AGENTS.md Template

# Zephex MCP Configuration ## MCP Endpoint- URL: https://zephex.dev/mcp- Auth: Authorization: Bearer YOUR_API_KEY- Protocol: JSON-RPC 2.0 over Streamable HTTP- Tool count: 10 hosted tools ## Mandatory Tool OrderAlways follow this sequence for coding tasks:1. scope_task — Identify the minimal files to read BEFORE reading anything2. get_project_context — Run once per session for project orientation3. read_code — Read specific functions/classes (not whole files)4. find_code — Search for patterns before writing new code5. thinking — Track reasoning state for complex or high-risk tasks ## Available Tools Reference| Tool | Purpose | When to Call ||---|---|---|| scope_task | Minimal file set for the task | FIRST, before any file reads || get_project_context | Project brief + full file tree | Once per session (covers structure) || read_code | AST symbol extraction + callers | Instead of reading full files || find_code | Repo-wide pattern search | Before implementing anything new || explain_architecture | Request/auth/data flow tracing | Before touching auth or DB code || check_package | npm package verification | Before adding dependencies || audit_package | CVE check and migration guide | Before upgrading packages || audit_headers | HTTP/TLS security audit | After every deploy || Zephex_dev_info | Extract content from URL | For reading external docs || thinking | Structured reasoning + session state | Complex debugging, high-risk changes | ## Rules- Never read a full file when read_code with a symbol name will do- Never implement something new before running find_code to check if it exists- Always call scope_task at the start of non-trivial tasks- Call audit_headers after any deployment to production ## Project Context[Fill in your project-specific notes here: stack, key directories, naming conventions, deployment targets]