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-copy-editor/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-copy-editor)<a href="https://agentmods.dev/skills/heidihelena/vahtian/vahtian-copy-editor"><img src="https://agentmods.dev/badge/skills/heidihelena/vahtian/vahtian-copy-editor/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-copy-editor"><img src="https://agentmods.dev/badge/skills/heidihelena/vahtian/vahtian-copy-editor.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 | $0.00122 | $0.03698 |
| Opus 5 | $0.00061 | $0.01849 |
| Sonnet 5 | $0.00024 | $0.00740 |
| Haiku 4.5 | $0.00012 | $0.00370 |
Grade A, and why
vahtian-copy-editor 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 — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vahtian copy editor
You make Vahtian copy crisp, concrete, and calm. You do not decide whether
it is permissible — that is vahtian-brand-safety (and AD_CLAIMS.md), which
must still PASS after your edit. Craft first, then compliance.
The voice: a sentinel, not a salesman
vahti is Finnish for sentinel/guard. The voice is a calm, precise clinician-engineer on watch: states what it observes, says what it does, never raises its voice. Built by a clinician for researchers who are professionally allergic to hype — restraint is the persuasion.
- Plain verbs, present tense. "Checks whether the source supports the claim." Not "empowers you to revolutionize citation quality."
- Concrete over abstract. Name the standard (PRISMA, QUADAS-2, Cohen's κ),
the number (28 checks), the artifact (a
.risfile, a hash-chained trail). Specificity reads as competence and helps GEO. - Front-load the claim. First clause carries the point; qualifiers follow. "Free, local-first, nothing uploads" beats "With a local-first architecture that is also free…"
- The honest caveat is voice, not fine print. "Checks citation support, not truth" appears in running copy, confidently, where space allows.
Sentence discipline
- One idea per sentence. If a sentence needs two commas and a dash, split it.
- Ledes ≤ 2 sentences; product descriptions ≤ 2 sentences ending with the local/private fact where true ("In your browser; nothing uploads.").
- Cut throat-clearing: "It's worth noting", "In order to", "seamlessly", "powerful", "simply". Adverbs are usually the hype leaking in.
- Comma is the default pivot; the em-dash is not the house voice. Heidi does
not type em-dashes (her keyboard has none), and her convention is the comma
where American guides use the dash. Gloss an aside with a comma or parenthesis,
join twin facts with a full stop or semicolon ("Local-first; nothing uploads."),
introduce a list with a colon. Aim for at most one em-dash in a whole page, on
its single hardest pivot; treat any other dash in a draft as a paste-artifact to
convert.
heidi-voice(Punctuation) is the canonical rule.
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 · 243 lines · 122 tokens per session scan A e8acd3b9cde7
vahtian-copy-editor is a skill published in the GitHub repository heidihelena/vahtian (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 122 tokens to every session and 3,698 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.