Borrowing it
Nothing to install: this file belongs to Apitomy/apitomy-data-models-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Apitomy/apitomy-data-models-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/Apitomy/apitomy-data-models-mcpWrote 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.
[](https://agentmods.dev/instructions/apitomy/apitomy-data-models-mcp/claude-md)<a href="https://agentmods.dev/instructions/apitomy/apitomy-data-models-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/apitomy/apitomy-data-models-mcp/claude-md/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.
<a href="https://agentmods.dev/instructions/apitomy/apitomy-data-models-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/apitomy/apitomy-data-models-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.02072 | $0.02072 |
| Opus 5.5 | $0.00829 | $0.00829 |
| Sonnet 5.5 | $0.00414 | $0.00414 |
| Haiku 4.5 | $0.00207 | $0.00207 |
Grade A, and why
apitomy-data-models-mcp CLAUDE.md 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Guidelines
Overview
This is an MCP (Model Context Protocol) server that wraps the @apitomy/data-models library to
provide AI-assisted querying, editing, validation, and transformation of OpenAPI and AsyncAPI
documents. It is a TypeScript project using the @modelcontextprotocol/sdk.
Architecture
Source Layout
src/
index.ts # Entry point (stdio transport)
server.ts # MCP server creation and tool/resource registration
session-manager.ts # In-memory session store (Map<string, SessionEntry>)
tools/
session.ts # Session lifecycle tools (create, list, get, close, export)
query.ts # Document query tools (info, paths, schemas, nodes, operations)
edit.ts # Document editing tools (set, remove, add schema)
transform.ts # Format conversion tools (JSON/YAML, version conversion)
validation.ts # Document validation tool
resources/
document.ts # MCP resource templates (info, paths, schemas per session)
visitors/
index.ts # Barrel export for all visitors
DocumentInfoVisitor.ts
OperationCollectorVisitor.ts
PathCollectorVisitor.ts
SchemaCollectorVisitor.ts
SchemaContainerVisitor.ts
SecuritySchemeCollectorVisitor.ts
ServerCollectorVisitor.ts
TagCollectorVisitor.ts
ClearNodeVisitor.ts
RemoveNodeVisitor.ts
util/
errors.ts # Error result helpers
format.ts # JSON/YAML format detection and serialization
model-type-map.ts # ModelType string-to-enum mapping
Session Model
Documents are managed through named sessions stored in a singleton SessionManager. Each session
holds a parsed Document object from the data-models library, along with metadata (model type,
file path, format, timestamps). Tools receive a session_name parameter to identify which
document to operate on.
Tool Categories
- Session tools (7):
document_load,document_create,document_save,document_close,document_list_sessions,document_export,document_clone_session - Query tools (16):
document_get_info,document_list_paths,document_get_operation,document_list_schemas,document_get_node,document_list_operations,document_get_schema,document_list_security_schemes,document_list_servers,document_list_tags,document_list_parameters,document_list_responses,document_list_media_types,document_list_extensions,document_list_examples,document_find_refs - Edit tools (76):
document_set_info,document_add_path,document_add_schema,document_set_node,document_remove_node,document_add_operation,document_remove_operation,document_add_response,document_add_parameter,document_add_request_body,document_add_media_type,document_set_media_type_schema,document_add_security_scheme,document_remove_response,document_add_response_definition,document_remove_parameter,document_remove_security_scheme,document_add_tag,document_add_server,document_set_contact,document_set_license,document_remove_schema,document_remove_path,document_add_channel,document_add_response_header,document_remove_request_body,document_update_security_scheme,document_remove_tag,document_rename_tag,document_remove_server,document_add_extension,document_remove_extension,document_remove_response_header,document_add_schema_property,document_remove_schema_property,document_add_security_requirement,document_add_example,document_set_operation_info,document_set_operation_tags,document_set_schema_required,document_set_schema_type,document_add_schema_enum,document_remove_all_security_requirements,document_remove_media_type,document_add_parameter_definition,document_remove_parameter_definition,document_add_header_definition,document_remove_header_definition,document_add_example_definition,document_remove_example_definition,document_add_request_body_definition,document_remove_request_body_definition,document_delete_contact,document_delete_license,document_update_extension,document_remove_all_examples,document_rename_path,document_rename_schema,document_copy_operation,document_move_operation,document_add_callback,document_remove_callback,document_add_link,document_remove_link,document_set_external_docs,document_add_server_variable,document_remove_server_variable,document_remove_all_operations,document_remove_all_responses,document_remove_all_parameters,document_remove_all_response_headers,document_remove_all_schema_properties,document_remove_all_servers,document_remove_all_tags,document_remove_all_security_schemes,document_remove_all_extensions - Validation tool (1):
document_validate - Transform tools (2):
document_transform,document_dereference
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.
- 2mo ago First seen · 202 lines · 2,072 tokens per session scan A 718436b267b3
apitomy-data-models-mcp CLAUDE.md is an instructions file published in the GitHub repository Apitomy/apitomy-data-models-mcp (0 stars, last pushed 2d ago), licensed Apache-2.0. It adds 2,072 tokens to every session, about $0.0083 per session on Opus 5.5. 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 2026-08-31.
apitomy-data-models-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| apitomy-data-models-mcp CLAUDE.mdApitomy/apitomy-data-models-mcp | Instructions file | 0 | 2d ago | Apache-2.0 | A | 2,072 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |