToDiscord AGENTS.md
AGENTS.md instructions for arespawn/WhatsAppToDiscord, covering agent notes (agents.md), project snapshot, fast start, where the source of truth lives and critical guardrails.
antigravity-testing-kit GEMINI.md
Instructions for anhtester/antigravity-testing-kit, covering gemini ai - global automation agent rules, git pull restriction rule, browser rules (mandatory), 🖥️ viewport & mode and 🔄 thứ tự debug bắt buộc (playwright mcp).
toh-framework CLAUDE.md
Claude Code instructions for wasintoh/toh-framework, covering claude.md — toh framework (repo development guide), what this is, everyday commands, verification protocol and single source, transformed per ide.
awesome-copilot-id AGENTS.md
AGENTS.md instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.
codevira CLAUDE.md
Instructions for sachinshelke/codevira, covering codevira — persistent project memory, when to call which codevira tool, at the start of every session, before modifying any file and before adopting a pattern, library, or naming convention.
agent-skills AGENTS.md
AGENTS.md instructions for racastellanosm/agent-skills, covering agents.md, 1. vision & architectural invariants, 2. repository architecture & layout, 3. harness support & installation paths and 4. scripting & tooling guardrails.