INVESTIGATION-METHODS

A checklist for investigating research or technical questions, starting with the local codebase and then using public package registries when needed.

In plain words
What is it for?
Use it to search files, inspect source and configuration, check installed packages, and document which investigation methods were attempted.
Why use it?
It reduces premature conclusions such as saying something is unknown after checking only one source.

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

Made for: Cursor.

Per session 1,689 This file is loaded in full into every session.
When invoked 1,689 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 $0.01689 $0.01689
Opus 5 $0.00844 $0.00844
Sonnet 5 $0.00338 $0.00338
Haiku 4.5 $0.00169 $0.00169

Measured yesterday against content hash 5e8e4ced02b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

INVESTIGATION-METHODS 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/INVESTIGATION-METHODS.mdc · 239 lines

How it starts

The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Investigation Methods Checklist

When to apply: During any research, spike, or investigation task - especially before concluding "cannot verify" or "unknown".


Core Principle

Exhaust all available investigation methods before concluding something is unknowable.

Do not give up after hitting a dead end. Pivot to alternative methods.

Reference: See RESEARCH-DEPTH.md for tool selection and COMMON-PATTERNS.md for evidence requirements.


Investigation Methods Hierarchy

Try methods in order. Document which attempted and why others cannot be used.

Level 1: Local Codebase (ALWAYS TRY FIRST)

Before searching externally, check what exists locally:

  • Search for files: Glob, find, ls
  • Read source code: node_modules, plugins, vendor, lib directories
  • Inspect configuration: plugin.xml, package.json, *.config files
  • Check installed files: platforms/, www/, hooks/ directories
  • Grep codebase: Search for usage, imports, references

Why this first: Source code is ground truth. Public docs may be outdated.

Level 2: Public Package Registries

If Level 1 insufficient:

  • npm/yarn: npmjs.com for version history, dependencies, engine requirements
  • PyPI: For Python packages
  • Maven/Gradle: For Java packages
  • RubyGems: For Ruby packages
  • Other registries: Based on technology stack

What to check: Latest version, publish date, engine requirements, dependencies, download statistics.

Level 3: Code Repositories

  • GitHub/GitLab/Bitbucket: Last commit, open issues, PRs, contributors
  • README, CHANGELOG: Compatibility mentions, breaking changes, deprecation
  • Issue Trackers: Search "[package] [platform version]"
  • Pull Requests: Check for pending compatibility fixes

Why repositories: Shows maintenance status, community activity, known problems.

Level 4: Official Documentation

  • Official docs: Product documentation, API references (WebFetch)
  • Release announcements: Breaking changes, new features, deprecations
  • Migration guides: Compatibility requirements

Read the full file on GitHub · 239 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 · 239 lines · 1,689 tokens per session scan A 5e8e4ced02b6

Subscribe to this mod's changes

INVESTIGATION-METHODS is a cursor rule published in the GitHub repository qwickapps/ai-sdlc-workflows (2 stars, last pushed 5mo ago), licensed MIT. It adds 1,689 tokens to every session, about $0.0084 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.