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 skills add Desko77/cursor-1c-skills --skill claude-md-bootstrapgit clone --depth 1 https://github.com/Desko77/cursor-1c-skillsWrote 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/desko77/cursor-1c-skills/claude-md-bootstrap)<a href="https://agentmods.dev/skills/desko77/cursor-1c-skills/claude-md-bootstrap"><img src="https://agentmods.dev/badge/skills/desko77/cursor-1c-skills/claude-md-bootstrap/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/desko77/cursor-1c-skills/claude-md-bootstrap"><img src="https://agentmods.dev/badge/skills/desko77/cursor-1c-skills/claude-md-bootstrap.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 | $0.00006 | $0.01982 |
| Opus 5 | $0.00003 | $0.00991 |
| Sonnet 5 | $0.00001 | $0.00396 |
| Haiku 4.5 | $0.00001 | $0.00198 |
Grade A, and why
claude-md-bootstrap 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 7d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude-md-bootstrap
Создает проектный CLAUDE.md в корне проекта - авто-загружаемый каждую сессию контекст для агента:
железные правила-грабли, протокол работы, указатели на доки и память. Цель - чтобы агент был
эффективен в проекте сразу, без переоткрытия граблей, и чтобы документация поддерживалась ПО ХОДУ
работы, а не постфактум.
Методика заимствована из opencode-скила project-bootstrap
(https://github.com/dimkurilo/opencode-skills/tree/main/skills/project-bootstrap) и адаптирована под
Claude Code: CLAUDE.md вместо AGENTS.md, память проекта (~/.claude/projects/<proj>/memory/)
вместо .agents/, без модельных профилей (DeepSeek/GLM) и без GRACE-якорей. Что заимствовано
дословно: Variant E (правила в primacy + recency против "Lost in the Middle"), классификация проекта,
режим расширения, contradiction check, progressive disclosure, лимит "не больше 2 вопросов".
Когда этот скил, а когда встроенный /init
/init- дженерик: сводка кодовой базы в CLAUDE.md. Используй, если нужен просто обзор кода.- Этот скил - опинионейтед агент-контекст: правила-грабли как IF-THEN, протокол, primacy/recency, "док как часть работы". Используй, когда проект сложный и нужен надежный контекст для агента.
- Можно комбинировать: сначала
/initдля черновой архитектуры, затем этот скил для структуры и правил.
Workflow
Фаза 0: Классификация + режим
- Тип проекта (определи по файлам, НЕ спрашивай):
| Тип | Сигналы |
|---|---|
code |
исходники (py/ts/js/go/...), тесты, CI |
ops |
Docker, SSH, .env, nginx, продакшен-риски |
agent |
скиллы, промпты, агенты, модели |
content |
статьи, briefs, Excel, документы |
Приоритет гибридов: ops > code > agent > content.
-
Режим:
ls CLAUDE.mdв корне. Если есть -> РЕЖИМ РАСШИРЕНИЯ (дополнять, не перезатирать; сохранить ручные правки пользователя, добавить недостающие секции). -
Загрузи контекст (Read/Glob/Grep, без вопросов):
README*,docs/**, корневые конфиги.git log --oneline -30и багфиксы - источник граблей.- Память проекта:
~/.claude/projects/<кодированный-путь>/memory/MEMORY.md(если есть). - Глобальный
~/.claude/CLAUDE.mdи~/.claude/rules/*- чтобы НЕ дублировать и не конфликтовать.
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.
- 7d ago First seen · 139 lines · 6 tokens per session scan A 3ed5d1b49d00
claude-md-bootstrap is a skill published in the GitHub repository Desko77/cursor-1c-skills (55 stars, last pushed 8d ago), licensed MIT. It adds 6 tokens to every session and 1,982 once invoked, about $0.0000 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 2026-09-03.
Other skills, from other repositories
meeting-to-tasks
A workflow that turns a meeting recording into a task list and separate development plans for tasks that require code.
composing-1c-queries
A guide for writing queries in the 1C:Enterprise query language. It covers how to select, filter, join, group, and summarize data from 1C catalogs, documents, and registers.
humanize-ai-text
A writing aid for rewriting text produced by language-model agents into a more natural human style. It keeps the original meaning, facts, numbers, and technical terms.
transcribe
A tool for turning video and audio recordings into written text, with optional speaker identification and video analysis.
1c-form-compile
A builder for managed 1C forms, the screens users work with in the 1C business-software platform. It creates the Form.xml file from a JSON description or from an object's metadata.
1c-web-test
A browser-automation tool for testing the 1C:Enterprise web client. It uses scripted actions to navigate screens, fill forms, read tables and reports, and apply filters.