tools-usage-patterns

Provides practical workflows for using specialized MCP tools. This rule covers the code investigation protocol for debugging and understanding code, and the memory management protocol for persistent knowledge capture and retrieval.

Cursor rule for Cursor

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add rules/felipebarcelospro/igniter-js/tools-usage-patterns
Clone the repo
git clone --depth 1 https://github.com/felipebarcelospro/igniter-js

Made for: Cursor.

Per session 988 This file is loaded in full into every session.
When invoked 988 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin unknown No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00988 $0.00988
Opus 5 $0.00494 $0.00494
Sonnet 5 $0.00198 $0.00198
Haiku 4.5 $0.00099 $0.00099

Measured today against content hash 452113d8b2e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tools-usage-patterns 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 today.

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.

apps/sample-realtime-chat/.cursor/rules/tools-usage-patterns.mdc · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tool Usage Patterns

This document provides standardized patterns for using specialized tools to investigate code and manage the project's knowledge base.

1. Code Investigation Protocol

This protocol should be followed whenever you encounter TypeScript errors, unknown APIs, or need to understand the implementation of a specific part of the codebase.

When to Investigate

  • TypeScript Errors: "Property does not exist," "Cannot find name," etc.
  • Import Errors: "Module not found," "Export does not exist."
  • API Understanding: Learning how a new library or internal module works.
  • Debugging: Tracing unexpected behavior.

Investigation Workflow

The investigation process is a funnel, moving from broad discovery to deep analysis.

  1. Locate the Symbol (find_implementation): This is your starting point. When you encounter an unknown symbol, use this tool to find where it's defined.

    {
      "tool": "find_implementation",
      "args": { "symbol": "symbolName", "filePath": "path/to/current/file.ts" }
    }
    
  2. Analyze the Source (explore_source): Once you have the file path from find_implementation, use this tool to get a deep understanding of the source code, especially for code in node_modules.

    {
      "tool": "explore_source",
      "args": { "filePath": "/path/to/implementation.ts", "symbol": "symbolName" }
    }
    
  3. Trace Complex Dependencies (trace_dependency_chain): If an import is complex (e.g., re-exported through multiple files), use this tool to map the entire chain back to its origin.

    {
      "tool": "trace_dependency_chain",
      "args": { "symbol": "symbolName", "startFile": "path/to/current/file.ts" }
    }
    

Strategic Pattern: Error Resolution

  1. Run analyze_file on the file with the error.
  2. Use find_implementation on the symbol causing the error.
  3. Use explore_source on the file where the implementation is located.
  4. After resolving the issue, ALWAYS use store_memory to document the solution as a bug_pattern. This prevents solving the same problem twice.

Read the full file on GitHub · 83 lines

Changes

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.

  1. today First seen · 83 lines · 988 tokens per session scan A 452113d8b2e5

Subscribe to this mod's changes

tools-usage-patterns is a cursor rule published in the GitHub repository felipebarcelospro/igniter-js (242 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 988 tokens to every session, about $0.0049 per session on Opus 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 2026-09-01.