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.
git clone --depth 1 https://github.com/maxbarsukov/vkr-builderWrote 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/rules/maxbarsukov/vkr-builder/vkr-findings)<a href="https://agentmods.dev/rules/maxbarsukov/vkr-builder/vkr-findings"><img src="https://agentmods.dev/badge/rules/maxbarsukov/vkr-builder/vkr-findings/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/rules/maxbarsukov/vkr-builder/vkr-findings"><img src="https://agentmods.dev/badge/rules/maxbarsukov/vkr-builder/vkr-findings.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 | $0.00000 | $0.00881 |
| Opus 5 | $0.00000 | $0.00441 |
| Sonnet 5 | $0.00000 | $0.00176 |
| Haiku 4.5 | $0.00000 | $0.00088 |
Grade A, and why
vkr-findings 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 8d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fixing findings
Findings carry a stable rule name (rule in --json). Fix by rule, not by
wording — the wording changes, the rule does not.
✗ 04-chapter1.md:12 reference [рис:nope] has no matching figure caption
Markdown (lint, and the pre-flight inside build)
| Rule | Fix |
|---|---|
unknown-reference |
add the caption carrying that {key}, or fix the key |
unknown-key |
{key} in a caption/formula is defined nowhere |
duplicate-key |
two objects share a key |
unknown-citation |
cited source missing from the source list |
uncited-source |
listed source nobody cites |
unreferenced-object |
figure/table/listing nothing refers to |
caption-order |
figures: caption after the image; tables/listings: before the block |
caption-spacing |
image and caption on adjacent lines — separate with a blank line |
comma-citation |
[1, 2] → [1; 2] |
spaced-range |
6 - 7 → 6-7; suppress if the spacing is deliberate |
table-columns |
row cell count ≠ header (error, blocks the build) |
long-paragraph, empty-section |
split it / write body text |
structural-heading |
level-1 heading that is not a GOST section name |
numbering-gap |
use {key} numbering instead of explicit numbers |
dictionary-order |
sort abbreviations/terms (or build.sort_dictionary_lists: true) |
appendix-letter |
invalid or repeated appendix letter |
listing-file |
the @listing file did not become a listing |
listing-file covers several causes and the message names which: file not found (the path is relative to listings_dir, or images_dir when that key
is unset — never to the Markdown file), path escapes the listings directory,
no listings directory is configured, a range past the end of the file, a
reversed range, a range starting at 0 where lines count from 1, cannot read
for anything that is not UTF-8 text, and an
is empty warning when the file has no lines. Do not suppress it: the caption
and its number stay, the code does not, and nothing in the document says so.
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.
- 8d ago First seen · 76 lines · 0 tokens per session scan A aafe638fa3f1
vkr-findings is a cursor rule published in the GitHub repository maxbarsukov/vkr-builder (4 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 881 tokens. 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 cursor rules, from other repositories
svelte
You are an expert in Svelte 5, SvelteKit, TypeScript, and modern web development.
frontend
Demo Shop frontend guidance.
write
Writing style guide with AI detection avoidance. For tweets, LinkedIn, blogs, READMEs, commits. Activate with @write.
rulesforconvex
description: Convex guidelines globs: alwaysApply: true.
mcp-tools
MCP tool implementation patterns for Textrawl.
typescript
TypeScript and Node.js conventions for Textrawl.