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.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/instructions/heidihelena/vahtian/claude-md)<a href="https://agentmods.dev/instructions/heidihelena/vahtian/claude-md"><img src="https://agentmods.dev/badge/instructions/heidihelena/vahtian/claude-md/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/instructions/heidihelena/vahtian/claude-md"><img src="https://agentmods.dev/badge/instructions/heidihelena/vahtian/claude-md.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 | $0.01039 | $0.01039 |
| Opus 5 | $0.00519 | $0.00519 |
| Sonnet 5 | $0.00208 | $0.00208 |
| Haiku 4.5 | $0.00104 | $0.00104 |
Grade A, and why
vahtian CLAUDE.md 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 9d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vahtian — repo guide for Claude
Vahtian is a research-integrity toolkit for biomedical researchers (StudyVahti,
CiteVahti, ReviewVahti, …), built by a clinician (MD, PhD). This repo holds the
static marketing site (repo root, one index.html per product, deployed via
Cloudflare — no framework, no build step, zero external requests/trackers) and
the packages (packages/vahtian-py/, packages/vahtian-r/). skill/ at the
repo root is a shipped product artifact (a distributable agent skill), not
internal tooling — don't confuse it with .claude/skills/.
The invariant (applies to every edit, every session)
Vahtian assesses whether a cited source supports a specific claim, and records who decided what — with a human first, AI second, and an auditable trail. It does NOT certify scientific truth, clinical validity, manuscript quality, publication readiness, or the absence of citation problems.
Never write or approve copy that makes AI the judge, certifies truth or
publication readiness, or claims unbenchmarked accuracy. The enforcement skill
is .claude/skills/vahtian-brand-safety/ (full rules + phrase tables); the
canonical marketing-claims document is AD_CLAIMS.md — on conflict,
AD_CLAIMS.md wins.
Which skill for what
| Task | Skill |
|---|---|
| Render / screenshot a page | run-vahtian (driver serves + shoots desktop/mobile PNGs) |
| Find UX problems (diagnose only) | vahtian-ux-auditor |
| Review or write any user-facing copy | vahtian-brand-safety — copy doesn't ship without PASS |
| Edit site HTML/CSS/JS | vahtian-frontend-implementer (smallest coherent change) |
| Add a page / site-wide quality pass | vahtian-site (meta, footer, sitemap, JSON-LD — CI gate: .github/scripts/audit.sh) |
| Release Python/R packages | vahtian-publishing (PyPI Trusted Publishing via .github/workflows/publish.yml) |
| Announce a shipped change (posts, release notes) | vahtian-announcer — drafts + queues; never posts without founder sign-off |
| Edit a copy skill's rules | run node .claude/evals/run.mjs first — CI gate: .claude/evals/ |
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.
- 9d ago First seen · 69 lines · 1,039 tokens per session scan A c8d92d50f0e4
vahtian CLAUDE.md is an instructions file published in the GitHub repository heidihelena/vahtian (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,039 tokens to every session, about $0.0052 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.