telegram-summarize: Instructions file for Codex

AGENTS.md

telegram-summarize AGENTS.md is an instructions file for Codex, OpenCode from t0uchY233/telegram-summarize. It costs 1,115 tokens per session, scanned A, original, MIT.

Project instructions for a Telegram discussion summarizer. They describe how an agent should retrieve messages for a date range, check coverage, and produce a cited summary.

In plain words
What is it for?
They guide agents in finding chats, retrieving complete message ranges, removing duplicates, sorting messages, and summarizing topics and participants.
Why use it?
They provide a consistent process for handling Telegram sources and dates without guessing which chat or messages to use.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Codex.

This is t0uchY233/telegram-summarize's own configuration. It tells Codex and OpenCode how to work on telegram-summarize itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything telegram-summarize configures →

Reuse

Borrowing it

Nothing to install: this file belongs to t0uchY233/telegram-summarize. 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/t0uchY233/telegram-summarize/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/t0uchY233/telegram-summarize

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.

agentmods badge for telegram-summarize AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/t0uchy233/telegram-summarize/agents-md/github.svg)](https://agentmods.dev/instructions/t0uchy233/telegram-summarize/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/t0uchy233/telegram-summarize/agents-md"><img src="https://agentmods.dev/badge/instructions/t0uchy233/telegram-summarize/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.

agentmods 80×15 button for telegram-summarize AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/t0uchy233/telegram-summarize/agents-md"><img src="https://agentmods.dev/badge/instructions/t0uchy233/telegram-summarize/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,115 This file is loaded in full into every session.
When invoked 1,115 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01115 $0.01115
Opus 5.5 $0.00446 $0.00446
Sonnet 5.5 $0.00223 $0.00223
Haiku 4.5 $0.00112 $0.00112

Measured 2mo ago against content hash e10c6bc1cdc5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

telegram-summarize 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 · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

telegram-mcp — Agent Instructions

This repository exposes a Telegram account to MCP clients through MTProto. It uses Bun, TypeScript, mtcute, and @modelcontextprotocol/sdk. The Streamable HTTP endpoint is /mcp.

Primary Workflow

Operate this repository primarily as a read-only Telegram discussion summarizer for Codex, Claude, and other MCP-compatible agents.

For every date-and-source summary request, load and follow .agents/skills/meeting-minutes/SKILL.md.

request -> normalize range -> resolve source -> fetch bounded windows
-> verify coverage -> deduplicate -> chronological sort
-> summarize topics and participants -> cite sources -> state limitations

The MCP server supplies atomic Telegram data operations. The agent orchestrates those tools and writes the summary; the server does not embed an LLM.

Source and Time Resolution

  • Use an exact @username or numeric chat ID directly.
  • Otherwise call search_dialogs. If multiple plausible matches remain, ask the user to choose. Never guess a Telegram identity.
  • Accept one or more sources. Retrieve and report coverage independently for each source.
  • Treat start and end as inclusive.
  • When the end is omitted, use the actual current time.
  • When the timezone is omitted, use the MCP client's environment timezone and state it. Ask when no timezone is available.
  • When the year is omitted, use the current year. If that places the start in the future, ask for the year.
  • Convert boundaries to ISO 8601 before calling Telegram tools.

Complete Range Retrieval

  1. Call get_messages with chatId, minDate, maxDate, limit: 500, onlyUnread: false, and markAsRead: false.
  2. When limitReached is true, split the interval at its midpoint. Start the right window one second before the midpoint when both children remain strictly smaller.
  3. Split saturated children recursively. If a range cannot be split safely, report it as incomplete instead of looping or claiming full coverage.
  4. Deduplicate overlapping results by (chatId, id) and sort by date, then id.
  5. Do not substitute search_messages for range retrieval unless the user explicitly asks for keyword search.
  6. On FLOOD_WAIT, authentication failure, or inaccessible history, do not retry automatically. State the successful and missing subranges.

Read the full file on GitHub · 134 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.

  1. 2mo ago First seen · 134 lines · 1,115 tokens per session scan A e10c6bc1cdc5

Subscribe to this mod's changes

telegram-summarize AGENTS.md is an instructions file published in the GitHub repository t0uchY233/telegram-summarize (0 stars, last pushed 3mo ago), licensed MIT. It adds 1,115 tokens to every session, about $0.0045 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 2026-09-01.

Related

telegram-summarize AGENTS.md compared with instructions from other repositories

telegram-summarize AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
telegram-summarize AGENTS.mdt0uchY233/telegram-summarizeInstructions file03mo agoMITA1,115Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode