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.
curl -O https://raw.githubusercontent.com/t0uchY233/telegram-summarize/main/AGENTS.mdgit clone --depth 1 https://github.com/t0uchY233/telegram-summarizeWrote 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/t0uchy233/telegram-summarize/agents-md)<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.
<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>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 | $0.01115 | $0.01115 |
| Opus 5.5 | $0.00446 | $0.00446 |
| Sonnet 5.5 | $0.00223 | $0.00223 |
| Haiku 4.5 | $0.00112 | $0.00112 |
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.
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
@usernameor 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
- Call
get_messageswithchatId,minDate,maxDate,limit: 500,onlyUnread: false, andmarkAsRead: false. - When
limitReachedis true, split the interval at its midpoint. Start the right window one second before the midpoint when both children remain strictly smaller. - Split saturated children recursively. If a range cannot be split safely, report it as incomplete instead of looping or claiming full coverage.
- Deduplicate overlapping results by
(chatId, id)and sort bydate, thenid. - Do not substitute
search_messagesfor range retrieval unless the user explicitly asks for keyword search. - On
FLOOD_WAIT, authentication failure, or inaccessible history, do not retry automatically. State the successful and missing subranges.
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 · 134 lines · 1,115 tokens per session scan A e10c6bc1cdc5
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.
telegram-summarize AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| telegram-summarize AGENTS.mdt0uchY233/telegram-summarize | Instructions file | 0 | 3mo ago | MIT | A | 1,115 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |