comol/ai_rules_1c/1c-impact
Claude Code and agent skill by comol/ai_rules_1c
- community
Checking that the SKILL.md file is still in the repository.
Usages, dependencies, call chains and change impact of 1C objects and routines — callers, downstream breakage, register movements, extension changes — via the graph MCP with code-metadata fallback. Mandatory before renames, removals, refactoring and public-contract changes (Gate 4).
Install
npx vskill@latest install comol/ai_rules_1c/1c-impactSKILL.md
1c-impact — usages, call graph, change impact
Evidence for content/rules/verification-gates.md → Gate 4 and for the pre-refactor analysis of content/rules/tooling-playbooks.md → Refactoring. Refactoring blind when these servers are exposed is a defect; when they are not, follow Gate 4 graceful degradation.
All graph project-data calls require the explicit returned project_id bound to the current roots; substitute <resolved-project-id> in the examples. Reuse it for searches, impact, evidence and pagination, with verified layer provenance for an extension. Follow the live schema for tools without this selector and for code-server scope; use verified fixed/session/entity scope or another scoped route, never invent arguments (content/rules/multi-contour-search.md).
Tools and exact arguments
| Need | Call (graph first) | Fallback (code) | |||
|---|---|---|---|---|---|
| What breaks if the object changes | trace_impact(object_name, direction="downstream", depth=3, relationship_types?) | `graph_dependencies(object_name, direction="both" \ | "forward" \ | "reverse", limit=50)` | |
| Who calls / what is called | `trace_call_chain(routine_name, object_name?, direction="callers" \ | "callees", depth=3)` | get_method_call_hierarchy(method_name, direction="both", depth=3) | ||
| Attributes that reference an object | find_usages_of_object(object_name) | graph_dependencies(..., direction="reverse") | |||
| Objects that use a type | find_objects_using_object(object_name) | same | |||
| Documents declaring movements into a register | find_register_movement_docs(register_name) or get_register_writers(register, direction="incoming") | codesearch(query="Движения.<Регистр>") (source evidence only) | |||
| Direct BSL access / targets shared by several objects | find_object_referrers(object_name?, access?, min_referrers=1); access="read" / "write", omit for both | Bounded codesearch then scoped native source search | |||
| Release-level transitive impact | affected_subgraph(roots, max_depth?, direction?, edge_types?) with entity references from resolve_graph_entity | — |
Object/call tools use object_name, routine_name, register_name, method_name; get_register_writers instead uses register / document. Do not invent aliases. Recorder movements and direct BSL access are separate relations: an independent register can have no recorders but still have BSL writers. find_object_referrers proves static access with file/line evidence; a record-set factory is write intent, not proof of a committed write.
Calls
Configurations with extensions
When the graph covers the relevant base/extension layers: list_graph_projects, match the current roots, keep the base project_id, and never register extensions as projects. Repeat discovery only when workspace/server context changes or the mapping becomes invalid. Effective implementation in that index — resolve_effective_entity(project_id, object_name, entity_kind="MetadataObject", entity_name?); what one indexed extension changed — compare_base_and_extension(project_id, object_name, extension_name). Keep the base and extension comparison inside that same project. Neither a plain hit nor an indexed effective view alone proves what runs in a named infobase.
For separate indexes or missing graph layers, use each contour's mapped code tools or own files. Account for base, primary, secondary and relevant infrastructure contours before project-wide impact/absence claims; disclose missing coverage. Routing and runtime-evidence boundaries — content/rules/multi-contour-search.md.
Rules
- Read
truncated,exhaustive(includingdata.exhaustive),degradedandwarnings; an exhaustive claim needs a complete page set, verified scope and current sources.source_refresh.driftinvalidates a Graph freshness claim even when tasks arecompleted; removed metadata/forms can survive an incremental refresh. See the graph catalog's refresh boundaries before relying on an old hit or requesting maintenance. - Callers of a public
Экспортroutine are a promotion trigger (content/rules/verification-policy.md); the caller list belongs in the delivery evidence. - Typed answers map to actions by code —
content/rules/mcp-policy.md → C. Server answers → actions.
Evidence-first tools (find_graph_path, explain_graph_evidence, compare_graph_scope), domain relations (rights, subscriptions, DCS lineage): 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
- SKILL.md in the repositoryCheckingcontent/skills/1c-impact/SKILL.md
Popularity
- Repository stars
- 480
- Repository forks
- 107
- 7-day trend score
- 36
Stars and forks are for the whole GitHub repository, not this skill alone. 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
[](https://verified-skill.com/skills/comol/ai_rules_1c/1c-impact)