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 instructions/maxbarsukov/vkr-builder/agents-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/instructions/maxbarsukov/vkr-builder/agents-md)<a href="https://agentmods.dev/instructions/maxbarsukov/vkr-builder/agents-md"><img src="https://agentmods.dev/badge/instructions/maxbarsukov/vkr-builder/agents-md.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 | $0.00420 | $0.00420 |
| Opus 5 | $0.00210 | $0.00210 |
| Sonnet 5 | $0.00084 | $0.00084 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
vkr-builder AGENTS.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 today.
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
vkr-builder
Собирает выпускную квалификационную работу в DOCX и PDF из файлов Markdown, по требованиям ИТМО (ЛНАОБУЧ-СМК-03-05-2022) и ГОСТ 7.32-2017.
Пользователь здесь пишет свою работу, а не дорабатывает инструмент.
Как себя вести
- Если пользователь здесь впервые — объясните своими словами, что это за инструмент, и
спросите, чего он хочет: посмотреть на готовый пример или начать свою работу.
Не пересказывайте
README.md. - Прежде чем писать или править текст работы, прочитайте
docs/llm-format/— там правила разметки, по которым документ собирается. Текст, написанный не по правилам, не соберётся или соберётся неправильно. - По остальным задачам ищите нужный документ в таблице «Документация» в
README.md. Правите сам инструмент — сначала.github/CONTRIBUTING.md. - Не переоформляйте чужой текст «под себя»: правьте то, о чём попросили.
Собранные
*.docxи*.pdfне редактируются вручную — они результат сборки. - Правила для конкретных ассистентов — в
.claude/skills/и.cursor/rules/; они дополняют этот файл.
Основные команды
./vkr-builder.sh doctor # что нашлось в системе
./vkr-builder.sh build --pdf # собрать DOCX и PDF
./vkr-builder.sh lint # проверить разметку
На Windows — vkr-builder.bat. Полный справочник: docs/cli/.
Перед сборкой прогоняйте lint: ошибки её останавливают, предупреждения — нет.
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.
- today First seen · 33 lines · 420 tokens per session scan A 19f4e8b90aa7
vkr-builder AGENTS.md is an instructions file published in the GitHub repository maxbarsukov/vkr-builder (4 stars, last pushed 2d ago), licensed MIT. It adds 420 tokens to every session, about $0.0021 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 2026-09-04.
Other instructions, from other repositories
go-docs-mcp CLAUDE.md
Instructions for drolosoft/go-docs-mcp, covering go-docs-mcp, build & run, architecture, key decisions and tools.
docsift CLAUDE.md
Instructions for anishmoncivarghese/docsift, covering docsift, key documents (read before making product decisions), commands, architecture (src layout, package docsift) and hard rules.
agentic-resume-builder CLAUDE.md
Claude Code instructions for WtotdeD/agentic-resume-builder, covering agentic-resume-builder development guidelines, what this repo is, active technologies, package manager and validation.
mcp-server-anydoc AGENTS.md
AGENTS.md instructions for ofershap/mcp-server-anydoc, covering mcp-server-anydoc, when to use, install (agent instructions), tools and limits.
md-anything copilot-instructions.md
Instructions for ojspace/md-anything, covering copilot instructions for md-anything, build, test, and lint commands, full suite, contributor-safe required subset and regenerate generated pdf/epub fixtures when needed.
agentic-reviewer AGENTS.md
Instructions for FilippoScaramuzza/agentic-reviewer, covering agentic reviewer — journal paper review framework, project overview, directory structure, workflow and phase 0: setup & paper conversion.