Large Language Models and their utilizing tools evolved to provide agents working autonomously on computer systems, with full access to files, configuration, and processes. Especially for software development, CLI tools like Claude Code facilitate engineering novel features, finding and fixing bugs, code changes due to updated library, and writing full documentation.
In an ongoing blog series, all commands from the Claude Code CLI are explored systematically. They can be separated into different groups, targeting aspects like session management, conversation ops, configuration, and much more. The particular focus of this article are terminal configuration, adjusting font, colors, and key binding, and diagnostics, identifying potential issues with the CLI functionality.
The technical context of this article is claude_code v2.1.91, published on 2026-04-02. Examples and most CLI commands should work with newer versions too.
While I’m fascinated by the capabilities of artificial intelligence tools and applications, crafting blog articles remains my personal skill. Every character, number, and symbol in this article was typed manually, with the exception of verbose copies from log messages and screenshots.
Claude Code CLI: Slash Command Overview
Once a Claude Code session is started, more than 40 built-in slash-commands are available. They can be grouped into different categories that reflect the session lifecycle of its invocation, augmented by universal commands. Here is my proposed structure:
-
✅ Session Configuration
/add-dir: Add an additional working directory to the current session/rename: Provide a meaningful name to the conversation, which reflects the variable name of the conversation file/model: Determine the LLM model to be used/effort: Configures the effort level of the model, adjusting its internal reasoning behavior/login: Log in to the Anthropic subscription or Console/logout: Log out of an Anthropic account
-
✅ Session Reflection
/cost: Shows the current session cost/usage: Shows token consumption in the context of a subscription plan/status: Shows essential CLI, model, and account information/stats: Shows usage statistics and activity overview/export: Create a compact conversation summary/insights: Generates a detailed report with meta information about the current session
-
✅ Session Management
/batch: Execute a plan file as a parallel running sub-session/btw: Process an additional instruction during a long-running main task/loop: Run a specific prompt periodically/tasks: List all background tasks/fork: Define a staging point in the conversation history from which different branches can be invoked/rewind: Roll back the conversation and optionally code base to an earlier state/exit: Stop the terminal/resume: Continue a session
-
✅ Context Management
/clear: Reset the conversation history/compact: Define a new conversation history entry, limiting the context that is sent to the LLM provider/context: Visualize current context usage as a colored grid/memory: Edit Claude memory files
-
✅ Conversation Ops
/rename: Provide a meaningful name to the conversation/init: Read the current project and generate a CLAUDE.md file/plan: Toggle between editing and plan mode/simplify: Review the changed code for efficiency/review: Review a merge request and optionally check comments from an origin repo/security-review: Invoke a special agent that checks the source code for security issues/diff: View and commit staged file changes/copy: Copy the last answer to the clipboard/export: Create a compact conversation summary
-
✅ Terminal Configuration
/theme: Configure the color theme/color: Configure prompt bar color/terminal-setup: Configure key bindings/vim: Enable or disable VIM editor support when editing files via the CLI/statusline: Set up a custom status line for the terminal
-
🌀 Diagnostics & User Support
/release-notes: Show the Claude Code release notes/doctor: Check configuration status/debug: Enable verbose debugging output and check for known issues/feedback: Write feedback about your Claude Code experience/help: Show general information about available slash commands/powerup: Explore Claude Code feature with small lessons/stickers: Order Claude Code stickers/buddy: Hatch a Tamagotchi-like coding companion
-
🌀 Permissions
/permissions: Fine-grained allow & deny tool permission rules/sandbox: Configure settings to secure Claude terminal access and program execution rights
-
Extensions
/hooks: View hook configurations for tool events/skills: View installed skills/agents: Create and manage agents/mcp: Set up and manage MCP server definitions/chrome: Start a local Chromium browser for browser interaction/plugin: Browse and configure CLI extension/reload-plugins: Reload all configured plugins
-
Integrations
/ide: Show IDE integrations for Claude, for example in Visual Studio Code/install-github-app: Configure GitHub actions that interact with Claude/install-slack-app: Configure Slack integration/mobile: Show a QR code to download the iOS or Android app/claude-api: Build native apps that integrate with Anthropic SDK
Groups and commands marked with ✅ were covered in an earlier article, while those with 🌀 are the focus of this article.
Diagnostics & User Support
/release-notes
This unassuming command prints the complete release-notes of all prior versions of the Claude Code binary. The output is very detailed, as you can see for yourself in the following excerpt.
/release-notes
Version 0.2.21:
· Fuzzy matching for /commands
Version 0.2.26:
· New /approved-tools command for managing tool permissions
· Word-level diff display for improved code readability
· Fuzzy matching for slash commands
...
Version 2.1.78:
· Added StopFailure hook event that fires when the turn ends due to an API error (rate limit, auth failure, etc.)
· Added ${CLAUDE_PLUGIN_DATA} variable for plugin persistent state that survives plugin updates; /plugin uninstall prompts before deleting
it
· Added effort, maxTurns, and disallowedTools frontmatter support for plugin-shipped agents
· Terminal notifications (iTerm2/Kitty/Ghostty popups, progress bar) now reach the outer terminal when running inside tmux with set -g
allow-passthrough on
· Response text now streams line-by-line as it's generated
/doctor
This command prints debug-like information about the current environment, including details such as the installer type, binary, install method, and information about updates.
See the full output of this command here:
Diagnostics
└ Currently running: npm-global (2.1.91)
└ Path: /usr/local/bin/node
└ Invoked: /usr/local/bin/claude
└ Config install method: not set
└ Search: OK (vendor)
Updates
└ Auto-updates: disabled (CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC set)
└ Update permissions: No (requires sudo)
└ Auto-update channel: latest
└ Stable version: 2.1.116
└ Latest version: 2.1.123
/debug
This command enables debugging log output. Upon execution, it prints file location to which verbose messages will be posted.
/debug
● Debug logging is now active. The log file is at /home/node/.claude/debug/3a0213a0-5ef4-420c-8d11-1bda03f41a1a.txt.
No issues captured yet since logging was just enabled. If you encounter a problem, reproduce it and I'll check the log for errors or warnings.
Meanwhile, I continued the Claude Code session, and checked the accumulated content in this file. It contains trace information about plugin loading, file history, authentication, and executing the configured status script that renders the status line.
2026-04-29T18:14:01.226Z [DEBUG] High write ratio: blit=0, write=58565 (100.0% writes), screen=756x143
2026-04-29T18:14:01.230Z [DEBUG] AutoUpdaterWrapper: Installation type: npm-global
2026-04-29T18:14:01.246Z [DEBUG] LSP Diagnostics: getLSPDiagnosticAttachments called
2026-04-29T18:14:01.248Z [DEBUG] LSP Diagnostics: Checking registry - 0 pending
2026-04-29T18:14:01.251Z [DEBUG] Hooks: Found 0 total hooks in registry
2026-04-29T18:14:01.253Z [DEBUG] Sending 5 skills via attachment (initial, 5 total sent)
2026-04-29T18:14:01.255Z [DEBUG] Hooks: checkForNewResponses returning 0 responses
2026-04-29T18:14:01.274Z [DEBUG] FileHistory: Making snapshot for message 03a71a38-a939-496a-b94c-94b593035519
2026-04-29T18:14:01.280Z [DEBUG] Total plugin output styles loaded: 0
2026-04-29T18:14:01.292Z [DEBUG] [useDeferredValue] Messages deferred by 5 (443→448)
2026-04-29T18:14:01.364Z [DEBUG] High write ratio: blit=0, write=58565 (100.0% writes), screen=756x143
2026-04-29T18:14:01.372Z [DEBUG] FileHistory: Missing tracked file: .claude/statusline-command.sh
2026-04-29T18:14:01.373Z [DEBUG] FileHistory: Missing tracked file: .claude/statusline-command.cjs
2026-04-29T18:14:01.380Z [DEBUG] autocompact: tokens=78124 threshold=167000 effectiveWindow=180000
2026-04-29T18:14:01.386Z [DEBUG] Tool search disabled: ToolSearchTool is not available (may have been disallowed via disallowedTools).
2026-04-29T18:14:01.427Z [DEBUG] [API:request] Creating client, ANTHROPIC_CUSTOM_HEADERS present: false, has Authorization header: false
2026-04-29T18:14:01.428Z [DEBUG] [API:auth] OAuth token check starting
2026-04-29T18:14:01.437Z [DEBUG] [useDeferredValue] Messages deferred by 5 (443→448)
2026-04-29T18:14:01.447Z [DEBUG] StatusLine [input=$(cat); model=$(echo "$input" | jq -r '.model.display_name'); tokens=$(echo "$input" | jq -r '.context_window.current_usage.input_tokens'); max=$(echo "$input" | jq -r '.context_window.context_window_size'); echo "$model, $tokens/$max"; proj=$(echo "$input" | jq -r '.workspace.project_dir' | xargs -I{} basename "{}"); branch=$(git -C "$(echo "$input" | jq -r '.workspace.project_dir')" branch --show-current 2>/dev/null || echo ""); echo "$proj, $branch"] completed with status 0
2026-04-29T18:14:01.451Z [DEBUG] [API:auth] OAuth token check complete
2026-04-29T18:14:01.469Z [DEBUG] [API REQUEST] /anthropic/v1/messages source=repl_main_thread
2026-04-29T18:14:01.517Z [DEBUG] FileHistory: Added snapshot for 03a71a38-a939-496a-b94c-94b593035519, tracking 10 files
2026-04-29T18:14:01.538Z [DEBUG] [useDeferredValue] Messages deferred by 5 (443→448)
2026-04-29T18:14:13.607Z [DEBUG] Stream started - received first chunk
2026-04-29T18:14:16.271Z [WARN] [3P telemetry] Event dropped (no event logger initialized): api_request
2026-04-29T18:14:16.276Z [DEBUG] [useDeferredValue] Messages deferred by 2 (448→450)
2026-04-29T18:14:16.357Z [DEBUG] High write ratio: blit=0, write=58567 (100.0% writes), screen=759x143
2026-04-29T18:14:16.374Z [DEBUG] Preserving file permissions: 100600
2026-04-29T18:14:16.376Z [DEBUG] Writing to temp file: /home/node/.claude.json.tmp.16.1777486456374
2026-04-29T18:14:16.376Z [DEBUG] Temp file written successfully, size: 1057 bytes
2026-04-29T18:14:16.377Z [DEBUG] Applied original permissions to temp file
2026-04-29T18:14:16.377Z [DEBUG] Renaming /home/node/.claude.json.tmp.16.1777486456374 to /home/node/.claude.json
2026-04-29T18:14:16.378Z [DEBUG] File /home/node/.claude.json written atomically
2026-04-29T18:16:46.423Z [DEBUG] LSP server manager shut down successfully
2026-04-29T18:16:46.435Z [DEBUG] Preserving file permissions: 100600
2026-04-29T18:16:46.436Z [DEBUG] Writing to temp file: /home/node/.claude.json.tmp.16.1777486606435
2026-04-29T18:16:46.436Z [DEBUG] Temp file written successfully, size: 1141 bytes
2026-04-29T18:16:46.437Z [DEBUG] Applied original permissions to temp file
2026-04-29T18:16:46.438Z [DEBUG] Renaming /home/node/.claude.json.tmp.16.1777486606435 to /home/node/.claude.json
2026-04-29T18:16:46.438Z [DEBUG] File /home/node/.claude.json written atomically
2026-04-29T18:16:46.439Z [DEBUG] Metrics export disabled by organization setting
2026-04-29T18:16:46.440Z [DEBUG] BigQuery metrics exporter flush complete
2026-04-29T18:16:46.441Z [DEBUG] BigQuery metrics exporter flush complete
2026-04-29T18:16:46.443Z [DEBUG] BigQuery metrics exporter shutdown complete
2026-04-29T18:16:46.447Z [WARN] [stderr]
2026-04-29T18:16:46.451Z [DEBUG] Preserving file permissions: 100600
2026-04-29T18:16:46.453Z [DEBUG] Writing to temp file: /home/node/.claude.json.tmp.16.1777486606451
2026-04-29T18:16:46.453Z [DEBUG] Temp file written successfully, size: 1966 bytes
2026-04-29T18:16:46.454Z [DEBUG] Applied original permissions to temp file
2026-04-29T18:16:46.455Z [DEBUG] Renaming /home/node/.claude.json.tmp.16.1777486606451 to /home/node/.claude.json
2026-04-29T18:16:46.457Z [DEBUG] File /home/node/.claude.json written atomically
2026-04-29T18:16:46.460Z [DEBUG] Preserving file permissions: 100600
2026-04-29T18:16:46.461Z [DEBUG] Writing to temp file: /home/node/.claude.json.tmp.16.1777486606460
2026-04-29T18:16:46.461Z [DEBUG] Temp file written successfully, size: 2358 bytes
2026-04-29T18:16:46.462Z [DEBUG] Applied original permissions to temp file
2026-04-29T18:16:46.463Z [DEBUG] Renaming /home/node/.claude.json.tmp.16.1777486606460 to /home/node/.claude.json
2026-04-29T18:16:46.463Z [DEBUG] File /home/node/.claude.json written atomically
/feedback
Occasionally, a Claude Code session might show unexpected behavior, or even crash. To capture the necessary diagnostics and create a bug ticket for Anthropic, this command can be used.
Executing this command opens an interactive dialog, in which a short explanation is requested from the user.
/feedback
─────────────────────────────────────────────────────────────────────────────
Submit Feedback / Bug Report
Describe the issue below:
When running long running tasks, the terminal commands to list background jobs should be executable in the same manner as the /btw command.
Enter to continue · Esc to cancel
Upon confirming you issue, another screen details which kind of information will be included in the report. Pressing enter confirms your acceptance, and the issue will be sent to Anthropic.
Submit Feedback / Bug Report
This report will include:
- Your feedback / bug description: When running long running tasks, the terminal commands to list background jobs should be executable in the same manner as the /btw command.
- Environment info: linux, xterm, v2.1.91
- Git repo metadata: feature/optimizations, c4d53f8 @ https://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@github.com/admantium-sg/universal-skill-converter.git, has local changes
- Current session transcript
We will use your feedback to debug related issues or to improve Claude Code's functionality (eg. to reduce the risk of bugs occurring in the future).
Press Enter to confirm and submit.
/help
To get familiar with the complexity of the Claude Code CLI, this command provides a structured, compact reference. When executed, it opens a horizontal navigable screen with the three sections general, command, and custom commands.
❯ /help
─────────────────────────────────────────────────────────────────────────────
Claude Code v2.1.91 general commands custom-commands
Claude understands your codebase, makes edits with your permission, and executes commands — right from your terminal.
New here? Run /powerup to learn the features most people miss.
In the first part, all defined keyboard shortcuts are printed. Helpful text editing features include file mentioning, undo, stashing, and opening an editor for complex prompts. You can also toggle the model and fast mode, and execute bash commands without leaving the CLI.
Shortcuts
! for bash mode double tap esc to clear input ctrl + shift + - to undo
/ for commands shift + tab to auto-accept edits ctrl + z to suspend
@ for file paths ctrl + o for verbose output ctrl + v to paste images
& for background ctrl + t to toggle tasks meta + p to switch model
/btw for side question backslash (\) + return (⏎) for meta + o to toggle fast mode
newline ctrl + s to stash prompt
ctrl + g to edit in $EDITOR
The second section lists all available commands, alphabetically.
Browse default commands:
/add-dir
Add a new working directory
/agents
Manage agent configurations
/branch
Create a branch of the current conversation at this point
/btw
Ask a quick side question without interrupting the main conversation
/clear
Clear conversation history and free up context
...
And the last section shows an interesting amount of commands grouped together, and includes custom commands defined in your global and local Claude settings.
Browse custom commands:
/batch
Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that ea…
/claude-api
Build apps with the Claude API or Anthropic SDK.…
/debug
Enable debug logging for this session and help diagnose issues (bundled)
/loop
Run a prompt or slash command on a recurring interval (e.g. /loop 5m /foo, defaults to 10m) (bundled)
/simplify
Review changed code for reuse, quality, and efficiency, then fix any issues found. (bundled)
/update-config
Use this skill to configure the Claude Code harness via settings.json. Automated behaviors ("from now on when X"…
/powerup
Another command to get familiar with the Claude Code CLI is to use powerup. It provides a to-do list with essential topics that you should work on.
/powerup
─────────────────────────────────────────────────────────────────────────────
Power-ups 0/10 unlocked
Each power-up teaches one thing Claude Code can do that most people miss. Open one, read it, try it, mark it done.
❯ ◯ Talk to your codebase @ files, line refs
◯ Steer with modes shift+tab, plan, auto
◯ Undo anything /rewind, Esc-Esc
◯ Run in the background tasks, /tasks
◯ Teach Claude your rules CLAUDE.md, /memory
◯ Extend with tools MCP, /mcp
◯ Automate your workflow skills, hooks
◯ Multiply yourself subagents, /agents
◯ Code from anywhere /remote-control, /teleport
◯ Dial the model /model, /effort
Here is the printout of the first lesson.
◯ Talk to your codebase
Type @ anywhere in your prompt to fuzzy-find and attach a file. Claude reads it before answering — no more pasting code.
╭──────────────────────────────────────────────╮
│ > what does @src/auth.ts do? ◐ demo │
│ ◐ Reading src/auth.ts… │
│ │
╰──────────────────────────────────────────────╯
Reference specific lines with src/app.ts:42 and Claude jumps straight there. Works in both directions: Claude cites files the same way, so you can click to open them in your editor.
Also try: @folder/ to attach a whole directory tree.
/stickers
A command named for what it does – it opens a webpage where you can order real stickers.
/stickers
⎿ Failed to open browser. Visit: https://www.stickermule.com/claudecode
Here is a screenshot of the offered variants.
/buddy
In the middle of working on this article, I discovered a new command in the list. It creates a coding companion, a Tamagotchi like creature that lives on your terminal.
╭──────────────────────────────────────╮
│ │
│ ★ COMMON CHONK │
│ │
│ /\ /\ │
│ ( ✦ ✦ ) │
│ ( .. ) │
│ `------´ │
│ │
│ Gravy │
│ │
│ "A common chonk of few words." │
│ │
│ DEBUGGING ███░░░░░░░ 25 │
│ PATIENCE ░░░░░░░░░░ 1 │
│ CHAOS █░░░░░░░░░ 9 │
│ WISDOM ██████░░░░ 55 │
│ SNARK ████░░░░░░ 43 │
│ │
╰──────────────────────────────────────╯
Gravy is here · it'll chime in as you code
your buddy won't count toward your usage
say its name to get its take · /buddy pet · /buddy off
During coding, prompts will be watched by this creature, increasing or decreasing its attributes. Alternatively, you can mention it actively, and give it a task. The interaction below shows that the main agent receives the prompt, and then invokes the companion, which is likely implemented as an agent too.
Gravy, what do you think is my intention during this session?
∴ Thinking…
The user is asking Gravy (the companion chonk) what their intention is during this session. Gravy will respond. My job is to stay out of the way and let Gravy answer - but also, as the assistant, I should be ready to continue work once Gravy finishes.
...
Gravy says: "It looks like you're here to learn how to build LLM-powered apps with the Claude API, then probably put that knowledge to work — maybe on the Python refactor plan that's sitting in the background? Or maybe you're just browsing the docs. Hard to tell, but I'm getting "planning to build something smart" vibes from you."
Permissions
Claude Code has an extensive permission system, regulating shell command execution, file modification, and access to special or pseudo files.
When starting a session inside a terminal, you must approve to trust this folder. Then, all bash commands that Claude generates to e.g. explore the code base, listing files, reading their content, and continuing with editing and writing files or running tests on your source code, ultimately require permissions. The individual commands allowed or restricted are recorded in a settings.json file.
Four scopes for this file exists: Globally managed, in Linux systems under the path /etc/claude-code/, in your home directory ~/.claude, in the project directory, and in the local folder you are working on. From all these locations, the currently effective config will be merged, in this order: local, project, user, command line arguments, managed. Local settings can override anything else, with the exception of managed settings. This file is meant to place system settings that restric access to conventional files, pseudo files at /proc, or special files such as sockets. This is advisable to limit the risks of accidential credantial exposure or executing malicious code that damages or infilrates the host.
/permissions
Editing the permission settings directly in the JSON files can be tedious. This command helps with a structured dialog to browse, edit, and add permissions.
The opening dialogue shows four sections at the top: Recently denied, Allow, Ask, Deny, and Workspace. Each of these sections list the corresponding permissions entries.
/permissions
─────────────────────────────────────────────────────────────────
Permissions: Recently denied Allow Ask Deny Workspace
Claude Code won't ask before using allowed tools.
╭───────────────────────────────────────────────╮
│ ⌕ Search… │
╰───────────────────────────────────────────────╯
1. Add a new rule…
2. Bash(node:*)
3. Read
4. WebSearch
←/→ tab switch · ↓ return · Esc cancel
Here is an example for adding a new rule, executing npm run lint in the project. The dialog ask where this rule should be persisted.
─────────────────────────────────────────────────────────────────
Add allow permission rule
Bash(npm run lint)
The Bash command npm run lint
Where should this rule be saved?
❯ 1. Project settings (local) Saved in .claude/settings.local.json
2. Project settings Checked in at .claude/settings.json
3. User settings Saved in at ~/.claude/settings.json
When browsing to the Deny section, entries from my managed settings are shown …
─────────────────────────────────────────────────────────────────
Permissions: Recently denied Allow Ask Deny Workspace
Claude Code will always reject requests to use denied tools.
╭──────────────────────────────────────────────────────────╮
│ ⌕ Search… │
╰──────────────────────────────────────────────────────────╯
1. Add a new rule…
2. Bash(env*)
3. Bash(nc*)
4. Bash(ncat*)
5. Bash(netcat*)
6. Bash(netstat*)
7. Bash(printenv*)
8. Bash(ss*)
9. Bash(ssh*)
↓ 10. Grep(**/.bash_history*)
… and can not be edited.
╭─────────────────────────────────────────────────────────────────────╮
│ Rule details │
│ Bash(netcat*) │
│ The Bash command netcat* │
│ From enterprise managed settings │
│ This rule is configured by managed settings and cannot be modified. │
│ Contact your system administrator for more information. │
╰─────────────────────────────────────────────────────────────────────╯
Esc to cancel
Finally, the Workspace section shows the current working directory, and enables to add additional ones too.
─────────────────────────────────────────────────────────────────
Permissions: Recently denied Allow Ask Deny Workspace
Claude Code can read files in the workspace, and make edits when auto-accept edits is on.
- /opt/claude/universal-skill-converter (Original working directory)
1. Add directory…
←/→ tab switch · ↓ return · Esc cancel
/sandbox
Another security layer is sandbox mode. The Claude CLI runs with a system-specific process supervisor, which is seatbelt for osx and bubblewrap for Linux and the Windows WSL2 shell.
This command start a dialogue that navigates the setting landscape of sandbox mode, with four different sections.
─────────────────────────────────────────────────────────────────
Sandbox: Mode Dependencies Overrides Config
In the first tab, “Mode”, the invocation alternatives are listed. The sandbox can be disabled, enabled for bash commands with regular permissions, or enabled for bash with auto allow
───────────────────────────────────────────────────────────────────────
Sandbox: Mode Dependencies Overrides Config
Note: Cannot block unix domain sockets (see Dependencies tab)
Configure Mode:
1. Sandbox BashTool, with auto-allow
2. Sandbox BashTool, with regular permissions
3. No Sandbox (current)
Auto-allow mode: Commands will try to run in the sandbox automatically, and attempts to run outside of the sandbox
fallback to regular permissions. Explicit ask/deny rules are always respected.
Learn more: code.claude.com/docs/en/sandboxing
I enabled the second option.
/sandbox
⎿ ✓ Sandbox enabled with regular bash permissions
The dependencies tab lists all required libraries or OS packages and their install status. When testing this command initially, I saw that one requirement was still missing, and installed it.
───────────────────────────────────────────────────────────────────────
Sandbox: Mode Dependencies Overrides Config
ripgrep (rg): found
bubblewrap (bwrap): installed
socat: installed
seccomp filter: not installed (required to block unix domain sockets)
· npm install -g @anthropic-ai/sandbox-runtime
· or copy vendor/seccomp/* from sandbox-runtime and set
sandbox.seccomp.bpfPath and applyPath in settings.json
In the Overrides tab, the current sandbox setting can be modified. If you want to stay strict, option 2 should be selected.
───────────────────────────────────────────────────────────────────────
Sandbox: Mode Dependencies Overrides Config
Configure Overrides:
1. Allow unsandboxed fallback (current)
2. Strict sandbox mode
Allow unsandboxed fallback: When a command fails due to sandbox restrictions, Claude can retry with
dangerouslyDisableSandbox to run outside the sandbox (falling back to default permissions).
Strict sandbox mode: All bash commands invoked by the model must run in the sandbox unless they are explicitly listed
in excludedCommands.
Learn more: code.claude.com/docs/en/sandboxing#configure-sandboxing
The final tab shows configs at a glance.
───────────────────────────────────────────────────────────────────────
Sandbox: Mode Dependencies +Overrides+ Config
Excluded Commands:
None
Filesystem Read Restrictions:
Denied: /opt/claude/universal-skill-converter/.env, /opt/claude/universal-skill-converter/node_modules/bottleneck/.env,
/opt/claude/proc, /opt/claude/run/docker.sock, /opt/claude/var/run/docker.sock
Filesystem Write Restrictions:
Allowed: /dev/stdout, /dev/stderr, /dev/null, /dev/tty, /dev/dtracehelper, /dev/autofs_nowait, /tmp/claude,
/private/tmp/claude, /home/node/.npm/_logs, /home/node/.claude/debug, ., /tmp/claude-1000/
Denied within allowed: /home/node/.claude/settings.json, /opt/claude/.claude/settings.json,
/opt/claude/.claude/settings.local.json, /etc/claude-code/managed-settings.json, /etc/claude-code/managed-settings.d,
/opt/claude/.claude/skills
⚠ Warning: Glob patterns not fully supported on Linux
The following patterns will be ignored: Read(**/.env*), Read(**/.git-credentials*), Read(**/.gitconfig*) (7 more)
Conclusion
The Claude Code CLI offers more than 40 subcommands. This blog article explored all commands concerned with Diagnostics & User Feedback as well as permissions. The Diagnostics & User support section includes commands about a) accessing release notes, b) seeing details about the Claude Code installation method and information about updates, c) starting debug mode that logs detailed statements to a file during your session, d) submitting a bug report from your current Claude Code session, including session logs and runtime information, e) seeing all key bindings in a compact form, and browse all CLI and custom commands, f) starting interactive learning sessions that help you master the CLI, g) ordering Claude Code stickers and f) creating a Tamagotchi-like coding buddy. The permissions commands allow yoo to a) browse, edit, and add permissions via a dialogue, and b) see and configure sandbox settings for an even stricter invocation of Claude Code.