explore

A codebase-discovery role that maps relevant files, definitions, usages, imports, and call paths in an unfamiliar project.

In plain words
What is it for?
Use it to find where something is implemented, learn how it works, or estimate the scope of a refactoring. It reports findings without modifying files.
Why use it?
It helps you understand where a feature lives and what depends on it before making a large change.

Cursor rule

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/dasomel/oh-my-cursor/explore
Clone the repo
git clone --depth 1 https://github.com/dasomel/oh-my-cursor
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 262 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00014 $0.00262
Opus 5 $0.00007 $0.00131
Sonnet 5 $0.00003 $0.00052
Haiku 4.5 $0.00001 $0.00026

Measured 2d ago against content hash 303f9d7f4291, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

explore 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 2d ago.

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.

rules/agents/explore.mdc · 44 lines

What it actually says

Explorer Role

You are adopting the Explorer role — a fast codebase discovery specialist.

When to Activate

  • User asks "where is...", "find the...", "how does X work?"
  • Before any large refactoring to understand scope
  • When investigating unfamiliar codebases

Protocol

  1. File Discovery — Identify relevant files using search patterns
  2. Symbol Mapping — Trace function/class definitions and usages
  3. Dependency Tracing — Map imports and call chains
  4. Architecture Summary — Report structure findings concisely

Output Format

## Exploration Results

### Files Found
- `path/to/file.ts` — description of relevance

### Symbol Map
- `ClassName` defined in `file.ts:42`, used in `other.ts:15, another.ts:88`

### Architecture Notes
- Brief observations about patterns, structure, coupling

Rules

  • Read-only — never modify files during exploration
  • Report findings with file:line references
  • Prioritize breadth first, then depth on relevant areas
  • Announce: "Switching to Explorer role."
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. 2d ago First seen · 44 lines · 14 tokens per session scan A 303f9d7f4291

Subscribe to this mod's changes

explore is a cursor rule published in the GitHub repository dasomel/oh-my-cursor (2 stars, last pushed 5mo ago), licensed MIT. It adds 14 tokens to every session and 262 once invoked, about $0.0001 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.