comol/ai_rules_1c/1c-code-search

Claude Code and agent skill by comol/ai_rules_1c

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

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.

Install

npx vskill@latest install comol/ai_rules_1c/1c-code-search

SKILL.md

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.

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/comol/ai_rules_1c/1c-code-search/badge)](https://verified-skill.com/skills/comol/ai_rules_1c/1c-code-search)

Something wrong with this skill or its page? Tell us.