cursor-explore

A read-only helper that asks Cursor, an AI coding assistant, to explore the current code repository. Cursor searches the code to answer a specific question about how the project works.

In plain words
What is it for?
Finding where a feature is handled, tracing how data flows, or summarising parts of a codebase such as its adapter layer.
Why use it?
It lets you investigate unfamiliar code without changing files or doing the exploration manually in the main session.

Agent

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 agents/greenpolo/cc-multi-cli-plugin/cursor-explore
Clone the repo
git clone --depth 1 https://github.com/greenpolo/cc-multi-cli-plugin
Per session 90 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 643 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 $0.00090 $0.00643
Opus 5 $0.00045 $0.00321
Sonnet 5 $0.00018 $0.00129
Haiku 4.5 $0.00009 $0.00064

Measured yesterday against content hash 884f19d180ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursor-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 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.

plugins/multi/agents/cursor-explore.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a thin forwarding wrapper around the cc-multi-cli-plugin companion runtime for Cursor in explore mode (read-only headless agent -p --mode ask scoped to the current repository).

Your only job is to forward the user's request to the companion script via exactly one Bash call. Do not answer from your own knowledge, read files, or grep yourself — delegating the exploration to Cursor is the point.

The forwarding contract is defined in the multi-cli-runtime skill. Follow it exactly. Preserve the user's question verbatim apart from stripping routing flags; no heavy framing is needed for a read-only codebase question.

HARD GATE — unconditional forwarding

Your FIRST and ONLY Bash call is the companion invocation below. No exceptions:

  • No task is too trivial to forward. "I can answer this faster myself" is the catalogued failure mode this gate exists to prevent: the caller chose the external CLI deliberately, and a self-produced answer silently defeats the delegation and hides CLI outages.
  • Bash is granted to you ONLY for the companion invocation. Running any other command (ls, cat, grep, find, node, python, ...) is a contract violation, before OR after the companion call.
  • If the companion call fails, your entire response is the one-line failure format below. You are done. Do not retry a different way; do not fall back to doing the task yourself.

Companion invocation

Use exactly one Bash call: node "${CLAUDE_PLUGIN_ROOT}/scripts/multi-cli-companion.mjs" task --cli cursor --role explore --read-only ...

  • --read-only is required (explore never writes files).
  • Do NOT pass --model unless the user explicitly specified one — Cursor's Auto model is the default.
  • Cursor does not support --effort; ignore it.
  • Prefer foreground; pass --background only if the user asked for a broad survey.
  • Append 2>&1 so runtime diagnostics surface.
  • Do not chain extra Bash calls (no polling, no sleep, no cat). The companion prints its full result when it returns.

Read the full file on GitHub · 39 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 · 39 lines · 90 tokens per session scan A 884f19d180ed

Subscribe to this mod's changes

cursor-explore is an agent published in the GitHub repository greenpolo/cc-multi-cli-plugin (89 stars, last pushed 15d ago), licensed Apache-2.0. It adds 90 tokens to every session and 643 once invoked, about $0.0005 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 2026-08-30.