A command for choosing whether Cursor Context Engine, a local service that supplies coding context, uses the Cursor command-line tool or the Cursor editor source. It can show the current choice or save a new one.

Use `/cce cli` or `/cce ide` to select a source, and `/cce` to display the current source and its local settings file.

It avoids changing the source manually and keeps the selected source across restarts and updates. It changes the routing preference without starting a context query.

cce — Command for Claude Code by Vanyangyang/cursor-bridge

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.

Clone the repo

git clone --depth 1 https://github.com/Vanyangyang/cursor-bridge

Made for: Claude Code.

Or install cursor-bridge, the plugin that ships this one along with the rest of its 3 skills, 1 command, 2 hooks, 1 MCP server, 1 plugin.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/commands/vanyangyang/cursor-bridge/cce/github.svg)](https://agentmods.dev/commands/vanyangyang/cursor-bridge/cce)

Your own site

<a href="https://agentmods.dev/commands/vanyangyang/cursor-bridge/cce"><img src="https://agentmods.dev/badge/commands/vanyangyang/cursor-bridge/cce/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/vanyangyang/cursor-bridge/cce"><img src="https://agentmods.dev/badge/commands/vanyangyang/cursor-bridge/cce.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 227 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00020	$0.00227
Opus 5.5	$0.00008	$0.00091
Sonnet 5.5	$0.00004	$0.00045
Haiku 4.5	$0.00002	$0.00023

Measured 5d ago against content hash 790652a9c47e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cce 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 5d 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.

commands/cce.md · 14 lines

What it actually says

Manage Cursor Context Engine's local source preference. User argument: $ARGUMENTS.

For exactly cli, call cursor_cce with {"action":"set","source":"cli"}. For exactly ide, call cursor_cce with {"action":"set","source":"ide"}. Without an argument, call cursor_cce with {"action":"show"}. For any other argument, explain /cce cli, /cce ide and /cce without modifying the preference.

Report cceSource and the local cceSourceFile in the user's language. The saved choice survives restarts and plugin updates, applies to later CCE queries, and keeps CCE's existing model/effort and evidence contract. Do not submit a query or change native Cursor settings. If the tool is unavailable, report that Bridge must be updated/reloaded instead of claiming the switch succeeded.

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.

5d ago First seen · 14 lines · 20 tokens per session scan A 790652a9c47e

Subscribe to this mod's changes

cce is a command published in the GitHub repository Vanyangyang/cursor-bridge (83 stars, last pushed 5d ago), licensed MIT. It adds 20 tokens to every session and 227 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-11-01.

Claude Code Productivity codex coding-agent cursor cursor-ide developer-tools

cce next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
cceVanyangyang/cursor-bridge	Command	83	5d ago	MIT	A	20	Claude Code
agent-work-receiptemaraschio/cursor-commands	Command	9	14d ago	MIT	A	27	Claude Code, Cursor
housekeep-fileskensaurus/cursor-kenji	Command	9	1mo ago	MIT	A	27	Claude Code
decision-auditemaraschio/cursor-commands	Command	9	14d ago	MIT	A	20	Claude Code, Cursor
prompt-eval-debugemaraschio/cursor-commands	Command	9	14d ago	MIT	A	31	Claude Code, Cursor
thermo-nuclear-code-quality-reviewemaraschio/cursor-commands	Command	9	14d ago	MIT	A	29	Claude Code, Cursor
address-github-pr-commentsemaraschio/cursor-commands	Command	9	14d ago	MIT	A	15	Claude Code, Cursor