Borrowing it
Nothing to install: this file belongs to maxbarsukov/vkr-builder. 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/maxbarsukov/vkr-builder/master/.claude/skills/vkr-building/SKILL.mdgit 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/skills/maxbarsukov/vkr-builder/vkr-building)<a href="https://agentmods.dev/skills/maxbarsukov/vkr-builder/vkr-building"><img src="https://agentmods.dev/badge/skills/maxbarsukov/vkr-builder/vkr-building/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/maxbarsukov/vkr-builder/vkr-building"><img src="https://agentmods.dev/badge/skills/maxbarsukov/vkr-builder/vkr-building.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 | $0.00061 | $0.00985 |
| Opus 5.5 | $0.00024 | $0.00394 |
| Sonnet 5.5 | $0.00012 | $0.00197 |
| Haiku 4.5 | $0.00006 | $0.00098 |
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 2mo 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Running the build
Call the launcher, not main.py — it finds Python and names itself in the
tool's own hints:
vkr-builder.bat build # Windows
./vkr-builder.sh build # Linux/macOS
python main.py build # only if the launchers cannot be used
build is the default command, so bare vkr-builder.bat builds too.
Commands
| Command | What it does |
|---|---|
build |
merge → lint → document (+ --pdf) |
merge |
only produce the bundle |
docx |
build from an existing bundle |
pdf [docx] |
convert a DOCX to PDF |
preview <file.md> |
build one file, no TOC, next to the source |
lint / stats / validate |
checks and numbers, no document |
diagnose <docx> |
quality report on a finished document |
watch |
rebuild on change (needs watchdog) |
doctor |
what is installed and which engine would be used |
init / profiles / help |
config template, profile list, usage |
Useful flags: --profile NAME, --pdf, --pagination-engine {auto,word,libreoffice},
--skip-merge, --skip-docx, --no-preflight, --diagnose.
Engines
pagination_engine: auto is the default: Word if it is installed (more
accurate for GOST layout), otherwise LibreOffice. The header says which one
was chosen — word engine (auto). Run doctor before blaming a build:
✓ word Word 16
✓ libreoffice /usr/bin/soffice
✓ pagination auto → word · Word 16
A missing engine is a warning there (one of the two is enough); "no layout engine available" is a command failure.
Reading the report
✓ lint no issues 0.2s
▲ 10-appendix-c.md:13 unknown reference [рис:k]
⠹ layout pass 2/3 · fitting tables 6.9s
46% ━━━━━━━━━━━━━━─────────────────── 3/8 tables
✓ build finished in 23s · 1 warning
document example/VKR-example.docx 94 KB
- Steps carry facts and timings; the footer carries the outcome, the counts and the files produced.
- Findings name the source file and line, not the merged bundle.
· N suppressedmeans an@suppressdirective silenced something on purpose. Do not report a run as clean if that number is non-zero.- Verbosity:
-vadds per-step notes,--debugadds the Word/LibreOffice trace,-qprints errors only.
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.
- 2mo ago First seen · 100 lines · 61 tokens per session scan A 78bd5455cf07
vkr-building is a skill published in the GitHub repository maxbarsukov/vkr-builder (9 stars, last pushed 23d ago), licensed MIT. It adds 61 tokens to every session and 985 once invoked, about $0.0002 per session on Opus 5.5. 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
csv-workbench
Analyze CSV files in /mnt/data and return concise numeric summaries.
xberg-extracting-tables
Use when extracting tabular data from PDFs, spreadsheets, or images. Covers layout-aware table detection, table model selection, output formats (markdown / JSON cells), and known limits.
format-specific-extraction
Per-format Xberg extractors (Office XML, PDF, archives, ...): parsers, security budgets, metadata helpers. Use when changing or adding one.
typescript-providers
Implement, modify, test, or document TypeScript provider packages under ts/packages/providers, including framework adapters for OpenAI, Anthropic, Google, LangChain, Mastra, Vercel, LlamaIndex, Cloudflare, Claude Agent SDK, and TypeSafe. Use for provider-specific TS work; do not use for core-only changes.
xlsx
Create polished Excel workbooks for budgets, trackers, and data tables.
docetl
Build and run LLM-powered data processing pipelines with DocETL. Use when users say "docetl", want to analyze unstructured data, process documents, extract information, or run ETL tasks on text. Helps with data collection, pipeline creation, execution, and optimization.