bsl-ai-toolkit: Skill for Claude Code

.claude/skills/1c-analyst/SKILL.md

1c-analyst is a skill for Claude Code from vgtitov/bsl-ai-toolkit. It costs 258 tokens per session (2,270 once invoked), scanned A, original, MIT.

An analysis and architecture aid for 1C:Enterprise projects, a platform used for business applications. It studies real code and configurations to explain what a requested change affects, then prepares a technical specification or architecture decision.

In plain words
What is it for?
Use it to analyse a business request, map related databases and functions, define data and behaviour, identify affected areas, and write acceptance criteria.
Why use it?
It prevents requirements from being based on assumptions about how the 1C system works. It checks both the main configuration and connected extensions, and marks unverified ideas clearly.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is vgtitov/bsl-ai-toolkit's own configuration. It tells Claude Code how to work on bsl-ai-toolkit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything bsl-ai-toolkit configures →

Reuse

Borrowing it

Nothing to install: this file belongs to vgtitov/bsl-ai-toolkit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/vgtitov/bsl-ai-toolkit/main/.claude/skills/1c-analyst/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/vgtitov/bsl-ai-toolkit

Made for: Claude Code.

Wrote 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.

agentmods badge for 1c-analyst

README.md
[![agentmods](https://agentmods.dev/badge/skills/vgtitov/bsl-ai-toolkit/1c-analyst/github.svg)](https://agentmods.dev/skills/vgtitov/bsl-ai-toolkit/1c-analyst)
Your own site
<a href="https://agentmods.dev/skills/vgtitov/bsl-ai-toolkit/1c-analyst"><img src="https://agentmods.dev/badge/skills/vgtitov/bsl-ai-toolkit/1c-analyst/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.

agentmods 80×15 button for 1c-analyst

Your own site · 80×15
<a href="https://agentmods.dev/skills/vgtitov/bsl-ai-toolkit/1c-analyst"><img src="https://agentmods.dev/badge/skills/vgtitov/bsl-ai-toolkit/1c-analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 258 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,270 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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 content
    Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00258 $0.02270
Opus 5 $0.00129 $0.01135
Sonnet 5 $0.00052 $0.00454
Haiku 4.5 $0.00026 $0.00227

Measured 10d ago against content hash 4d5e525af569, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

1c-analyst 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 10d 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.

.claude/skills/1c-analyst/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Анализ и архитектура 1С

Локализация (сначала, если есть)

Если в скилле есть каталог references/local/ — прочитай его ПЕРЕД работой: version-stack.md (версии платформы/библиотек, режим совместимости, префиксы ТВОЕЙ компании) и остальные карты. При противоречии локальное побеждает generic. Контракт — docs/SKILL_LOCALIZATION.md toolkit.

Скилл аналитика/архитектора: понять задачу и контур, что с чем связано, что затронет изменение, и подготовить ЧТЗ/архитектурное решение так, чтобы дальше тех-лид и dev-фаза (1c-dev) превратили это в атомарные задачи и код.

Железное правило анализа

  1. Контур = конфигурация (основа) + подключённое расширение. Искать функционал в ОБОИХ слоях.
  2. Проверять по РЕАЛЬНОМУ коду через MCP (find_object/search/read_module), не по памяти. Нет в коде — так и скажи, гипотезу помечай [проверить].
  3. Слой не загружен в MCP-индекс → это «не загружено», НЕ «функционала нет».

Роли и границы

  • Аналитик — владелец бизнес-смысла: проблема/потребность, ожидаемое поведение, границы, логическая модель данных, бизнес-ошибки и запреты, критерии приёмки. НЕ описывает реализацию.
  • Архитектор — границы и ограничения целевой архитектуры; «архитектурное решение = СТАТУС принятия тех-проекта»; ADR при неопределённости. Подключается при риске/влиянии на архитектуру.
  • Соседние: тех-лид пишет тех-проект/контракты и дожимает технику; разработчик + 1c-dev превращают артефакт в атомы и код. Контуры аналитики и разработки независимы, связаны через артефакты + трекер; уточнение требований в процессе реализации = возврат в аналитический контур.

Контуры и базы — карта в данных локализации

Карта контуров вынесена в данные, не в тело скилла: config/contours.example.md (generic-шаблон) → СВОЙ файл в локализации (config/contours.<org>.md). Там: какие конфигурации/базы, какие слои (конфигурация + расширения), что с чем связано, риски переноса, слепые зоны, незагруженные слои. Заполняется по РЕАЛЬНОМУ коду (оба слоя) и держится согласованным со scope-группами из config/layers.*.toml (машинная раскладка слоёв для поиска). Так локализация под организацию = обновить данные, а не править скилл/движок. Шаблон конвенций слоёв для dev — в 1c-dev (references/conventions-template.md).

Read the full file on GitHub · 99 lines

Changes

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.

  1. 10d ago First seen · 99 lines · 258 tokens per session scan A 4d5e525af569

Subscribe to this mod's changes

1c-analyst is a skill published in the GitHub repository vgtitov/bsl-ai-toolkit (21 stars, last pushed 3d ago), licensed MIT. It adds 258 tokens to every session and 2,270 once invoked, about $0.0013 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 2026-08-30.