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 heidihelena/citevahti --skill citevahti-onboardinggit clone --depth 1 https://github.com/heidihelena/citevahtiWrote 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/citevahti/citevahti-onboarding)<a href="https://agentmods.dev/skills/heidihelena/citevahti/citevahti-onboarding"><img src="https://agentmods.dev/badge/skills/heidihelena/citevahti/citevahti-onboarding/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/citevahti/citevahti-onboarding"><img src="https://agentmods.dev/badge/skills/heidihelena/citevahti/citevahti-onboarding.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 | $0.00095 | $0.01104 |
| Opus 5 | $0.00048 | $0.00552 |
| Sonnet 5 | $0.00019 | $0.00221 |
| Haiku 4.5 | $0.00010 | $0.00110 |
Grade A, and why
citevahti-onboarding 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CiteVahti onboarding — per-channel quickstart generation
One product, several doors: desktop app, .mcpb in Claude Desktop, MCP stdio in Claude
Code / other clients, VS Code extension, plain pip + panel. Each door needs its own
first-ten-minutes doc, and those docs rot every release. This skill regenerates them
from the shipped truth instead of from memory.
Sequencing gate (from docs/BETA_TO_PRODUCTION.md): hold large doc regeneration
until citevahti-eval and citevahti-release outputs are stable — docs churn before
that is wasted. Fixing a doc that's actively wrong is always in scope.
Triggers
Use when the maintainer asks to: write/refresh a channel quickstart, update
docs/QUICKSTART.md after a release, document a new distribution channel, or check
that channel docs still match the current version.
Do NOT use for: live-helping one user (use docs/QUICKSTART.md +
citevahti-dev's troubleshooting table; on an AI client, the read-only
getting_started tool returns the user's single next step from their real ledger
state), or marketing copy (citevahti-claims audits that; this skill writes
instructions).
Sources of truth — generate FROM these, never from memory
| Fact | Source |
|---|---|
| Install paths + exact commands | docs/QUICKSTART.md (canonical), README.md |
| Channel-specific setup | skills/citevahti-dev/SKILL.md §Setup paths A/B/C |
| What's in the current release | CHANGELOG.md top section, docs/STATUS.md |
| Safety framing users must see | docs/DISCLOSURE.md, docs/KNOWN_LIMITATIONS.md |
| Update path per channel | secure-release §3 (no auto-update; per-surface manual paths) |
Per-channel skeleton
Every channel quickstart contains, in order:
- Who this path is for (one line — e.g. "Mac, no terminal" vs "Claude Code user").
- What CiteVahti is and isn't — reuse the
docs/QUICKSTART.mdboxed paragraph verbatim (human decides; no silent writes; local-first with outbound literature lookups only; beta). Don't paraphrase it — paraphrase is where overclaiming creeps in, andcitevahti-claimsaudits these docs too. - Install — copy-pasteable, nothing to memorize, tested against the current release on that channel.
- First success in ≤10 minutes — one real claim checked end to end, or
citevahti demofor the nothing-real path. - Connect Zotero (optional step, panel-driven) and AI second opinion setup.
- Where things go wrong — link the troubleshooting table; don't fork it.
- How you'll get updates — honest per-channel story: pip upgrade command;
.mcpbremove-and-reinstall; version nudge for the desktop app. Never promise auto-update.
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 · 79 lines · 95 tokens per session scan A 17657be669b8
citevahti-onboarding is a skill published in the GitHub repository heidihelena/citevahti (1 stars, last pushed 6d ago), licensed Apache-2.0. It adds 95 tokens to every session and 1,104 once invoked, about $0.0005 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
ml-paper-writing
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.
idea-bib-review
A writing workflow for drafting a literature review from a research idea and BibTeX files, which are structured records of academic sources. It preserves citation keys and checks whether claims are supported by the supplied evidence.
ml-paper-writing
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.
ml-paper-writing
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, conducting literature reviews, finding related work, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, citation verification workflows, and paper…
econ-management-paper-polish
A writing and editing guide for papers in economics, management, finance, accounting, marketing, information systems, public administration, and related fields.
socsci-paper-orchestrator
An orchestrator for writing Korean social-science research papers with a team of six specialized agents. Social science studies people, organizations, and society; a research paper presents a question, evidence, methods, and conclusions.