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 agentmods add rules/maxbarsukov/vkr-builder/vkr-buildinggit 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-building)<a href="https://agentmods.dev/rules/maxbarsukov/vkr-builder/vkr-building"><img src="https://agentmods.dev/badge/rules/maxbarsukov/vkr-builder/vkr-building.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00588 |
| Opus 5 | $0.00000 | $0.00294 |
| Sonnet 5 | $0.00000 | $0.00118 |
| Haiku 4.5 | $0.00000 | $0.00059 |
Grade A, and why
vkr-building scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Running vkr-builder
Use the launcher, not main.py — it locates Python and names itself in the
tool's hints:
vkr-builder.bat build # Windows
./vkr-builder.sh build # Linux/macOS
build is the default command. Others: merge, docx, pdf, preview <file.md>, lint, stats, validate, diagnose <docx>, watch,
doctor, init, profiles, help.
Common flags: --profile NAME, --pdf, --pagination-engine {auto,word,libreoffice}, --skip-merge, --skip-docx, --no-preflight,
--diagnose, -v, --debug, -q, --json.
Engines
auto is the default: Word when installed, else LibreOffice. The report
header says which was chosen (word engine (auto)); doctor lists both and
what would be picked. A missing engine is only a warning there — "no layout
engine available" is the failure.
Reading the report
- Steps carry facts and timings, the footer carries the outcome and the files produced.
- Findings name the source markdown file and line, never
_bundle.md. · N suppressedmeans@suppresssilenced something deliberately — a run with a non-zero count is not "clean".- Exit codes:
0success,1the command failed,2bad command line.
For scripts
docx=$(./vkr-builder.sh build -q) # stdout: produced paths
./vkr-builder.sh lint --json | jq '.findings[]'
--json emits the whole report — steps with timings, findings with rule and
location, artifacts with sizes, result — on stdout.
Docker
docker build -t vkr-builder .
docker run --rm -v "$PWD/example:/work/example" vkr-builder build --pdf
No Word in the image, so auto resolves to LibreOffice.
Never
- edit or commit
_bundle.md,*.preview.docx; - hand-edit generated DOCX or PDF; rebuild it.
- add
--no-preflightto get past lint errors — fix the markdown; - call a run successful when its footer shows
✗or the exit code is not 0.
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.
- 5d ago First seen · 66 lines · 0 tokens per session scan A 49d6dc4b0fa3
vkr-building is a cursor rule published in the GitHub repository maxbarsukov/vkr-builder (4 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 588 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.