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 skills/zevtos/agentpipe/gost-reportnpx skills add zevtos/agentpipe --skill gost-reportgit clone --depth 1 https://github.com/zevtos/agentpipeWrote 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/zevtos/agentpipe/gost-report)<a href="https://agentmods.dev/skills/zevtos/agentpipe/gost-report"><img src="https://agentmods.dev/badge/skills/zevtos/agentpipe/gost-report.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 5.1 | $0.00175 | $0.06906 |
| Opus 5 | $0.00088 | $0.03453 |
| Sonnet 5 | $0.00035 | $0.01381 |
| Haiku 4.5 | $0.00017 | $0.00691 |
Grade B, and why
gost-report scanned grade B with 1 finding 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 6d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
brew install graphviz # или: sudo apt install graphviz — для диаграмм (бинарь dot) How it starts
The opening of the file, as written. The whole thing — 360 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GOST report generator
⛔ Правило №1 — приоритет выше всего остального
Никогда не пиши длинное (—) или среднее (–) тире в тексте отчёта. Ни в одном тексте, который ты передаёшь в r.text(...), r.task(...), r.h1/h2/h3(...), r.numbered([...]), r.bullet([...]), в caption у r.figure/r.table, и в ячейках таблиц. Это правило важнее любых стилистических соображений — даже если ИИ-«хороший вкус» подсказывает, что тире здесь к месту, не ставь его.
Вместо тире: между словами — запятая или точка с запятой («Москва, столица России»); в диапазонах — дефис (1-5); прямую речь и тире-связку переписывай. Санитайзер дублирует замену (—→, , —→-), но пиши сразу без тире. Авто-санитайз покрывает прозу, ячейки таблиц и текст графиков r.plot.* (легенда labels=, xlabel/ylabel, label опорных линий, text аннотаций) — он запекается в PNG, поэтому чистится у источника. Валидатор _check_dashes дополнительно сканирует ячейки таблиц и жёстко падает на тире в них (см. references/api.md).
Без «ИИ-тона». Живой русский, без канцеляризмов, лишних кавычек и шаблонов. Не пиши: «В ходе выполнения работы…», «В результате проведённого исследования…», «Данный / вышеуказанный…», «является / представляет собой…», «Стоит отметить…», «Таким образом, можно сделать вывод…». Коротко по делу: «Команда ls -la показывает все файлы» вместо «Для решения данной задачи была применена команда…».
Исключения (тут тире и формулировки ставит сама библиотека — не трогай): авто-подписи «Рисунок N — …» / «Таблица N — …» (твой caption уже очищен), канонические заголовки («Введение», «Заключение», «Список использованных источников»), прямые цитаты.
When to use
Любая русскоязычная академическая работа по ГОСТ: лабораторная, отчёт по практике, курсовая/курсовой проект, ВКР, домашнее задание/РГР. Не используй для презентаций, не-ГОСТ-документов, нерусских работ.
Quickstart
Запускай билд командой gr (ставится на PATH установщиком вместе со скиллом):
What ships with it
37 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- LICENSE 1.0 KB
- references/api.md 24 KB
- references/formulas.md 6.6 KB
- references/patterns.md 4.7 KB
- references/profiles.md 5.9 KB
- references/templates/build.py 2.5 KB runs code
- references/templates/gost-report.env.example 1.5 KB
- scripts/_paths.py 4.9 KB runs code
- scripts/cli.py 2.9 KB runs code
- scripts/config.env.example 3.0 KB
- scripts/core_api.py 6.4 KB runs code
- scripts/ensure_env.py 14 KB runs code
- scripts/example_lab.py 3.5 KB runs code
- scripts/example_other_university.py 3.2 KB runs code
- scripts/gost_report_bib/__init__.py 811 B runs code
- scripts/gost_report_bib/format.py 4.6 KB runs code
- scripts/gost_report_bib/module.py 5.3 KB runs code
- scripts/gost_report_diagrams/__init__.py 629 B runs code
- scripts/gost_report_diagrams/backends.py 1.8 KB runs code
- scripts/gost_report_diagrams/module.py 5.1 KB runs code
- scripts/gost_report_math/__init__.py 412 B runs code
- scripts/gost_report_math/_omml.py 25 KB runs code
- scripts/gost_report_math/module.py 3.7 KB runs code
- scripts/gost_report_viz/__init__.py 558 B runs code
- scripts/gost_report_viz/charts.py 18 KB runs code
- scripts/gost_report_viz/module.py 12 KB runs code
- scripts/gost_report_viz/style.py 3.6 KB runs code
- scripts/gost_report_xref/__init__.py 726 B runs code
- scripts/gost_report_xref/module.py 4.3 KB runs code
- scripts/gost_report.py 73 KB runs code
- scripts/new_module.py 5.6 KB runs code
- scripts/registry.py 3.3 KB runs code
- scripts/requirements.d/viz.txt 631 B
- scripts/requirements.txt 40 B
- scripts/test_sanitize_integration.py 14 KB runs code
- scripts/test_viz.py 28 KB runs code
- scripts/validate.py 26 KB runs code
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.
- 6d ago First seen · 360 lines · 175 tokens per session scan B d252db33b8a1
gost-report is a skill published in the GitHub repository zevtos/agentpipe (11 stars, last pushed 2mo ago), licensed MIT. It adds 175 tokens to every session and 6,906 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
baoyu-youtube-transcript
Downloads YouTube video transcripts/subtitles and cover images by URL or video ID. Supports multiple languages, translation, chapters, and speaker identification. Caches raw data for fast re-formatting. Use when user asks to "get YouTube transcript", "download subtitles", "get captions", "YouTube字幕", "YouTube封面"…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
gog-slides
Google Slides operations through gog.