Documentation Index
Fetch the complete documentation index at: https://docs.entire.io/llms.txt
Use this file to discover all available pages before exploring further.
The entire CLI comes with powerful commands to manage your local development experience. All commands are called on the entire CLI path.
attach
Attach an existing agent session that was not captured automatically by Entire.
entire session attach <session-id> [flags]
This command reads the session transcript, creates a checkpoint, and links it to your last commit.
Use it when:
- Hooks were not installed when the session started
- Hooks failed to fire
- You want to keep a research-only session that did not produce file changes
If the last commit already has an Entire-Checkpoint trailer, the session is added to that existing checkpoint. Otherwise, Entire creates a new checkpoint and offers to amend the last commit with the trailer.
| Flag | Description |
|---|
-a, --agent <name> | Agent that created the session. Defaults to claude-code. Supported values: claude-code, gemini, opencode, codex, cursor, copilot-cli, factoryai-droid |
-f, --force | Skip confirmation and amend the last commit with the checkpoint trailer |
# Attach a Codex session and amend HEAD automatically
entire session attach 019d6c43-1537-7343-9691-1f8cee04fe59 -a codex -f
# Attach a Claude Code session using the default agent
entire session attach 9b1deb4d-3b7d-4bad-9bdd-2b0d7b3dcbfe
entire session attach requires the repository to already have at least one commit. If Entire cannot find the transcript for the agent you specify, it will try to auto-detect the correct agent from known transcript locations.
activity
Show your Entire activity overview from your hosted Entire account.
This command loads your activity from the last month from entire.io, including:
- Activity overview and aggregate stats
- Repository breakdown
- Recent commits from the last month, grouped by day
If you are not logged in, authenticate first:
When you run entire activity in an interactive terminal, it opens a richer terminal UI. In non-interactive contexts, such as piped output, or when accessibility mode is enabled with ACCESSIBLE=1, it falls back to a simpler static text view that works better with screen readers.
# Open the interactive activity view
entire activity
# Use simpler static output for screen readers
ACCESSIBLE=1 entire activity
entire activity shows account-level activity from Entire, not just local repository state.
agent
Manage agent integrations in the current repository.
entire agent <subcommand>
agent list
List installed and available agents.
agent add
Install hooks for an agent.
entire agent add <agent-name> [flags]
| Flag | Description |
|---|
--force | Reinstall hooks even if already present |
--local-dev | Install hooks in local-dev mode |
agent remove
Uninstall hooks for an agent.
entire agent remove <agent-name>
Configure Entire settings in the current repository. To manage agent hooks, use entire agent; on first run, it installs agent hooks, and on subsequent runs, it lets you enable more agents.
| Flag | Description |
|---|
--absolute-git-hook-path | Embed full binary path in Git hooks. Required for GUI Git clients that don’t source shell profiles. See GUI Git Clients. |
--checkpoint-remote <provider:owner/repo> | Push checkpoint branches to a separate repository (e.g., github:org/checkpoints-private). See Checkpoint Remote. |
-f, --force | Force reinstall the Entire Git hook |
--local | Write settings to .entire/settings.local.json instead of .entire/settings.json |
--project | Write settings to .entire/settings.json even if it already exists |
--skip-push-sessions | Disable automatic pushing of session logs on Git push |
--summarize-model <model> | Set the model hint used by checkpoint explain --generate |
--summarize-provider <provider> | Set the provider used by checkpoint explain --generate |
--telemetry | Enable anonymous usage analytics (default: true) |
Use entire agent remove <name> to uninstall hooks for a specific agent.
clean
Clean up Entire session data.
| Flag | Description |
|---|
-a, --all | Clean all Entire session data across the repository |
--dry-run | Show what would be cleaned without actually deleting |
-f, --force | Skip confirmation and override the active-session guard |
--session <id> | Clean a specific session by ID |
By default, entire clean removes session data for the current HEAD commit:
- Session state files for sessions based on the current commit
- The shadow branch for the current commit and worktree
Use --session <id> to clean a single session. This removes the session state and deletes its shadow branch if no other session still needs it. File changes remain in your working directory.
Use --all to clean Entire session data across the repository:
- All session state files in
.git/entire-sessions/
- All shadow branches
- Temporary files in
.entire/tmp/
The permanent entire/checkpoints/v1 branch is preserved.
# Preview cleanup for the current HEAD
entire clean --dry-run
# Clean one session
entire clean --session 2026-02-02-test123 --force
# Clean all session data in the repository
entire clean --all --force
entire reset is deprecated. Use entire clean instead, or entire clean --all for repository-wide cleanup.
disable
Remove Entire hooks from a repository. This stops session capture but preserves existing session data.
| Flag | Description |
|---|
--force | Skip confirmation prompt (use with --uninstall) |
--project | Update .entire/settings.json instead of .entire/settings.local.json |
--uninstall | Completely remove Entire from this repository |
Disabling Entire does not delete your session history. You can re-enable at any time with entire enable. Use --uninstall to completely remove Entire from the repository.
doctor
Scan for stuck or problematic sessions and offer to fix them.
A session is considered stuck if:
- It is in ACTIVE phase with no interaction for over 1 hour
- It is in ENDED phase with uncondensed checkpoint data on a shadow branch
| Flag | Description |
|---|
-f, --force | Fix all issues without prompting (condense if possible, otherwise discard) |
For each stuck session, you can choose to:
- Condense: Save session data to permanent storage (
entire/checkpoints/v1 branch)
- Discard: Remove the session state and shadow branch data
- Skip: Leave the session as-is
doctor logs
Show recent operational logs.
entire doctor logs [flags]
| Flag | Description |
|---|
-f, --follow | Stream new log lines as they are written |
--tail <N> | Show the last N lines. Use 0 for all. Defaults to 100. |
doctor bundle
Produce a diagnostic bundle for bug reports.
entire doctor bundle [flags]
| Flag | Description |
|---|
-o, --out <path> | Path to write the bundle archive. Defaults to the OS temp directory. |
--raw | Skip secret redaction. Use only when support has asked for an unredacted bundle. |
doctor trace
Show hook performance traces for debugging slow Git operations.
entire doctor trace [flags]
| Flag | Description |
|---|
--last <N> | Show last N hook invocations (default: 1) |
--hook <type> | Filter by hook type (e.g., post-commit, prepare-commit-msg, pre-push) |
Traces are only logged at DEBUG level. Enable with ENTIRE_LOG_LEVEL=DEBUG or set "log_level": "DEBUG" in .entire/settings.json.
dispatch
Generate a dispatch summarizing recent agent work.
entire dispatch has two modes:
- Cloud mode (default) generates a dispatch from Entire server data
- Local mode (
--local) generates a dispatch from local repository data using your locally installed agent CLI
If you run entire dispatch with no flags in an interactive terminal, Entire launches a guided wizard. In non-interactive contexts, or whenever you provide flags, it prints markdown output directly.
| Flag | Description |
|---|
--local | Generate via the locally installed agent CLI instead of the Entire server |
--since <time> | Start of the time window. Accepts Go durations, relative times, or ISO dates. Defaults to 7d. |
--until <time> | End of the time window. Defaults to now. |
--all-branches | Include every existing local branch. Only valid with --local. |
--repos <owner/repo> | Limit cloud dispatch to one or more repos. Accepts comma-separated GitHub repo slugs. |
--voice <preset-or-text> | Customize the dispatch tone with a preset such as neutral or marvin, or provide your own text. |
Use cloud mode when you want a dispatch from Entire-tracked repo data:
# Default dispatch for recent work in the current repo
entire dispatch
# Limit cloud dispatch to specific repos
entire dispatch --repos entireio/cli,entireio/entire.io
Use local mode when you want a dispatch from local repository history:
# Local dispatch from the current branch
entire dispatch --local
# Local dispatch across all local branches
entire dispatch --local --all-branches
You can also customize the dispatch voice:
entire dispatch --voice neutral
--repos cannot be combined with --local, and --all-branches only applies to --local.
Cloud dispatch supports up to 5 repos per request, and each repo must use owner/repo format.
enable
Initialize Entire in a Git repository. This installs the necessary Git hooks to capture AI coding sessions.
| Flag | Description |
|---|
--absolute-git-hook-path | Embed full binary path in Git hooks. Required for GUI Git clients that don’t source shell profiles. See GUI Git Clients. |
--agent <name> | Agent to setup hooks for: claude-code, codex, gemini, opencode, cursor, copilot-cli, or factoryai-droid. Enables non-interactive mode. |
--checkpoint-remote <provider:owner/repo> | Push checkpoint branches to a separate repository (e.g., github:org/checkpoints-private). See Checkpoint Remote. |
-f, --force | Force reinstall hooks (removes existing Entire hooks first) |
--local | Write settings to .entire/settings.local.json instead of .entire/settings.json. |
--project | Write settings to .entire/settings.json even if it already exists |
--skip-push-sessions | Disable automatic pushing of session logs on Git push |
--telemetry | Enable anonymous usage analytics (default: true) |
-y, --yes | Accept defaults without prompting. Useful for automation, CI, and bootstrap flows. |
Use --yes for non-interactive setup flows:
# Non-interactive setup for a specific agent
entire enable --yes --agent claude-code
# Non-interactive setup using default choices
entire enable --yes
--yes is not just a confirmation bypass. It runs entire enable non-interactively with default choices. On a fresh repository, it enables the default setup without prompts. On an already configured repository, it follows the setup-management path. Outside a Git repository, it also accepts the bootstrap defaults to initialize Git, create a private GitHub repository through gh, and create the initial commit.
Important behavior:
- If you also pass
--agent <name>, that explicit agent selection takes precedence over the default multi-agent behavior.
- If you pass
--telemetry=false, or set ENTIRE_TELEMETRY_OPTOUT, that explicit telemetry opt-out still overrides the --yes default.
The --local and --project flags control which Entire settings file is modified. Entire always modifies the agent’s project settings (e.g., .claude/settings.json, .gemini/settings.json, .opencode/plugins/entire.ts, or .factory/settings.json).
explain
Generate an AI-powered explanation of a session or commit.
entire checkpoint explain [checkpoint-id | commit-sha] [flags]
| Flag | Description |
|---|
-c, --checkpoint <id> | Explain a specific checkpoint (ID or prefix) |
--commit <sha> | Explain a specific commit (SHA or ref, “commit-ish”) |
--force | Regenerate summary even if one already exists (requires --generate) |
--full | Show full parsed transcript (all prompts/responses) |
--generate | Generate an AI summary for the checkpoint |
--no-pager | Disable pager output |
--raw-transcript | Show raw transcript file (JSONL format) |
--search-all | Search all commits (no branch/depth limit, may be slow) |
--session <id> | Filter checkpoints by session ID (or prefix) |
-s, --short | Show summary only (omit prompts and files) |
The --generate flag requires the configured provider CLI, such as Claude CLI, to be installed and authenticated.
auth
Manage authentication and API tokens.
auth login
Authenticate with your Entire account. Equivalent to the top-level entire login.
auth logout
Sign out of your Entire account. Equivalent to the top-level entire logout.
auth status
Show authentication status.
auth list
List active API tokens for the authenticated user.
auth revoke
Revoke an API token by ID.
entire auth revoke [token-id] [flags]
| Flag | Description |
|---|
--current | Revoke the token used by this CLI and remove the local copy |
checkpoint list
List checkpoints on the current branch.
entire checkpoint list [flags]
| Flag | Description |
|---|
--no-pager | Disable pager output |
--session <id> | Filter checkpoints by session ID (or prefix) |
search
Search checkpoints using semantic and keyword matching.
entire checkpoint search [query] [flags]
| Flag | Description |
|---|
--author <name> | Filter by author name |
--branch <name> | Filter by branch name |
--date <period> | Filter by time period (week or month) |
--json | Output as JSON |
--limit <N> | Maximum number of results per page |
--page <N> | Page number, 1-based |
--repo <owner/repo> | Filter by repository. Use * to search all accessible repos. |
help
Display help information about any command.
| Argument | Description |
|---|
command | Optional. The command to get help for. |
# Show general help
entire help
# Get help for a specific command
entire help enable
entire enable --help
login
Log in to Entire.
This command starts a device authorization flow, prints a device code, and asks you to approve the login in your browser.
If Entire is running interactively, it prompts you before opening the approval URL automatically. In non-interactive environments, it prints the approval URL so you can open it manually.
entire login stores an authentication token for the current Entire API base URL after login completes.
logout
Log out of Entire.
This command removes the saved authentication token for the current Entire API base URL.
labs
Explore experimental Entire workflows.
This command lists newer Entire workflows that are available to try while they are still being refined, including entire review.
Use it to discover experimental commands and see where to find their command-specific help.
# List experimental workflows
entire labs
# Open help for the currently listed review workflow
entire review --help
entire labs is a discovery command. It does not run the listed workflows as nested subcommands. For example, use entire review --help, not entire labs review --help.
review
Run configured review skills against the current branch and record the review with the checkpoint it covered.
entire review is an experimental workflow listed by entire labs. Run it directly as entire review, not entire labs review.
On first run, entire review opens a setup picker and saves review settings to .entire/settings.json. After setup, it runs the selected review skills with the configured agent.
The review session is recorded as review metadata on the next checkpoint, including the review skills and the prompt sent to the reviewer. This helps future agents and teammates understand what was reviewed and why.
| Flag | Description |
|---|
--edit | Reopen the review config picker |
--findings | Browse local review findings |
--fix | Apply review findings in a normal agent session |
--all | With --fix, apply all sources and findings without selectors |
--agent <name> | Select a specific configured agent |
review attach
Tag an existing agent session as a review.
entire review attach <session-id> [flags]
Use this when you ran a review manually and want the review metadata attached after the fact.
| Flag | Description |
|---|
-a, --agent <name> | Agent that created the session |
--skills <skill> | Review skill that was run. Repeat to declare multiple skills. |
-f, --force | Skip confirmation and amend the last commit with the checkpoint trailer |
# Run a review
entire review
# Reopen the review setup picker
entire review --edit
# Tag an existing session as a review
entire review attach 019d6c43-1537-7343-9691-1f8cee04fe59 --agent claude-code --skills /pr-review-toolkit:review-pr
resume
Switch to a local branch and resume the agent session from its last commit.
entire session resume <branch> [flags]
This command:
- Checks out the specified branch
- Finds the session ID from commits unique to this branch (not on main)
- Restores the session log if it doesn’t exist locally
- Shows the command to resume the session
| Argument | Description |
|---|
branch | The branch to resume the agent session from |
| Flag | Description |
|---|
-f, --force | Resume from older checkpoint without confirmation |
If the branch doesn’t exist locally but exists on origin, you’ll be prompted to fetch it.
If newer commits without checkpoints exist on the branch (e.g., after merging main or cherry-picking), this operation will reset your Git status to the most recent commit with a checkpoint. You’ll be prompted to confirm.
rewind
Rewind to a previous checkpoint within the current session.
entire checkpoint rewind [flags]
| Flag | Description |
|---|
--to <commit> | Rewind to specific commit ID (non-interactive) |
--list | List available rewind points (JSON output) |
--logs-only | Only restore logs, don’t modify working directory (for logs-only points) |
--reset | Reset branch to commit (destructive, for logs-only points) |
Rewinding discards changes made after the selected checkpoint. Make sure to commit any changes you want to keep before rewinding. The --reset flag is destructive and will reset your branch.
sessions
View and manage agent sessions tracked by Entire.
entire session <subcommand>
session current
Show the active session for the current worktree.
entire session current [flags]
| Flag | Description |
|---|
--json | Output as JSON |
session list
List all sessions tracked by Entire, including ended sessions.
session info
Show detailed information for a specific session.
entire session info shows agent, model, status, worktree, timing, token usage, checkpoint linkage, and files touched.
entire session info <session-id> [flags]
| Flag | Description |
|---|
--json | Output as JSON |
session stop
Stop one or more active sessions.
entire session stop [session-id] [flags]
| Flag | Description |
|---|
--all | Stop all active sessions |
-f, --force | Skip confirmation prompt |
status
Show the current Entire status for this repository.
| Flag | Description |
|---|
--detailed | Show detailed status for each settings file |
version
Show build information including the CLI version, Git commit, Go version, and OS/architecture.
You can also use the --version flag on the root command:
Both produce identical output:
Entire CLI v1.2.3 (abc1234)
Go version: go1.21.0
OS/Arch: darwin/arm64
Global Flags
These flags are available on the root command:
| Flag | Description |
|---|
--help, -h | Show help for entire or any subcommand |
--version, -v | Show build information (same as entire version) |