telegram-summarize: Skill for Claude Code

.agents/skills/meeting-minutes/SKILL.md

meeting-minutes is a skill for Claude Code, Codex from t0uchY233/telegram-summarize. It costs 29 tokens per session (2,624 once invoked), scanned A, a copy of meeting-minutes, MIT.

A skill for turning short meetings, notes, transcripts, or Telegram discussions into structured minutes. TDD means test-driven development, but this skill is about documenting conversations, not writing tests.

In plain words
What is it for?
It helps create concise internal meeting minutes and topic-based summaries of Telegram groups or channels.
Why use it?
It keeps decisions, action items, participants, viewpoints, and discussion context together instead of producing an unstructured summary.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is t0uchY233/telegram-summarize's own configuration. It tells Claude Code and Codex 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/skills/meeting-minutes/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/t0uchY233/telegram-summarize

Made for: Claude Code, Codex.

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 meeting-minutes

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/t0uchy233/telegram-summarize/meeting-minutes"><img src="https://agentmods.dev/badge/skills/t0uchy233/telegram-summarize/meeting-minutes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,624 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 84% copy Near-identical to another mod 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 $0.00029 $0.02624
Opus 5 $0.00015 $0.01312
Sonnet 5 $0.00006 $0.00525
Haiku 4.5 $0.00003 $0.00262

Measured 11d ago against content hash 229558cdb37e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

meeting-minutes 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 11d 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.

Origin

This is a copy

84% identical to meeting-minutes — 58 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/meeting-minutes/SKILL.md · 292 lines

How it starts

The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Meeting Minutes Skill — Short Internal Meetings

Purpose / Overview

This Skill produces high-quality, consistent meeting minutes for internal meetings that are 60 minutes or shorter. Output is designed to be clear, actionable, and easy to convert into task trackers (e.g., GitHub Issues, Jira). The generated minutes prioritize decisions and action items so teams can move quickly from discussion to execution.

Telegram Discussion Summary Mode

Use this mode when the source is a Telegram channel or group. It replaces the meeting-specific intake questions and the Strict Minutes Schema below: do not ask for an organizer, agenda, reviewer, action items, or a next meeting unless the Telegram messages themselves establish them.

The core unit of the summary is a topic with its participants, positions, humor, and resources kept together. This preserves the social context of the discussion instead of reducing it to an anonymous list of conclusions.

Topic block

Use this shape for every substantive topic:

### <Topic>

- **What was discussed:** <concise synthesis>
- **Active participants and positions:**
  - @handle — <main claims, arguments, examples, or disagreement>
- **Outcome / disagreement:** <supported conclusion or unresolved split>
- **Resources:**
  - <exact URL> — <why it mattered in this topic> — <source message link>
- **From the chat:**
  > "<verbatim joke or meme quote>" — @handle, <reaction count>, <source message link>

Apply these rules:

  1. Attribute every topic. Name the people who materially advanced that topic and summarize the main thought each person contributed. Message volume alone does not make someone an active participant. A global participant table may supplement this, but never replace topic-level attribution.
  2. Use humor as evidence of the chat's tone. Quote a topical joke or meme verbatim when it naturally fits the topic. A context-free joke may appear in a separate From the chat interlude only when verified reaction metadata totals more than 4 reactions. Prefer the strongest 1–3 quotes across the whole summary so humor adds texture without taking over.
  3. Never infer reactions. Show a reaction count only when the source payload provides it. If reaction metadata is unavailable, do not claim that a quote passed the reaction threshold and do not use it as a context-free interlude.
  4. Keep resources with their discussion. Place GitHub repositories, documentation, articles, tools, videos, and other links inside the topic where they were mentioned. Preserve URLs exactly and add the source Telegram message link when possible.
  5. Reserve a standalone resources section for orphan links. Use Standalone resources only for links posted without enough surrounding discussion to assign them to a topic. Do not duplicate topic resources there.
  6. Preserve quotation fidelity. Do not rewrite, correct, sanitize, or merge a quoted joke. Keep it short, identify the author, and link the source message when possible.

Read the full file on GitHub · 292 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. 11d ago First seen · 292 lines · 29 tokens per session scan A 229558cdb37e

Subscribe to this mod's changes

meeting-minutes is a skill published in the GitHub repository t0uchY233/telegram-summarize (0 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 2,624 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 84% identical to meeting-minutes, differing in 58 lines, and is treated as a copy.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens