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-publishing/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-publishing)<a href="https://agentmods.dev/skills/heidihelena/vahtian/vahtian-publishing"><img src="https://agentmods.dev/badge/skills/heidihelena/vahtian/vahtian-publishing/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-publishing"><img src="https://agentmods.dev/badge/skills/heidihelena/vahtian/vahtian-publishing.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 | $0.00130 | $0.02187 |
| Opus 5 | $0.00065 | $0.01094 |
| Sonnet 5 | $0.00026 | $0.00437 |
| Haiku 4.5 | $0.00013 | $0.00219 |
Grade A, and why
vahtian-publishing 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vahtian — publishing Python (PyPI) + R (CRAN / R-universe) from the monorepo
Both packages live in subdirectories of heidihelena/vahtian (the static site is
at the repo root): packages/vahtian-py/ and packages/vahtian-r/ (R package name
TBD — vahtian for brand parity, or vahtianR per the epinet convention). Same flagship
name, same freeze/verify/audit core, byte-identical content_hash — so the headline
CI gate is a cross-language parity test, not just two independent test suites.
Tags below: [do] (adopt — high impact-to-effort for a solo maintainer) · [over] (real but disproportionate for a solo, no-team product — skip for now).
A. PyPI — Trusted Publishing (no stored tokens)
The whole point: no API tokens in the repo. GitHub Actions authenticates to PyPI via OIDC; PyPI mints a project-scoped token valid for only ~15 minutes, so nothing leakable persists.
One-time setup — the workflow already exists; verify the PyPI side matches it:
- On PyPI → your account → Publishing → Add a pending publisher (GitHub). A pending
publisher lets you reserve a not-yet-existent project; it auto-converts to a normal
trusted publisher on the first successful publish — no manual first upload needed. Fields
(must match the committed workflow exactly — PyPI matches on the literal filename):
- PyPI Project Name:
vahtian - Owner:
heidihelena - Repository name:
vahtian(this monorepo) - Workflow name:
publish.yml(filename only — the committed workflow at repo-root.github/workflows/publish.yml) - Environment name: leave blank —
publish.ymlcurrently sets noenvironment:. If you later add a protected GitHub Environment ([do], gates who/what can publish), addenvironment: pypito the publish job and set the same name on the PyPI publisher — the two must agree or the publish is rejected.
- PyPI Project Name:
- Repeat on test.pypi.org for dry-runs (separate pending publisher).
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 · 120 lines · 130 tokens per session scan A 81106029082e
vahtian-publishing is a skill published in the GitHub repository heidihelena/vahtian (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 130 tokens to every session and 2,187 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
citevahti-release
Use when shipping a CiteVahti release — cutting a version, checking feature parity across the MCP server, desktop extension (.mcpb), loopback panel, and VS Code extension, bumping versions in lockstep, writing the changelog entry, minting the release DOI, or preparing rollback notes. Maintainer-facing. Runs the…
bump
Use when bumping Wheeler version after shipping features. Trigger when user says 'bump version', 'release', 'cut a release', 'version bump', 'update version', or after a set of features have been committed and the user wants to formalize a new version.
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.