RESEARCH-DEPTH

A rule set requiring evidence-based research before making assumptions or implementing changes. It directs the agent to investigate unfamiliar code, patterns, and available tools first.

In plain words
What is it for?
Use it during investigation and planning to find existing implementations, conventions, files, and relevant research before acting.
Why use it?
It reduces errors caused by guessing about the codebase or its architecture and encourages decisions based on observed evidence.

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/qwickapps/ai-sdlc-workflows/research-depth
Clone the repo
git clone --depth 1 https://github.com/qwickapps/ai-sdlc-workflows

Made for: Cursor.

Per session 1,884 This file is loaded in full into every session.
When invoked 1,884 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original 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 $0.01884 $0.01884
Opus 5 $0.00942 $0.00942
Sonnet 5 $0.00377 $0.00377
Haiku 4.5 $0.00188 $0.00188

Measured yesterday against content hash 01cce406e560, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

RESEARCH-DEPTH 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 yesterday.

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.

cursor/.cursor/rules/RESEARCH-DEPTH.mdc · 342 lines

How it starts

The opening of the file, as written. The whole thing — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Depth Requirements

When to apply: Before making assumptions, before implementing solutions, during investigation phases.


Core Principle

Do NOT make assumptions. Use available research tools to gather evidence BEFORE acting.

You have powerful research tools (Explore agent, Grep, Chrome automation, QwickBrain MCP). Use them. Shallow research leads to wrong assumptions and wasted effort.

Reference: See COMMON-PATTERNS.md for evidence requirements and research documentation patterns.


Research Tools Available

1. Explore Agent

Task tool with subagent_type=Explore

When to use:

  • Exploring unfamiliar codebase
  • Finding patterns/conventions/existing implementations
  • Understanding "how does X work?"
  • Locating files by functionality (not exact name)

Example prompts:

  • "Find how authentication is implemented"
  • "Explore migration system and how it loads files"
  • "Find error handling patterns in API endpoints"

Do NOT:

  • Search manually with multiple Grep commands
  • Make assumptions about architecture
  • Guess where code might be

2. Grep (Content Search)

When to use:

  • Finding specific code patterns, function names, strings
  • Searching for exact matches
  • Finding usages of function/variable

Example patterns:

  • pattern: "import.*PayloadConfig"
  • pattern: "migration\.up"
  • pattern: "class.*Migration"

Do NOT:

  • Use for open-ended exploration (use Explore)
  • Search without specific pattern

3. Chrome Automation

Tools: mcp__claude-in-chrome__*

When to use:

  • Testing web applications
  • Verifying frontend functionality
  • Capturing UI state/errors
  • Recording user workflows
  • Checking browser console for errors

Key operations:

  • tabs_context_mcp - Get current tabs
  • tabs_create_mcp - Create new tab
  • screenshot - Capture state
  • read_console_messages - Check errors
  • gif_creator - Record interactions

Do NOT:

  • Assume frontend works without browser check
  • Skip console error checks
  • Trigger JavaScript alerts (blocks extension)

Read the full file on GitHub · 342 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. yesterday First seen · 342 lines · 1,884 tokens per session scan A 01cce406e560

Subscribe to this mod's changes

RESEARCH-DEPTH is a cursor rule published in the GitHub repository qwickapps/ai-sdlc-workflows (2 stars, last pushed 5mo ago), licensed MIT. It adds 1,884 tokens to every session, about $0.0094 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 2026-08-31.