Tracks token usage in conversations, warns at 70% capacity, auto-triggers handover at 80% threshold with conversation summary and continuation prompts.

2026-02-120

credential-handling

bermingham85/warp-config

Never expose secrets in output. Use environment variables, reference .env files without reading contents aloud, recommend rotation if exposed.

2026-02-120

document-filing

bermingham85/warp-config

Every artifact must be filed in correct location with version control. Defines filing structure and naming conventions.

2026-02-120

error-handling-process

bermingham85/warp-config

Structured error handling - stop, assess, log, route, then fix or escalate. Prevents compounding problems.

2026-02-120

name	services-before-tokens
description	Routes tasks to external services (MCP, shell, n8n) before using AI tokens. Prevents wasteful AI processing for tool-solvable tasks.

Services Before Tokens

Trigger

Any task that could be handled by an external tool, API, MCP, or automation service.

Action

STOP before generating AI output. Check if a service can do it instead:

Routing Priority

File Operations → filesystem_mcp or shell commands
Database Queries → Direct PostgreSQL/SQL
Web Scraping → Playwright MCP
Calculations → Python/calculator
Git Operations → git CLI or GitHub MCP
Memory/Context → Memory MCP
n8n Workflows → Trigger webhook
Document Search → Notion MCP or grep
API Calls → Direct HTTP via curl/webhook

Anti-Patterns (Token Waste)

AI reads file and summarizes → Use read_files tool
AI "searches" codebase → Use grep or codebase_semantic_search
AI calculates → Python one-liner
AI formats JSON → jq command