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.
npx skills add smixs/iva-agent --skill rich-postgit clone --depth 1 https://github.com/smixs/iva-agentWrote 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/skills/smixs/iva-agent/rich-post)<a href="https://agentmods.dev/skills/smixs/iva-agent/rich-post"><img src="https://agentmods.dev/badge/skills/smixs/iva-agent/rich-post.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00129 | $0.01834 |
| Opus 5 | $0.00064 | $0.00917 |
| Sonnet 5 | $0.00026 | $0.00367 |
| Haiku 4.5 | $0.00013 | $0.00183 |
Grade A, and why
rich-post 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 9d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rich-post — Telegram rich messages via the bot
Send ONE message that mixes text, inline images, tables, headings, lists,
block quotes, collapsible blocks and formulas. This is sendRichMessage
(Bot API 10.1, June 2026), not an album.
When NOT to use this
A report or an answer for the chat you are talking in is the plain reply of the
turn. The Outbox (agent/lib/outbox.ts) already routes a reply that needs
tables, task lists, <details> or block formulas into sendRichMessage, and
falls back to HTML if Bot API refuses it. Sending the same text with iva post
on top of that reply simply delivers it twice. Reach for this skill only when
the destination is a different allowlisted chat, or when the post needs inline
images and the owner asked for it there.
Album (sendMediaGroup) = up to 10 media, ONE caption, no text between images. Rich message = up to 50 media, text/tables/blocks interleaved in a single bubble. If the user wants "картинка в середине текста" or "таблица в посте" — this skill.
Quick start
iva post is the installed CLI command; run it from anywhere.
iva post --md-file /tmp/post.md
- Recipient: by default the message goes to
TELEGRAM_DIGEST_CHAT_IDfrom.env. An explicit--chat <id>is accepted ONLY if the id is allowlisted (TELEGRAM_ALLOWED_USER_IDS+TELEGRAM_DIGEST_CHAT_ID) — the recipient of a report is the owner's setting, not the model's choice. Anything else is refused without sending. --md/--md-file— markdown content (--md-file -reads stdin).--dry-run— OFFLINE check: validates the markdown and image paths, prints the result; nothing is uploaded or sent. Always run this first.--allow-upload— see «Local images» below. Off by default.--silent,--thread-id— optional.- Token: taken from the installation's
.env. There is NO--tokenflag (argv is visible in the process list) — don't put the token on the command line.
Local images — read before using
Telegram accepts ONLY public URLs for rich-message media (attach:// and
multipart upload fail with RICH_MESSAGE_PHOTO_URL_INVALID). So a local image
referenced as  must first be uploaded to a
public host. The command uses tmpfiles.org — an anonymous PUBLIC host:
anyone with the link can open the file while it lives there.
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.
- 9d ago First seen · 171 lines · 129 tokens per session scan A c4a28c50f890
rich-post is a skill published in the GitHub repository smixs/iva-agent (203 stars, last pushed 3d ago), licensed MIT. It adds 129 tokens to every session and 1,834 once invoked, about $0.0006 per session on Opus 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.
Other skills, from other repositories
ideation
Generate project ideas through creative constraints. Use when the user says 'I want to build something', 'give me a project idea', 'I'm bored', 'what should I make', 'inspire me', or any variant of 'I have tools but no direction'. Works for code, art, hardware, writing, tools, and anything that can be made.
sherpa-onnx-tts
Local text-to-speech via sherpa-onnx (offline, no cloud).
video-frames
Extract frames or short clips from videos using ffmpeg.
spotify-player
Terminal Spotify playback/search via spogo (preferred) or spotifyplayer.
design_creator
Structured workflow for creating professional designs — slide decks, documents, landing pages, app mockups, and motion storyboards.
video_guide
Guidance for generating videos and animating images.