1c Code Search logo

1c Code Search

Community
comol
1c-code-search

Find BSL code in a 1C project — routines by name, code by behaviour or exact literal, module layout, members of a context — through the graph and code-metadata MCP servers before any Grep. Use whenever a task needs to locate or read a fragment of BSL it does not yet have a path for.

Overview

Publishercomol
Repositoryai_rules_1c
Skill name1c-code-search
Stars
496
Forks
112
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by comol on GitHub. Read the source before you install it.

Installation

Install the 1c Code Search AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/comol/ai_rules_1c/tree/main/content/skills/1c-code-search
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/comol/ai_rules_1c.git /tmp/ai_rules_1c
mkdir -p .claude/skills
cp -r /tmp/ai_rules_1c/content/skills/1c-code-search .claude/skills/1c-code-search
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable 1c Code Search in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads 1c Code Search on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so 1c Code Search is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

1c-code-search — locate BSL code

Project-source search is MCP-first within verified contour coverage: graph → mapped code-metadata → scoped native Grep after a bounded miss with a one-line fallback note. Skip uncovered lanes; never substitute a neighboring contour's index. content/rules/multi-contour-search.md selects scope and server mappings for multiple roots; content/rules/mcp-first-search.md owns retrieval, freshness and native exceptions. This skill owns the calls below; any shared-server scope arguments must match its live contract.

Tools and exact arguments

Every graph call below includes the returned project_id matched to the current source roots; <resolved-project-id> in examples must be substituted, never sent literally. Discover via list_graph_projects using the mcp-1c-tools router before this skill when needed. Verify the relevant extension layer and response attribution. Code-server scope comes from its own live schema/mapping; do not copy graph arguments into it. Contract and ambiguity handling — content/rules/multi-contour-search.md.

NeedCallArguments (exact names)
Code by behaviour / intentsearch_code (graph)query, search_type="semantic", detail_level="L1", top_k=3, optional filter_type
Code by identifier / literalsearch_code (graph)query, search_type="fulltext"; miss → codesearch(query, limit=5)
Hybrid fallbackcodesearch (code)query, limit=5 — result count is limit, never top_k
Routine by namesearch_function (code)name, exact=true, limit=10, optional module_path
Full routine bodysearch_codedetail_level="L0" for one routine; or compact_symbol(name, include_body=true)
Module layout before editingget_module_structure (code)module_path
Members of a contextbsl_scope_members (code)context (Справочник.Номенклатура, Глобальный), member_type="all" | "methods" | "properties" | "events"

Text searches above use query; routine lookup uses name. Do not invent q, text, prompt or search_query.

Calls

json
{"tool": "search_code", "args": {"project_id": "<resolved-project-id>", "query": "расчёт остатков по складу на дату", "search_type": "semantic", "detail_level": "L1", "top_k": 5}}
{"tool": "search_function", "args": {"name": "ОбработкаПроведения", "exact": true, "limit": 10}}
{"tool": "codesearch", "args": {"query": "ТекущаяДатаСеанса()", "limit": 5}}
{"tool": "get_module_structure", "args": {"module_path": "Documents/РеализацияТоваровУслуг/Ext/ObjectModule.bsl"}}

Miss handling

  1. Reformulate once when useful, using only that tool's modes and parameters (search_type, detail_level, top_k / limit, filter_type, module_path).
  2. Current Code search tools have no grep input. Read search_layer: "grep" as the server's internal file-scan fallback, not a request to resend the call. If an indexed search misses a literal, continue to scoped native search after the bounded attempt.
  3. A typed server answer maps to an action by code — content/rules/mcp-policy.md → C. Server answers → actions; never probe the same gap through sibling tools.
  4. Then native Grep / Read, with the note. Reading a file already located here is normal work.

Rare modes, response shapes, compact API paging: content/skills/mcp-1c-tools/docs/1c-code-metadata-mcp.md, content/skills/mcp-1c-tools/docs/1c-graph-metadata-mcp.md.

Frequently asked questions

What does the 1c Code Search AI skill do?

Find BSL code in a 1C project — routines by name, code by behaviour or exact literal, module layout, members of a context — through the graph and code-metadata MCP servers before any Grep. Use whenever a task needs to locate or read a fragment of BSL it does not yet have a path for.

Why use 1c Code Search on TypingMind?

Because you install it once and use it with any model. 1c Code Search is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install 1c Code Search in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/comol/ai_rules_1c/tree/main/content/skills/1c-code-search. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use 1c Code Search?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with 1c Code Search?

As many as you like. As long as a model supports skills, you can use 1c Code Search with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the 1c Code Search AI skill free?

It is published on GitHub by comol. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇