A specialist skill for diagnosing and improving slow, unstable, or heavily loaded 1C systems. 1C is business software commonly used for accounting, enterprise operations, and databases, and a technological log records detailed system events.

Use it to investigate slowdowns, hangs, rising load, instability, locking, and database or platform configuration issues in 1C installations.

It replaces guesses about performance problems with measurements from logs, operating-system and database counters, query plans, and database statistics.

How vgtitov/bsl-ai-toolkit configures Claude Code

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-expert/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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/vgtitov/bsl-ai-toolkit/1c-expert/github.svg)](https://agentmods.dev/skills/vgtitov/bsl-ai-toolkit/1c-expert)

Your own site

<a href="https://agentmods.dev/skills/vgtitov/bsl-ai-toolkit/1c-expert"><img src="https://agentmods.dev/badge/skills/vgtitov/bsl-ai-toolkit/1c-expert/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/vgtitov/bsl-ai-toolkit/1c-expert"><img src="https://agentmods.dev/badge/skills/vgtitov/bsl-ai-toolkit/1c-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 457 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,733 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.

Model	Per session	Once invoked
Fable 5.1	$0.00457	$0.02733
Opus 5	$0.00229	$0.01367
Sonnet 5	$0.00091	$0.00547
Haiku 4.5	$0.00046	$0.00273

Measured 10d ago against content hash dd1abd1bdc6d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

1c-expert 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-expert/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Эксперт по технологическим вопросам 1С и высоконагруженным системам

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.

Роль расследователя и оптимизатора: понять, ПОЧЕМУ система 1С работает медленно, нестабильно или не масштабируется, найти корневую причину по измерениям и устранить её. Покрывает компетенции экзамена 1С:Профессионал по техническим вопросам (14 разделов — карта самопроверки в references/investigation-methodology.md). Адаптируется под любой проект — версии платформы/СУБД/ОС НАСТРОЙ ПОД СВОЙ ПРОЕКТ, не хардкодь.

Главное правило: измерь, не угадывай

Нейросеть врёт в деталях 1С (события ТЖ, поля, пороги счётчиков, поведение оптимизатора). Источник истины — инструмент и измерение, не память:

Сначала сними данные — технологический журнал (logcfg.xml), счётчики ОС/СУБД, план запроса, статистика PostgreSQL/MS SQL, замер производительности. Потом делай вывод о причине.
Сначала корневая причина, потом фикс. Симптом «тормозит проведение» ≠ диагноз. Гипотеза (CPU / IO / память / блокировки / сеть) подтверждается данными до того, как что-то менять.
Измеряй ДО и ПОСЛЕ. Любая оптимизация валидируется повторным замером той же ключевой операции (APDEX / время / план / счётчики). Нет замера «после» — работа не закрыта.
Не уверен в детали под конкретную версию платформы/СУБД — помечай [проверить] и сверяйся со справкой ИТС / реальным выводом инструмента, не выдавай за факт.

Технологический журнал — главный инструмент расследования

logcfg.xml собирает события платформы (EXCP, TLOCK, TDEADLOCK, TTIMEOUT, QERR, SDBL, DBMSSQL/DBPOSTGRS, CALL/SCALL и др.); фильтры <event>/<property>, history, location, отбор по свойствам, сбор техдампов (<dump>), планы запросов (<plansql>). Анализ — grep/awk/perl по логам или ЦУП/КИП. Синтаксис, полный список событий, что из каждого извлекать, готовые bash-конвейеры «top-5 длительных запросов/транзакций/ вызовов/ожиданий» — references/tech-journal.md. Правило: на проде собирай ТОЛЬКО нужные события на время расследования (полный журнал быстро забивает диск и тормозит систему).

Read the full file on GitHub · 116 lines

Files

What ships with it

9 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.

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.

10d ago First seen · 116 lines · 457 tokens per session scan A dd1abd1bdc6d

Subscribe to this mod's changes

1c-expert is a skill published in the GitHub repository vgtitov/bsl-ai-toolkit (21 stars, last pushed 3d ago), licensed MIT. It adds 457 tokens to every session and 2,733 once invoked, about $0.0023 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.

1c 1c-enterprise Claude Code Debugging ai bsl claude

1c-skd-validate

A checker for a 1C data composition schema, the XML definition that describes how a report builds and presents data. It checks structure, references, duplicate names, and optionally whether referenced objects exist in the configuration.

Desko77/cursor-1c-skills · 40 tokens

1c-subsystem-validate

A checker for the XML definition of a 1C subsystem. It verifies the subsystem's structure and can compare its listed contents with objects that actually exist in the configuration.

Desko77/cursor-1c-skills · 34 tokens

1c-cfe-validate

A validator for a CFE, the extension format used to modify a 1C configuration, that checks its XML structure and included objects.

Desko77/cursor-1c-skills · 38 tokens

bsl-diagnostic-rule-development

Semantic workflow for implementing, reviewing, or fixing onec-hbk-bsl diagnostic rules. Use for BSL/1C rule semantics, CST or tree-sitter behavior, BSLLS parity, performance, synthetic fixtures, related-rule overlap, and questions about whether a rule matches its documented language behavior.

mussolene/1c_hbk_bsl · 68 tokens

ai-edt

1C:Enterprise development through the AI-EDT MCP server - BSL analysis and editing, metadata and managed forms, query validation, project diagnostics, debugging, infobase updates and unit tests. Use when the project is a 1C:EDT workspace: BSL modules, .mdo metadata, 1C queries, managed forms. Also use when all you…

Desko77/ai-edt · 111 tokens

file-hygiene

A file-format check for 1C files. It checks encoding, hidden byte-order marks, control characters, dash characters, and line-ending consistency.

Romandredan/1c-quality-gate · 104 tokens

bsl-ai-toolkit: Skill for Claude Code