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 serejaris/telegram-skills --skill tg-rich-digestgit clone --depth 1 https://github.com/serejaris/telegram-skillsWrote 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/serejaris/telegram-skills/tg-rich-digest)<a href="https://agentmods.dev/skills/serejaris/telegram-skills/tg-rich-digest"><img src="https://agentmods.dev/badge/skills/serejaris/telegram-skills/tg-rich-digest/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/serejaris/telegram-skills/tg-rich-digest"><img src="https://agentmods.dev/badge/skills/serejaris/telegram-skills/tg-rich-digest.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 | $0.00113 | $0.03692 |
| Opus 5 | $0.00056 | $0.01846 |
| Sonnet 5 | $0.00023 | $0.00738 |
| Haiku 4.5 | $0.00011 | $0.00369 |
Grade A, and why
tg-rich-digest scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST "https://api.telegram.org/bot$BOT_TOKEN/sendRichMessage" \ Copies of this mod
1 near-identical copy found in the catalogue:
- api-platform-state-processors — 86% identical, 385 lines differ
How it starts
The opening of the file, as written. The whole thing — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tg-rich-digest
Send a digest or report as a single structured Telegram Rich Message (Bot API 10.2) — section headings, topic lists, collapsible long-tail, photo collage, map embed, and a footer — all in one document-grade message.
Overview
A digest is a structured document, not a wall of text. Rich Messages let you organize it with real headings, lists, collapsible sections, and embedded media — readable on any screen, no HTML page required.
This skill covers the digest/report pattern specifically. For the complete block reference see ../tg-rich-messages/SKILL.md. To convert an existing Markdown report see ../tg-markdown-to-rich/SKILL.md.
Anatomy of a Digest
Recommended block sequence:
[heading h2] — digest title + date range
[paragraph] — 1–3 sentence lead: what happened, key number
[heading h3] — topic 1
[list] — 3–7 bullet items for topic 1
[heading h3] — topic 2
[list] — ...
[details] — "All links / Full list" — long-tail, closed by default
[divider] — visual separator before footer
[collage] — photo report (optional)
[map] — event location (optional)
[footer] — date, source, issue number
Each element below is shown as HTML markup, the string placed inside
InputRichMessage.html. Bot API 10.2 also accepts InputRichMessage.blocks for code-built
documents.
Note: When you receive the message back,
Message.rich_messagecontains the parsedRichBlockJSON (e.g.{"type": "heading", ...}). That structure is receive-only — you cannot send it.
Layout choice: flat digest vs. preview + full version
The anatomy above is the flat layout: everything visible, <details> reserved for the
long tail. It works for a short digest — a handful of bullets a reader scans in the feed.
It stops working once the digest becomes an article. A long rich message in a channel is rendered collapsed anyway, but Telegram decides where to cut, and the cut usually lands mid-sentence in the middle of your third section. The fix is to make the cut yourself:
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 359 lines · 113 tokens per session scan A 9d25ad072902
tg-rich-digest is a skill published in the GitHub repository serejaris/telegram-skills (18 stars, last pushed 1mo ago), licensed MIT. It adds 113 tokens to every session and 3,692 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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.
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…
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…