Cursor Codebase Indexing

What it does

When your agent uses it

• Codebase indexing
• Cursor semantic search
• Cursor embeddings

Example prompts

• “cursor index”
• “codebase indexing”
• “index codebase”
• “/cursor-codebase-indexing”

Requirements

• Compatibility (from SKILL.md): Designed for Claude Code
• Pre-approved tools (allowed-tools): Read, Write, Edit, Bash(cmd:*)

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

1. 1Define the intended workspace scope and add exclusions before the first indexing pass.
2. 2Verify required files can be found and excluded paths cannot be attached or discovered.
3. 3Reindex only after a reviewed configuration/workspace change and capture a redacted result.
4. 4Monitor index size/performance and narrow scope rather than weakening data controls.

What it can do on your machine

Read from SKILL.md and the folder at commit 23ea8d4. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Write
  • Edit
  • Bash(cmd:*)

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • cursor

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • docs.cursor.com
  • cursor.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Designed for Claude Code

  From compatibility in the SKILL.md frontmatter.

Context cost

Cursor Codebase Indexing loads about 2k tokens when it runs, and up to ~3.4k if it reads all its reference files. Until then it costs about 61 tokens; SKILL.md has 736 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~61

When it runs · the whole SKILL.md, loaded when a task matches

~2k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~3.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NoteMentions a .env fileSKILL.md:46

  d `docs/` for a service while excluding `.env*`, build output, vendor directories, and customer exports. Verify a saniti

• NoteMentions a .env fileSKILL.md:128

  .env*

• NoteRuns commands with sudoSKILL.md:229

  sudo sysctl fs.inotify.max_user_watches=524288

• NoteRuns commands with sudoSKILL.md:232

  o "fs.inotify.max_user_watches=524288" | sudo tee -a /etc/sysctl.conf

• NoteRuns commands with sudoSKILL.md:233

  sudo sysctl -p

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jeremylongshore/tons-of-skills-marketplace at commit 23ea8d4, republished under its MIT licence (© jeremylongshore). 736 words, ~2,037 tokens.

name

cursor-codebase-indexing

description

Set up and optimize Cursor codebase indexing for semantic code search and @Codebase queries. Triggers on "cursor index", "codebase indexing", "index codebase", "cursor semantic search", "@codebase", "cursor embeddings".

allowed-tools

Read, Write, Edit, Bash(cmd:*)

compatibility

Designed for Claude Code

version

1.19.0

license

MIT

author

Jeremy Longshore <jeremy@intentsolutions.io>

tags

saas, cursor, cursor-codebase

Your Code Files
      │
      ▼
  Syntax Chunking ─── splits files into meaningful code blocks
      │
      ▼
  Embedding Generation ─── converts chunks to vector representations
      │
      ▼
  Vector Storage (Turbopuffer) ─── cloud-hosted nearest-neighbor search
      │
      ▼
  @Codebase Query ─── your question → embedding → similarity search → relevant chunks

# .cursorignore

# Build artifacts (large, not useful for AI context)
dist/
build/
out/
.next/
target/

# Dependencies
node_modules/
vendor/
venv/
.venv/

# Generated files
*.min.js
*.min.css
*.bundle.js
*.map
*.lock

# Large data files
*.csv
*.sql
*.sqlite
*.parquet
fixtures/
seed-data/

# Secrets (defense in depth -- also use .gitignore)
.env*
**/secrets/
**/credentials/

# .cursorindexingignore

# Large test fixtures -- don't index, but allow @Files reference
tests/fixtures/
e2e/recordings/

# Documentation build output
docs/.vitepress/dist/

@Codebase where is user authentication handled?

@Codebase show me all API endpoints that accept file uploads

@Codebase how does the payment processing flow work?

@Codebase find all places where we connect to Redis

# Instead of opening the entire monorepo:
cursor /path/to/monorepo           # Indexes everything -- slow

# Open the specific package:
cursor /path/to/monorepo/packages/api   # Indexes only this package -- fast

# .cursorignore -- monorepo, focus on api and shared
packages/web/
packages/mobile/
packages/admin/
# packages/api/    ← not listed, so it IS indexed
# packages/shared/ ← not listed, so it IS indexed

# Check current limit
cat /proc/sys/fs/inotify/max_user_watches

# Increase (temporary)
sudo sysctl fs.inotify.max_user_watches=524288

# Increase (permanent)
echo "fs.inotify.max_user_watches=524288" | sudo tee -a /etc/sysctl.conf
sudo sysctl -p

© jeremylongshore, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 8 other files (references) in skills/.curated/cursor-codebase-indexing of jeremylongshore/tons-of-skills-marketplace.

• SKILL.md
• references/configuration.md
• references/errors.md
• references/examples.md
• references/index-settings.md
• references/maintaining-the-index.md
• references/optimization-for-large-projects.md
• references/troubleshooting.md
• references/using-the-index.md

Open the folder on GitHubat commit 23ea8d4