What is tgcli AGENTS.md?

Repository-specific instructions for tgcli, a tool that connects to Telegram and can archive messages in a local SQLite database. They describe the project layout, commands, configuration, and coding conventions.

Use them when installing dependencies, starting the MCP server, testing the Telegram client, building the project, or deciding where code and runtime data belong.

They give contributors the project rules and commands needed to change and test the code consistently.

How kfastov/tgcli configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to kfastov/tgcli. 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/kfastov/tgcli/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/kfastov/tgcli

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/kfastov/tgcli/agents-md/github.svg)](https://agentmods.dev/instructions/kfastov/tgcli/agents-md)

Your own site

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

Per session 912 This file is loaded in full into every session.

When invoked 912 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	$0.00912	$0.00912
Opus 5.5	$0.00365	$0.00365
Sonnet 5.5	$0.00182	$0.00182
Haiku 4.5	$0.00091	$0.00091

Measured yesterday against content hash 5578d2ea1173, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tgcli 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 yesterday.

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 · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure & Module Organization

mcp-server.js: MCP HTTP server built with @modelcontextprotocol/sdk, registering the Telegram tools (listChannels, searchChannels, getChannelMessages, scheduleMessageSync, listMessageSyncJobs).
telegram-client.js: Domain logic for MTProto login, dialog traversal, and message helpers.
client.js: Example CLI harness for manual testing without the MCP layer.
message-sync-service.js: Background worker that archives messages into a local SQLite database.
Store location: OS app-data dir (tgcli store; override with TGCLI_STORE); keep runtime artifacts out of version control.
Documentation lives in README.md and LIBRARY.md; configuration relies on environment variables and the tgcli store.

Build, Test, and Development Commands

npm install: Restore dependencies whenever package-lock.json changes.
npm start: Boot the MCP server on http://localhost:8080/mcp using Streamable HTTP transport; first run drives the Telegram login flow.
node cli.js <command>: Run the CLI from the clone (Node 22, see .nvmrc); docs/development.md covers trying a change on the real account with node cli.js server restart.
node client.js: Run the sample script to exercise the client API and inspect dialog listings.
npm run build: Currently a no-op placeholder—extend it only if a transpile/bundle step is introduced.
npm test: Placeholder that echoes a notice; replace with real checks once tests exist.

Coding Style & Naming Conventions

Use ES modules with semicolons, two-space indentation, and camelCase identifiers.
Keep tool names descriptive and aligned with Telegram operations (listChannels, searchChannels, etc.).
Emit log lines that explain side effects (login state, MTProto calls, sync progress) and reference chat IDs/titles.
Keep message sync queue strictly sequential; jobs transition through pending → in_progress → idle and may move to error if retries are needed.
Store secrets in .env; never hard-code API credentials or session paths in commits.

Read the full file on GitHub · 57 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.

yesterday Changed · +3 lines · +141 tokens per session 5578d2ea1173
19d ago Changed · +1 tokens per session c05e2a1b711e
1mo ago Changed · +14 lines · +109 tokens per session 822d7051aaf2
2mo ago First seen · 40 lines · 661 tokens per session scan A 6557263b51cd

Subscribe to this mod's changes

tgcli AGENTS.md is an instructions file published in the GitHub repository kfastov/tgcli (44 stars, last pushed 2d ago), licensed MIT. It adds 912 tokens to every session, about $0.0036 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 2026-08-30.

agent-skill ai-agents mcp mcp-server telegram telegram-client

tgcli AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
tgcli AGENTS.mdkfastov/tgcli	Instructions file	44	2d ago	MIT	A	912	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
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

tgcli: Instructions file for Codex