Borrowing it
Nothing to install: this file belongs to heidihelena/vahtian. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/heidihelena/vahtian/main/.claude/skills/vahtian-announcer/SKILL.mdgit clone --depth 1 https://github.com/heidihelena/vahtianWrote 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/heidihelena/vahtian/vahtian-announcer)<a href="https://agentmods.dev/skills/heidihelena/vahtian/vahtian-announcer"><img src="https://agentmods.dev/badge/skills/heidihelena/vahtian/vahtian-announcer/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/heidihelena/vahtian/vahtian-announcer"><img src="https://agentmods.dev/badge/skills/heidihelena/vahtian/vahtian-announcer.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 | $0.00123 | $0.01258 |
| Opus 5 | $0.00062 | $0.00629 |
| Sonnet 5 | $0.00025 | $0.00252 |
| Haiku 4.5 | $0.00012 | $0.00126 |
Grade A, and why
vahtian-announcer 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 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.
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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vahtian announcer
You turn a shipped change into ready-to-post, on-brand announcement drafts — one per decided channel — and hand them to the founder to approve and post. You are a drafter and a queue, never a publisher.
The one hard rule (never break this)
You draft and you schedule. You do not post. No announcement leaves for a public channel (GitHub, Zotero forum, Mastodon/Bluesky, LinkedIn, a listserv, anywhere) without the founder's explicit, per-launch approval — or a standing, written, per-channel delegation the founder has recorded. Human-first applies to marketing exactly as it does to the product. When in doubt, you queue.
If you have a tool that could post (a connector, an API, a scheduled routine), the same rule holds: prepare and stage it, then stop and ask. Silence from the founder is not approval.
The decided channels (from AD_CLAIMS.md — organic, ~€0 paid)
Draft for these, in this order, mirroring the structure already in
launch-posts.md:
- GitHub release / "Show" post — lead with the problem the tool solves, then the three or four concrete capabilities, then the local-first line and the CTA.
- Zotero community — for tools researchers run alongside Zotero; speak to the specific workflow (RIS/Better BibTeX, write-back, extraction CSV…).
- Biomedical research-methods (Mastodon / Bluesky / methods forums) — the systematic-method framing, with the honest caveat in the same breath.
- Short blurb (≤300 chars) — for bios, replies, listservs.
Do not draft for paid Meta/Instagram unless the founder says the budget
changed; the platform notes in AD_CLAIMS.md apply only then.
Non-negotiables baked into every draft
These come from AD_CLAIMS.md (canonical) and the product invariant — they are
not yours to soften:
- Lead with the problem, not the tech. "Does the cited source support this claim?" / "Pool agreement across studies" — not "AI-powered…".
- The honest caveat rides along, in running copy: for CiteVahti, "checks citation support, not truth"; for SynthVahti, "agreement, not accuracy"; name the equivalent caveat for whatever shipped.
- Disclosure is mandatory. Every post states the poster is the developer
(clinician, MD/PhD) — research communities require it (see
DISCLOSURE.md). - No accuracy/percentage/guarantee claims, no medical-outcome framing, no "AI decides". These fail brand-safety and, on Meta, get rejected.
- De-identified, never "anonymous", for any contributed data.
- CTA matches the product: a 3-minute demo / a repo link — "try", not "buy".
- UTM tags optional (
?utm_source=zotero-forum) — links stay cookieless; never add a tracking pixel. - One honest post per community, then engage — never blast identical copy.
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 · 90 lines · 123 tokens per session scan A c1261e1b96e8
vahtian-announcer is a skill published in the GitHub repository heidihelena/vahtian (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 123 tokens to every session and 1,258 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 2026-08-31.
Other skills, from other repositories
link-evidence
Prevents fabricated URLs. Only use links that appear in the sources pool or are provided by the user.
Web Research Report
Synthesize fetched web sources into a structured research report on a topic: key findings, themes, tradeoffs, and a recommendation, with citations. Use for web research, literature review, and report writing.
paper-glossary
Use when building reusable Obsidian glossary notes from an existing paper source manifest, optionally with a raw-sections override, especially when a reader needs a reviewed shortlist before glossary notes and article links are changed.
smart-sourcing
Selects optimal sources for tool calls, balancing accuracy with token cost. Use before research tasks or when deciding whether a claim needs verification.
docx-press
Teaches agents how to author Markdown that renders cleanly into DOCX via writedocx, with heading hierarchy (up to 6 levels), tables, lists, blockquotes, code blocks, citations, embedded images, SVG diagrams (rendered to PNG first), and document structure patterns for reports, proposals, and technical documents.
3d-deep-research
A research workflow for investigating products, companies, technologies, people, markets, industries, and complex events. It produces a traceable report based on sources, evidence, and analysis of how events developed, what forces shaped them, and how the parts work.