Skip to main content
Cursor is an AI-powered code editor available as both an IDE and a command-line agent. Entire integrates with Cursor through its hook system, capturing sessions and checkpoints across both interfaces.

​
Prerequisites

​
How It Works

Entire integrates with Cursor through hook configuration in .cursor/hooks.json. When you enable Entire with Cursor, hooks are installed automatically: 
entire enable --agent cursor
The hooks track the full session lifecycle:
  1. Session Start - Fires when Cursor launches, creating a new Entire session
  2. Prompt Tracking - before-submit-prompt hook captures each prompt submission
  3. Subagent Tracking - subagent-start and subagent-stop hooks track nested agent operations
  4. Session End - Fires when Cursor exits, finalizing the session
  5. Compaction - pre-compact hook triggers before session data compaction
  6. Transcript Capture - Session transcript is read from Cursor’s JSONL log files
  7. Session Storage - Data saved to the entire/checkpoints/v1 branch

​
Captured Data

DataDescription
ConversationFull transcript of prompts and responses
File changesAll files modified during the session
Subagent callsNested agent invocations and operations
TimestampsSession, message, and checkpoint timing
Note: Unlike Claude Code, Cursor transcripts do not include token usage data or detailed tool invocation records.

​
Cursor IDE vs Cursor CLI

Entire supports both Cursor interfaces. Choose Cursor IDE for traditional development workflows and Cursor CLI for scripted tasks, parallel processing, or terminal-first development.

​
Features

​
Session Capture

Entire automatically captures both the conversation flow and file modifications: 
# Start Cursor (IDE or CLI)
cursor
# or
agent

# Work with Cursor - make changes, run agents, etc.

# In another terminal, check session status
entire status

​
Explain Commits

View or generate explanations of how code was written: 
# Explain a specific commit
entire explain --commit abc1234

# Explain a specific checkpoint
entire explain --checkpoint a3b2c4d5

# Show full transcript
entire explain --full
FlagDescription
-c, --checkpoint <id>Explain a specific checkpoint (ID or prefix)
--commit <sha>Explain a specific commit (SHA or ref)
--fullShow full parsed transcript (all prompts/responses)
-s, --shortShow summary only (omit prompts and files)

​
Important Caveats

​
No Rewind/resume Support

Rewind and resume are not available for Cursor sessions. You can use other Entire commands (status, doctor, explain, disable), but cannot restore to previous checkpoints. Plan your commits carefully as you cannot undo changes via entire rewind.

​
No Token Accounting

Cursor transcripts do not include token usage data (unlike Claude Code). Token calculation is unavailable for Cursor sessions. You can still see the conversation and file changes, but not the computational cost.

​
File Detection via Git Status

Cursor’s transcript format lacks detailed tool invocation records, so modified file detection relies on git status instead of transcript analysis. This means:
  • Files must be committed or staged to be tracked
  • File modifications not in git are not captured in transcripts
  • The file change detection is accurate but less granular than Claude Code

​
Context Attachment Differences

When using Cursor CLI, the @ syntax for attaching files/folders as context does not behave identically to the IDE:
  • IDE: @ mentions work through the AI chat interface for context selection
  • CLI: @ syntax may require different handling; check Cursor CLI documentation for current behavior

​
Best Practices

​
Commit at Logical Points

Create checkpoints at natural stopping points:
  • After implementing a feature
  • Before making major changes
  • When you’d want to document progress

​
Review Sessions in PRs

Share session context in pull request reviews:
  1. Create a PR
  2. Commits include Entire-Checkpoint trailers
  3. Reviewers can click to view session details
  4. Understanding why code was written helps with review

​
Example Workflow

​
With Cursor IDE

# 1. Enable Entire
cd my-project
entire enable --agent cursor

# 2. Start Cursor IDE
cursor

# 3. Work with Cursor IDE
# Use @ mentions to attach files for context
# Ask the AI to implement features

# 4. Check status (in another terminal)
entire status

# 5. Commit when ready
git add .
git commit -m "Add feature with Cursor"

# 6. Push to see on entire.io
git push

​
With Cursor CLI

# 1. Enable Entire
cd my-project
entire enable --agent cursor

# 2. Run Cursor CLI
agent

# 2.1 Instruct Cursor CLI
"refactor the authentication module"

# 3. In parallel terminal, run another Cursor CLI
agent

# 3.1 Instruct the other CLI
"update database schema"

# 4. Check both sessions
entire status

# 5. Commit all changes
git add .
git commit -m "Parallel refactoring with Cursor CLI"

# 6. Push to see on entire.io
git push

​
Troubleshooting

  1. Verify Entire is enabled: entire status
  2. Check that hooks are installed: cat .cursor/hooks.json
  3. Ensure Cursor is running from within the repository
  4. For Cursor CLI, verify the process exits cleanly to trigger session-end hook
  1. Checkpoints require file changes — ensure Cursor is modifying files
  2. Changes must be staged or committed (git status is used for detection)
  3. Check your settings in .entire/settings.json
  4. Verify the .cursor/hooks.json hooks are present
  1. Ensure Cursor’s session storage exists (check ~/.cursor/ directory)
  2. Verify JSONL transcript files are being written by Cursor
  3. Check that the session completed normally (session-end hook must fire)
  4. Look for errors in Entire hook output with entire doctor
This is expected behavior for Cursor. Since transcripts lack tool_use blocks, file detection relies on git status. Make sure to:
  1. Stage or commit your changes with git add and git commit
  2. Run entire status to verify files are detected
  3. Review actual file changes in git diff if transcript shows nothing
When using Cursor CLI, @ mentions for file context may not work identically to the IDE:
  1. Check Cursor CLI documentation for current context attachment syntax
  2. Consider using environment variables or configuration files for context
  3. Include relevant files in your initial prompt text instead of @ mentions

​
Limitations

  • Rewind is not available - cannot restore to previous checkpoints
  • No token accounting - transcripts don’t include token usage data
  • File detection is git-based - relies on git status rather than transcript analysis
  • No detailed tool records - unlike Claude Code, tool invocation details are limited
  • Integration is in preview - may contain rough edges or undocumented behavior