agentmods.dev

tg-rich-send

tg-rich-send is a skill for Cursor from mamahoos/dot-files. It costs 77 tokens per session (463 once invoked), scanned A, original, MIT.

A tool for sending Markdown messages or documents to Telegram, a messaging service, through a command-line program. It supports right-to-left text and splits long Markdown into message-sized parts.

In plain words
What is it for?
Use it to send a Markdown file or standard input to a Telegram chat, preview how it will be split, or choose the chat and text direction.
Why use it?
It avoids manually copying long reports into Telegram and preserves common Markdown formatting when sending them.

Skill for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions OpenCode.

not rated 5repo yesterday A scan 77 tokens original MIT

Good fit Use it to send a Markdown file or standard input to a Telegram chat, preview how it will be split, or choose the chat and text direction.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mamahoos/dot-files/tg-rich-send
View source ↗ mamahoos/dot-files
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add mamahoos/dot-files --skill tg-rich-send
Clone the repo
git clone --depth 1 https://github.com/mamahoos/dot-files

Made for: Cursor.

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 tg-rich-send

README.md
[![agentmods](https://agentmods.dev/badge/skills/mamahoos/dot-files/tg-rich-send/github.svg)](https://agentmods.dev/skills/mamahoos/dot-files/tg-rich-send)
Your own site
<a href="https://agentmods.dev/skills/mamahoos/dot-files/tg-rich-send"><img src="https://agentmods.dev/badge/skills/mamahoos/dot-files/tg-rich-send/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 tg-rich-send

Your own site · 80×15
<a href="https://agentmods.dev/skills/mamahoos/dot-files/tg-rich-send"><img src="https://agentmods.dev/badge/skills/mamahoos/dot-files/tg-rich-send.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 463 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 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 $0.00077 $0.00463
Opus 5.5 $0.00031 $0.00185
Sonnet 5.5 $0.00015 $0.00093
Haiku 4.5 $0.00008 $0.00046

Measured 20d ago against content hash fc9ea0370d3f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tg-rich-send 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 20d 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.

home/.cursor/skills/tg-rich-send/SKILL.md · 44 lines

What it actually says

tg-rich-send

Send Markdown to the user's Telegram. All logic (env, chunking, retries) lives in the script — call it, do not re-implement it.

Quick start

python3 ~/dev/scripts/tg-rich FILE.md          # send a file
cat doc.md | python3 ~/dev/scripts/tg-rich -   # send stdin
python3 ~/dev/scripts/tg-rich FILE.md --dry-run  # preview chunking only

Write the Markdown to a temp file first if it only exists in the conversation (/tmp/opencode/ is the approved scratch dir).

What the script does

  • Reads TELEGRAM_BOT_TOKEN / TELEGRAM_CHAT_ID from env or ~/dev/.env
  • Sends via sendRichMessage with rich_message.markdown (rich markdown style: # headings, > quotes, lists, --- dividers, ``` fences) and is_rtl: true
  • Chunks at top-level --- boundaries, never inside code fences (limit 3900 chars)
  • Prints part i/N: ok=True · message_id=... per chunk; exits non-zero on failure

Flags

Flag Effect
--dry-run show chunk sizes without sending
--no-rtl left-to-right (English/LTR-only content)
--limit N chunk size in chars
--chat ID override chat id

Notes

  • On failure the script prints the Telegram API error body — report it verbatim.
  • Missing env → check ~/dev/.env; do not hard-code the token anywhere.
  • Order of chunks is preserved; tell the user how many parts were sent.
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. 20d ago First seen · 44 lines · 77 tokens per session scan A fc9ea0370d3f

Subscribe to this mod's changes

tg-rich-send is a skill published in the GitHub repository mamahoos/dot-files (5 stars, last pushed yesterday), licensed MIT. It adds 77 tokens to every session and 463 once invoked, about $0.0003 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 2026-10-07.

ProductivityWriting and docsbashconfigurationdotfiles
Related

Other skills, from other repositories

herdr

Use when the user mentions herdr or is working inside a herdr pane and wants to save/restore a pane layout, change herdr's theme, prefix or other preferences on this host only, start or check on an agent in another herdr pane, add, turn off or open a herdr plugin (file viewer, keybindings), or asks why the herdr…

sfc-gh-eraigosa/dotfiles · 91 tokens

dotfile-systems-architect

Guides the creation of a "Minimal Root" home directory using the XDG Base Directory specification and a Bare Git Repository. Manages config separation, secrets, and cross-platform syncing.

organvm-iv-taxis/a-i--skills · 44 tokens

ghostty-config

Use when configuring Ghostty terminal emulator, working with ghostty config files, or looking up Ghostty settings and options.

denolfe/dotfiles · 28 tokens

defer

Use when you notice something to fix later while working on another task - captures context without breaking flow (10 seconds).

denolfe/dotfiles · 26 tokens

caveman

Ultra-compressed communication mode. Slash token usage 75% by speaking like caveman while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

Mte90/dotfiles · 73 tokens

master-build

Keep a stable, installed build of a desktop app that the owner can use and test while agents keep working in the repository. Use when agents building or launching the app are getting in the owner's way, when the working tree is often mid edit and does not compile, when asked for a "master build", or when the owner…

freekmurze/dotfiles · 80 tokens