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 datacore-one/datacore --skill telegram-output-formattinggit clone --depth 1 https://github.com/datacore-one/datacoreWrote 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/datacore-one/datacore/telegram-output-formatting)<a href="https://agentmods.dev/skills/datacore-one/datacore/telegram-output-formatting"><img src="https://agentmods.dev/badge/skills/datacore-one/datacore/telegram-output-formatting/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/datacore-one/datacore/telegram-output-formatting"><img src="https://agentmods.dev/badge/skills/datacore-one/datacore/telegram-output-formatting.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 | $0.00051 | $0.01077 |
| Opus 5.5 | $0.00020 | $0.00431 |
| Sonnet 5.5 | $0.00010 | $0.00215 |
| Haiku 4.5 | $0.00005 | $0.00108 |
Grade A, and why
telegram-output-formatting 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `references/openrouter-credit-check.md` — How to check OpenRouter credit balance (python3 urllib workaround for blocklisted curl auth) How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Telegram Output Formatting
The Rule
Telegram is the memo. The disk is the dossier.
Chat output = short, punchy, scannable.
Full reports = committed to the space's journal (<space>/journal/).
Format Rules
Titles
- Use emojis in section titles: ✅ 🔴 🟢 🟡 📋 🔍 💡 ⚠️
- Titles are SHORT — 2-4 words max
- CAPS for status markers when needed (OK, ERROR, DONE)
Lists
- Use bullet points (•) — NOT hyphens (-)
- One line per item, no nested sub-bullets deeper than one level
- Keep items to a single sentence
Length
- Telegram messages should fit on one phone screen
- Highlights and takeaways only — "what matters, what's next"
- If the output would exceed ~15 lines, write a full report to disk and summarize in chat with a pointer to the file
Structure
A typical task report:
emoji TITLE
• Key finding 1
• Key finding 2
• Key finding 3
Next: what to do about it
For multi-item status reports (cron jobs, task lists):
📋 Header
🟢 Item 1 — status
🔴 Item 2 — status
🟢 Item 3 — status
Summary line
What goes to disk, not chat
- Full methodology and sources
- Raw data dumps (GitHub API responses, scan logs)
- Multi-paragraph analysis
- Reproduction steps for technical issues
- Anything that would make the message scroll past one screen
Save full reports to: <space>/journal/YYYY-MM-DD-topic.md
Group Chat vs DM
In The Firm group chat: even shorter. Phone screen, quick scan.
See the-firm-etiquette for when to respond at all.
In DM with Gregor: the rules above apply.
Why
Gregor reads on a phone. The memo fits on one screen; the dossier lives in the file. Intelligence briefings that dump full analysis into chat are unreadable — the signal drowns in the noise.
Cron Job Deliveries — Executive Summary Format
Cron job responses delivered to Telegram have a stricter format than interactive responses. The user explicitly wants executive summaries, not log dumps.
Rules for cron delivery format:
- Title: "{Job Title} — {Human-friendly date}" (e.g., "Monday, September 22, 2026") — always include the day of the week, never ISO dates
- One-line TL;DR: what was done and the headline finding
- 2-5 bullet points: key findings ranked by importance
- One-line "What to watch" or "Action this week" closing note
- Word limits: 150 for daily jobs, 200 for weekly, 300 for monthly
- If nothing significant happened: respond with exactly
[SILENT]
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.
- 20d ago First seen · 133 lines · 51 tokens per session scan A 2edab49a2cdc
telegram-output-formatting is a skill published in the GitHub repository datacore-one/datacore (4 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 1,077 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-27.
Other skills, from other repositories
deck-ai
Generate modern presentation decks (PDF) from markdown content. Local open-source alternative to Gamma — uses Slidev for layouts and Unsplash for imagery. Invoke when the user asks to "make a deck", "build slides from this", or "turn this into a presentation".
add-pdf-reader
Add PDF reading to Deus agents. Extracts text from PDFs via pdftotext CLI. Handles WhatsApp attachments, URLs, and local files.
wowerpoint
Turn one document into a kawaii NotebookLM slide deck. Use for "wowerpoint this", "make a deck about ", "turn this report into slides", or any request to render a single document as narrative slides.
ppt-analysis
A parser for PowerPoint presentations in .pptx or older .ppt format that extracts their contents and flags slides needing image-based inspection.
pie-chart-data-analysis
A data-analysis workflow for pie charts that reads CSV or Excel files, counts rows across worksheets, and identifies category and numeric columns using built-in rules.
multi-sheet-reading-and-analysis
A workflow for reading and analyzing Excel files with multiple worksheets, including data cleaning, grouping, fitting lines to data, and formatted charts.