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-repliesgit 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-replies)<a href="https://agentmods.dev/skills/smixs/iva-agent/rich-replies"><img src="https://agentmods.dev/badge/skills/smixs/iva-agent/rich-replies/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/skills/smixs/iva-agent/rich-replies"><img src="https://agentmods.dev/badge/skills/smixs/iva-agent/rich-replies.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 | $0.00071 | $0.02645 |
| Opus 5.5 | $0.00028 | $0.01058 |
| Sonnet 5.5 | $0.00014 | $0.00529 |
| Haiku 4.5 | $0.00007 | $0.00265 |
Grade A, and why
rich-replies 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 7d 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rich replies — what Telegram can render in your answer
Your reply is markdown. The host sends it as a Telegram rich message as soon
as it contains something ordinary messages cannot show (a table, a fold, a
footnote, a formula, a picture, any <tg-*> tag, a button). Otherwise it goes
as a plain formatted message. You never call anything: you write the markup and
the transport is chosen for you. Every construct below renders natively on a
Telegram client from summer 2026 or later.
This skill is about the reply in the current chat. A post to another chat
(digest, channel) with local pictures is rich-post.
When to reach for rich constructs
Use them when they carry meaning the reader would otherwise have to dig out:
| Reader's need | Use | Don't |
|---|---|---|
| Compare 3+ things by 2+ attributes | table | a table for two numbers |
| Long answer with sections | ## headings |
headings in a three-line reply |
| Optional depth (logs, raw data, method) | <details> fold |
hide the answer itself |
| Source or aside | footnote [^1] |
footnotes instead of a link |
| Formula | $x^2$, $$…$$ |
LaTeX for "2 + 2" |
| Step status, checklist | - [ ] / - [x] |
task list for prose |
| Picture or several by public URL | image line, <tg-collage>, <tg-slideshow> |
local file paths (use rich-post) |
| Place | <tg-map> |
a map for a city name |
| A moment in the reader's time zone | <tg-time> |
for "tomorrow" in prose |
| Next step, choice, link, copyable value | buttons under a question (below) | buttons on every reply |
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.
- 7d ago Changed · +47 lines a220a0d87f93
- 10d ago Changed dfa64f398ff4
- 1mo ago First seen · 154 lines · 71 tokens per session scan A f0a37d582e67
rich-replies is a skill published in the GitHub repository smixs/iva-agent (240 stars, last pushed today), licensed MIT. It adds 71 tokens to every session and 2,645 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 2026-09-14.
Other skills, from other repositories
research-report
Research report on companies, competitors, markets or products: research a company, compare competitors, market landscape, funding, pricing, launches. Also to save a brief, summary or snapshot built from search results.
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.
slacrawl
Archive and search Slack workspace messages, threads, and channels via the slacrawl CLI. Supports API sync, Slack export ZIP import, local desktop cache import, and full-text search.
apple-notes
Manage Apple Notes via the memo CLI on macOS (create, view, search, edit).
obsidian
Read, search, and create notes in the Obsidian vault.
designer_guide
Guidance for creating and editing designs using the designer tool.