What is telegram-agent AGENTS.md?

A project guide for coding agents working on a local Telegram tool. It describes the project's purpose, files, architecture, configuration, and main entry points.

Use it when developing, debugging, or extending the Telegram agent, its MCP server, setup wizard, authentication, search, digests, or reply features.

It gives an agent the context needed to navigate the codebase and make changes in the right places. This reduces guesswork about how the Telegram tool is structured.

How Frejixxx/telegram-agent configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Frejixxx/telegram-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Frejixxx/telegram-agent/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Frejixxx/telegram-agent

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/frejixxx/telegram-agent/agents-md/github.svg)](https://agentmods.dev/instructions/frejixxx/telegram-agent/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/frejixxx/telegram-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/frejixxx/telegram-agent/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/frejixxx/telegram-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/frejixxx/telegram-agent/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,165 This file is loaded in full into every session.

When invoked 1,165 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01165	$0.01165
Opus 5.5	$0.00466	$0.00466
Sonnet 5.5	$0.00233	$0.00233
Haiku 4.5	$0.00117	$0.00117

Measured 2mo ago against content hash 31fe8aee1e73, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

telegram-agent AGENTS.md 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 2mo 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.

AGENTS.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project Identity

Telegram Agent is a local Codex plugin and MCP server for Telegram setup, inbox triage, dialog lookup, selected-chat context, message search, SQLite-backed digests/search/watchlists, maintainer intelligence, ordinary-user personal briefings, smart inbox ranking, local memory search, secret-safe sensitive search, contact briefs, follow-up tracking, prompt-injection detection, GitHub issue drafts, Codex context packs, local reply drafts, scoped reply sessions, and explicitly authorized sends. It is a CommonJS Node.js project.

Runtime Map

MCP entry point: scripts/telegram-agent-server.js.
Intelligence/cache module: scripts/intelligence-store.js.
Auth metadata module: scripts/auth-store.js.
Browser setup wizard: scripts/setup-web.js and scripts/setup-web-ui.js.
Demo entry point: scripts/demo.js.
Terminal login fallback: scripts/login.js.
Codex plugin manifest: .codex-plugin/plugin.json.
MCP server config: .mcp.json and .codex/config.toml.
Skill instructions loaded by Codex: skills/telegram-agent/SKILL.md.

The MCP server runs over stdio, implements initialize, tools/list, and tools/call, and returns tool output as JSON text content.

Directory Map

scripts/: first-party runtime and login code.
fixtures/: synthetic demo sources/messages; no real Telegram data.
skills/: Codex skill instructions for safe Telegram tool usage.
.codex-plugin/: plugin manifest consumed by Codex plugin install/cache.
.codex/: local Codex MCP config for this plugin.
.github/: GitHub Actions workflows.
test/: Node node:test unit tests.
node_modules/: vendored dependencies from npm install; do not edit.

Core Architecture

scripts/telegram-agent-server.js owns:

MCP tool schemas;
Telegram client loading/caching;
dialog and entity summaries;
message normalization and chat stats;
draft file creation/list/delete/send;
direct send gate via TELEGRAM_AGENT_ALLOW_SEND;
JSON-RPC framing over stdio.

Read the full file on GitHub · 111 lines

Changes

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.

2mo ago First seen · 111 lines · 1,165 tokens per session scan A 31fe8aee1e73

Subscribe to this mod's changes

telegram-agent AGENTS.md is an instructions file published in the GitHub repository Frejixxx/telegram-agent (1 stars, last pushed 4mo ago), licensed MIT. It adds 1,165 tokens to every session, about $0.0047 per session on Opus 5.5. 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.

telegram-agent AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
telegram-agent AGENTS.mdFrejixxx/telegram-agent	Instructions file	1	4mo ago	MIT	A	1,165	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,649	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

telegram-agent: Instructions file for Codex