### Build Mode Examples

Source: https://commandcode.ai/docs/design

Provides examples of using the 'Build' modes: 'redesign' for visual changes, 'setup' for project context, and 'tokenize' for component extraction.

```bash
/design redesign src/pages/Home.tsx         # Full visual rework, logic untouched
```

```bash
/design setup                               # Create brief.md for this project
```

```bash
/design tokenize src/components/            # Extract tokens from repeated patterns 
```

--------------------------------

### Get a broad overview of a codebase

Source: https://commandcode.ai/docs/workflows

Use this prompt to get a high-level understanding of a project's structure, key packages, and entry points. Ensure Command Code is started in the project root.

```bash
> give me a brief overview of this codebase — structure, key packages, and entry points 
```

--------------------------------

### Install a skill from a GitHub repository

Source: https://commandcode.ai/docs/skills/commands

Use this command to install a skill from a GitHub repository. You can specify a single-skill repo, a specific path within a repo, pick a skill from a multi-skill repo, or install from a specific branch. Skills can be installed to the current project or globally.

```bash
cmd skills add acme/my-skills 
```

```bash
cmd skills add acme/skills/path/to/skill 
```

```bash
cmd skills add acme/multi-skills -s my-skill 
```

```bash
cmd skills add acme/repo@branch 
```

```bash
cmd skills add acme/repo --global 
```

--------------------------------

### Skill Folder with References Directory Example

Source: https://commandcode.ai/docs/skills

An example of a skill folder structure that includes the references/ subdirectory for organizing additional documentation like API references or troubleshooting guides.

```bash
my-skill/
├── SKILL.md
└── references/
    ├── API_REFERENCE.md
    ├── FORMS.md
    └── TROUBLESHOOTING.md
```

--------------------------------

### Example Output - Project Push

Source: https://commandcode.ai/docs/taste/commands/push

Example output indicating a successful push of an entire project taste, showing the number of packages and learnings.

```bash
✓ Pushed project taste to commandcode.ai/aa/taste (3 packages, 15 learnings) 
```

--------------------------------

### Install IDE Extension Non-interactively

Source: https://commandcode.ai/docs/core-concepts/ide-integration

Use the `--ide-setup` flag for a non-interactive installation of the IDE extension. This is useful for scripting purposes.

```bash
cmd --ide-setup 
```

--------------------------------

### Example Output - Individual Package Push

Source: https://commandcode.ai/docs/taste/commands/push

Example output for pushing an individual package, detailing the number of learnings added, updated, or unchanged.

```bash
✓ Pushed 'cli' to commandcode.ai/aa/taste (2 learnings added, 1 updated, 3 unchanged) 
```

--------------------------------

### Example: Add GitHub MCP Server from JSON

Source: https://commandcode.ai/docs/mcp/quickstart

This example demonstrates adding a GitHub MCP server using JSON configuration, specifying HTTP transport, URL, and an Authorization header.

```bash
cmd mcp add-json github '{"type":"http","url":"https://api.githubcopilot.com/mcp","headers":{"Authorization":"Bearer ghp_xxx"}}'
```

--------------------------------

### Install WSL

Source: https://commandcode.ai/docs/troubleshooting/windows

Run this command in PowerShell as Administrator to install WSL 2 with Ubuntu by default.

```powershell
wsl --install 
```

--------------------------------

### Skill Folder Structure Example

Source: https://commandcode.ai/docs/skills

An example of a skill folder structure, showing the placement of SKILL.md and the optional scripts/ subdirectory containing executable files.

```bash
my-skill/
├── SKILL.md
└── scripts/
    ├── extract.py
    └── process.sh
```

--------------------------------

### Example Output of taste open

Source: https://commandcode.ai/docs/taste/commands/open

Confirms that the 'cli' taste package was successfully opened from the project.

```bash
✓ Opened 'cli' taste package from project
```

--------------------------------

### Documentation Command Usage

Source: https://commandcode.ai/docs/reference/slash-commands

Example of how to invoke the documentation command.

```bash
/docs function 
```

--------------------------------

### Project Scope Configuration Example

Source: https://commandcode.ai/docs/mcp/manage

Example of the `.mcp.json` file content when a server is added to the project scope. Sensitive information like OAuth client secrets is omitted.

```json
{
  "mcpServers": {
    "stripe": {
      "transport": "http",
      "url": "https://mcp.stripe.com"
    }
  }
}
```

--------------------------------

### Install Community Skill

Source: https://commandcode.ai/docs/skills/manage

Installs a skill directly from a GitHub repository using the 'cmd skills add' command.

```bash
cmd skills add https://github.com/remotion-dev/skills --skill remotion-best-practices
```

--------------------------------

### Start Session with Initial Message

Source: https://commandcode.ai/docs/reference/cli

Starts an interactive session with a predefined initial message. This is useful for guiding the AI's first response.

```bash
cmd "fix login redirect"
```

--------------------------------

### Skill Folder with Assets Directory Example

Source: https://commandcode.ai/docs/skills

An example of a skill folder structure that includes the assets/ subdirectory for static resources such as template files, images, or database schemas.

```bash
my-skill/
├── SKILL.md
└── assets/
    ├── template.json
    ├── diagram.png
    └── schema.sql
```

--------------------------------

### Skill Directory Structure Example

Source: https://commandcode.ai/docs/skills/manage

Illustrates the recommended organization for skills, with each skill in its own directory.

```tree
.commandcode/skills/
├── code-review/
│   └── SKILL.md
├── api-guidelines/
│   └── SKILL.md
└── testing-patterns/
    └── SKILL.md
```

--------------------------------

### Editor Configuration Examples

Source: https://commandcode.ai/docs/taste/commands/open

Provides examples for setting the default editor environment variable in different shells and for various editors. After setting, restart your terminal or source the configuration file.

```bash
# VS Code
echo 'export EDITOR="code"' >> ~/.zshrc  # Vim
echo 'export EDITOR="vim"' >> ~/.zshrc  # Nano
echo 'export EDITOR="nano"' >> ~/.zshrc  # Sublime Text
echo 'export EDITOR="subl"' >> ~/.zshrc 
```

--------------------------------

### Install Command Code CLI

Source: https://commandcode.ai/docs

Install the Command Code CLI globally using npm.

```bash
npm i -g command-code
```

--------------------------------

### List all installed skills

Source: https://commandcode.ai/docs/skills/commands

This command lists all installed skills, categorized by project and global locations. Use the `--debug` flag to see details about skills that failed to load.

```bash
cmd skills list 
```

```bash
cmd skills list --debug 
```

--------------------------------

### Example: Add Notion MCP Server (HTTP)

Source: https://commandcode.ai/docs/mcp/quickstart

This is a concrete example of adding the Notion MCP server using HTTP transport. It specifies the server name as 'notion' and provides its URL.

```bash
cmd mcp add --transport http notion https://mcp.notion.com/mcp
```

--------------------------------

### Verify Command Code Installation

Source: https://commandcode.ai/docs/quickstart

Verify that Command Code has been installed correctly by checking its version. This command works on macOS and Linux.

```bash
cmd --version 
```

--------------------------------

### IDE Setup

Source: https://commandcode.ai/docs/reference/cli

Connects your IDE to Command Code to share open files and selected lines. Refer to IDE integration documentation for more details.

```bash
cmd --ide-setup
```

--------------------------------

### Realistic Design Workflow

Source: https://commandcode.ai/docs/design

Outlines a step-by-step workflow for using the /design command, from initial setup and auditing to refinement and final passes.

```bash
# 1. Set up project context /design setup  # 2. Audit what exists /design checkup /design smell  # 3. Refine with focused modes /design typeset src/components/Hero.tsx /design recolor /design relayout /design motion src/components/Button.tsx  # 4. Tokenize and harden /design tokenize /design surface  # 5. Final pass before shipping /design responsive /design finish 
```

--------------------------------

### Create Code Review User Skill

Source: https://commandcode.ai/docs/skills/manage

This example demonstrates creating a user-level skill for code reviews by creating its directory and `SKILL.md` file with detailed review checklist instructions.

```bash
mkdir -p ~/.commandcode/skills/code-review cat > ~/.commandcode/skills/code-review/SKILL.md << 'EOF' --- name: code-review description: Perform thorough code reviews checking for bugs, security issues, and best practices ---  # Code Review Checklist  ## Security - [ ] No hardcoded credentials or API keys - [ ] Input validation on all user data - [ ] Proper authentication and authorization  ## Code Quality - [ ] Clear, descriptive variable names - [ ] Functions do one thing well - [ ] No code duplication  ## Performance - [ ] No unnecessary loops - [ ] Efficient data structures - [ ] Optimized queries  ## Testing - [ ] Unit tests cover main functionality - [ ] Edge cases tested - [ ] Error conditions handled EOF 
```

--------------------------------

### Start in Auto-Accept Mode

Source: https://commandcode.ai/docs/reference/cli

Starts Command Code in auto-accept mode, which is an alias for `--permission-mode auto-accept`. This automatically accepts permissions.

```bash
cmd --auto-accept
```

--------------------------------

### Start in Plan Mode

Source: https://commandcode.ai/docs/reference/cli

Initiates Command Code in plan mode using the `--plan` flag. This mode is for generating and executing plans.

```bash
cmd --plan
```

--------------------------------

### Example output (valid)

Source: https://commandcode.ai/docs/taste/commands/lint

This output indicates that all checked taste files are valid, with no errors or warnings found.

```text
taste.md ✓ File is valid  cli/taste.md ✓ File is valid  Summary: 0 errors, 0 warnings across 2 files ✓ All 2 taste files are valid 
```

--------------------------------

### Progressive Disclosure Example

Source: https://commandcode.ai/docs/skills/best-practices

Keep the main SKILL.md file concise by moving detailed content to separate reference files. This example shows how to link to external documentation for API guidelines.

```markdown
# API Guidelines  Quick reference of our API patterns.  For complete documentation, see: - [Authentication details](references/AUTH.md) - [Error handling guide](references/ERRORS.md) - [Versioning strategy](references/VERSIONING.md) 
```

--------------------------------

### Skill Description Example

Source: https://commandcode.ai/docs/skills/best-practices

Use specific and keyword-rich descriptions to help Command Code determine when to use a skill. This example shows how to extract text and tables from PDF files.

```yaml
description: Extract text and tables from PDF files using pdfplumber. Use when user mentions PDFs, pdf files, document extraction, or needs to read PDF content. 
```

--------------------------------

### Natural Language Command Example

Source: https://commandcode.ai/docs/mcp/quickstart

An example of a natural language request that Command Code can process, demonstrating its ability to discover and use MCP tools.

```bash
Create a note on Notion named "API Design v2".
```

--------------------------------

### Describe Plan for Building

Source: https://commandcode.ai/docs/workflows

Use this prompt in plan mode to describe the desired feature, such as designing a role-based access control system, and explore the current setup.

```bash
> design a role-based access control system for the API — explore the current auth setup first 
```

--------------------------------

### Explore codebase architecture

Source: https://commandcode.ai/docs/workflows

After getting an overview, use this prompt to understand the architecture patterns and module connections within the codebase. This helps in grasping how different parts of the system interact.

```bash
> explain the architecture patterns used here and how the modules connect 
```

--------------------------------

### Start Command Code in Auto-Accept Mode (Long Form)

Source: https://commandcode.ai/docs/resources/security

An alternative, more explicit way to start a Command Code session in 'auto-accept' mode.

```bash
cmd --permission-mode auto-accept
```

--------------------------------

### Start Session with Specific Model

Source: https://commandcode.ai/docs/core-concepts/interactive-mode

Use the `--model` flag to start a session with a specific model. This is a session-scoped override and does not change the saved default.

```bash
cmd --model <model_id>
```

--------------------------------

### Example Custom Agent File

Source: https://commandcode.ai/docs/core-concepts/custom-agents

Defines a custom agent named 'security-review' with specific tools and a system prompt for security-focused reviews. This file should be placed in the .commandcode/agents/ or ~/.commandcode/agents/ directory.

```markdown
---
name: "security-review"
description: "Use for dependency and secret-scanning review before release."
tools: "glob, grep, read_file, think"
---

You are a security-focused reviewer. Prioritize dependency risks, secrets in code, and unsafe patterns. Be concise; cite file paths and lines. 
```

--------------------------------

### Skill Name Examples

Source: https://commandcode.ai/docs/skills/best-practices

Prefer task-oriented skill names that are unlikely to conflict with built-in commands or custom commands. Safe examples include 'pr-desc', 'api-guidelines', 'release-notes', and 'code-review'.

```yaml
Safe: pr-desc, api-guidelines, release-notes, code-review
Risky: clear, help, share, rewind — these are built-in.
```

--------------------------------

### List Global Packages

Source: https://commandcode.ai/docs/taste/commands/list

Lists all taste packages installed globally in `~/.commandcode/taste/`. Use the `-g` or `--global` flag to access these packages.

```bash
npx taste list -g 
```

--------------------------------

### Configure Multiple Hooks for an Event

Source: https://commandcode.ai/docs/hooks/configuration

This example shows how to wire multiple hooks under a single matcher for the 'PreToolUse' event. The hooks execute sequentially, with subsequent hooks being skipped if an earlier hook denies the action.

```json
{  "hooks": {  "PreToolUse": [  {  "matcher": "shell",  "hooks": [  { "type": "command", "command": "./.commandcode/hooks/guard-bash.sh", "timeout": 5 },  { "type": "command", "command": "./.commandcode/hooks/log-shell.sh" }  ]  }  ]  } }
```

--------------------------------

### Auto-install Command Code Extension

Source: https://commandcode.ai/docs/core-concepts/ide-integration

Launch Command Code from your IDE's integrated terminal to automatically install the extension. This is the recommended method.

```bash
cmd 
```

--------------------------------

### Start Command Code Session

Source: https://commandcode.ai/docs/mcp/quickstart

Initiates a Command Code session, allowing you to interact with configured MCP servers and tools.

```bash
cmd
```

--------------------------------

### Example output (with errors)

Source: https://commandcode.ai/docs/taste/commands/lint

This output shows validation failures, detailing the number of errors, specific line numbers, and the nature of the problems found.

```text
cli/taste.md ✗ 2 errors found    Line 5: Invalid confidence value (must be between 0 and 1)   Line 12: Missing required header  Summary: 2 errors, 0 warnings across 1 file ✗ Validation failed 
```

--------------------------------

### Example Taste File Structure (TypeScript)

Source: https://commandcode.ai/docs/skills/skills-vs-taste

Demonstrates the structure of a `taste.md` file, showing learned preferences for TypeScript, exports, and error handling. Confidence scores indicate the strength of observed patterns.

```markdown
1## TypeScript
2- Use strict mode. Confidence: 0.80
3- Prefer explicit return types on exported functions. Confidence: 0.65
4- Use type imports for type-only imports. Confidence: 0.90
5
6## Exports
7- Use named exports. Confidence: 0.85
8- Group related exports in barrel files. Confidence: 0.70
9- Avoid default exports except for page components. Confidence: 0.85
10
11## Error Handling
12- Use typed error classes. Confidence: 0.85
13- Always include error codes. Confidence: 0.90
14- Log to stderr, not stdout. Confidence: 0.75
```

--------------------------------

### Connect IDE using /ide Command

Source: https://commandcode.ai/docs/core-concepts/ide-integration

Run the `/ide` slash command within a Command Code session to check connection status, install the extension if needed, and view diagnostic information.

```bash
/ide 
```

--------------------------------

### Add Context7 MCP Server

Source: https://commandcode.ai/docs/mcp/examples

Adds the Context7 MCP server to connect to up-to-date developer documentation, dynamically fetching version-specific docs and code examples.

```bash
cmd mcp add context7 -- npx -y @upstash/context7-mcp
```

--------------------------------

### HTTP Server Configuration Schema

Source: https://commandcode.ai/docs/mcp/manage

Example of the configuration schema for an HTTP MCP server, including transport, URL, headers, and environment variables.

```json
{
  "mcpServers": {
    "my-server": {
      "transport": "http",
      "enabled": true,
      "url": "https://api.example.com/mcp",
      "headers": {
        "Authorization": "Bearer token"
      },
      "env": {
        "API_KEY": "value"
      }
    }
  }
}
```

--------------------------------

### Placeholder Usage Example

Source: https://commandcode.ai/docs/core-concepts/slash-commands

Demonstrates how different placeholders capture arguments passed to a slash command. $1 and $2 capture the first and second arguments respectively, while $ARGUMENTS captures all arguments as a single string.

```bash
/test unit Jest 
```

--------------------------------

### Stop Hook Execution Example

Source: https://commandcode.ai/docs/hooks/examples

Illustrates the output when a stop hook detects a 'DO NOT SHIP' marker, showing the error message and exit code.

```text
  Ran 1 stop hook   └ Stop hook [./.commandcode/hooks/no-ship-gate.sh] exited 2: Remove these 'DO NOT SHIP' markers before finishing: [retry 1/3] 
```

--------------------------------

### Check npm Global Bin Directory

Source: https://commandcode.ai/docs/troubleshooting/common-issues

Determine the prefix directory where npm installs global packages. Ensure this directory's 'bin' subfolder is in your system's PATH.

```bash
npm config get prefix
```

--------------------------------

### Example Output of taste pull

Source: https://commandcode.ai/docs/taste/commands/pull

Illustrates the typical output message after a successful 'taste pull' operation, indicating the status of pulled learnings and the save location.

```bash
✓ Pulled 'cli' from saqib (1 learning added, 2 unchanged) Saved to: .commandcode/taste/cli/taste.md
```

--------------------------------

### AGENTS.md Template Example

Source: https://commandcode.ai/docs/core-concepts/memory

This is a template for the AGENTS.md file, which allows you to define project overview, code style guidelines, architecture notes, and common workflows. Customize this template to suit your project's specific needs.

```markdown
# Memory  ## Project Overview  See @README.md for project overview and @package.json for available npm/pnpm commands for this project.  ## Code Style Guidelines  - Use descriptive variable names - Follow existing patterns in the codebase - Extract complex conditions into meaningful boolean variables  ## Architecture Notes  Add important architectural decisions and patterns here.  ## Common Workflows  Document frequently used workflows and commands here.  
```

--------------------------------

### Verify Command Code Install in WSL

Source: https://commandcode.ai/docs/troubleshooting/windows

Check the installed version of Command Code within the WSL environment.

```bash
cmdc --version 
```

--------------------------------

### Add MCP Server from JSON Configuration

Source: https://commandcode.ai/docs/mcp/quickstart

For complex setups, you can add an MCP server by providing its configuration as a JSON string. This allows for detailed settings like transport, URL, and headers.

```bash
cmd mcp add-json my-server '{   "transport": "http",   "url": "https://api.example.com/mcp",   "headers": {     "Authorization": "Bearer ${API_KEY}"   } }'
```

--------------------------------

### Command Usage with Positional Arguments

Source: https://commandcode.ai/docs/reference/slash-commands

Demonstrates how to use the 'create-component' command, providing values for the $1, $2, and $3 placeholders.

```bash
/create-component React Button "onClick and disabled props" 
```

--------------------------------

### Full Hook Script Example

Source: https://commandcode.ai/docs/hooks/reference

This bash script demonstrates a pre-tool-use hook that inspects the command input. It denies destructive commands like 'rm -rf /' and allows other commands while adding context. It reads session and command details from stdin, processes them using jq, and outputs a JSON payload to control execution flow and provide feedback to the model.

```bash
#!/usr/bin/env bash
set -euo pipefail

# Read the entire stdin payload once.
payload=$(cat)

# Common fields on every event.
session_id=$(printf '%s' "$payload" | jq -r '.session_id')
cwd=$(printf '%s' "$payload" | jq -r '.cwd')
event=$(printf '%s' "$payload" | jq -r '.hook_event_name')

# Tool-call fields, present on every tool event.
tool_name=$(printf '%s' "$payload" | jq -r '.tool_name')
tool_display=$(printf '%s' "$payload" | jq -r '.tool_display_name')
cmd=$(printf '%s' "$payload" | jq -r '.tool_input.command // ""')

# Command Code also injects env vars for the same context.
: "${COMMANDCODE_PROJECT_DIR:?}"
: "${COMMANDCODE_SESSION_ID:?}"
: "${COMMANDCODE_HOOK_EVENT:?}"

# Deny a destructive command with a reason the model will see.
if [[ "$cmd" == *"rm -rf /"* ]]; then
  jq -n --arg cmd "$cmd" '{ \
    continue: true, \
    systemMessage: "Blocked destructive command", \
    hookSpecificOutput: { \
      hookEventName: "PreToolUse", \
      permissionDecision: "deny", \
      permissionDecisionReason: ("Policy forbids: " + $cmd) \
    } \
  }'

exit 0
fi

# Otherwise allow and attach extra context for the model's next turn.
jq -n --arg event "$event" '{ \
  continue: true, \
  hookSpecificOutput: { \
    hookEventName: "PreToolUse", \
    permissionDecision: "allow", \
    additionalContext: ("Verified by guard-shell.sh during " + $event) \
  } \
}'
```

--------------------------------

### Focused Skill Examples

Source: https://commandcode.ai/docs/skills/best-practices

Each skill should perform a single, well-defined task. Examples of focused skills include 'code-review', 'commit-messages', and 'testing-patterns'.

```yaml
  * `code-review` - Code review checklist
  * `commit-messages` - Commit message format
  * `testing-patterns` - Testing conventions
```

--------------------------------

### Command Usage with $ARGUMENTS

Source: https://commandcode.ai/docs/reference/slash-commands

Demonstrates how to use the 'explain' command, passing a query as a single string argument that will be captured by $ARGUMENTS.

```bash
/explain how async await works in JavaScript 
```

--------------------------------

### Example of feeding stderr to the model on retry

Source: https://commandcode.ai/docs/hooks/reference

When a hook exits with code 2, its stderr is fed to the model. This example shows how to simulate this by echoing a message to stderr.

```shell
echo "tsc: 3 errors found" >&2
exit 2
```

--------------------------------

### Enter Plan Mode

Source: https://commandcode.ai/docs/workflows

Initiates plan mode for exploring the codebase and designing an implementation approach before making any file changes.

```bash
cmd --plan 
```

--------------------------------

### Interactive Conversation Picker Example

Source: https://commandcode.ai/docs/workflows

An example of the interactive picker interface for selecting a past conversation, showing details like modification time, message count, and summary.

```text
          Modified       # Messages   Git Branch            Summary   ❯ 1.     20 hours ago   172          main                  Follow this practice and up...    2.     21 hours ago   13           main                  Add the common workflows he...    3.     22 hours ago   2            main                  does this {src/components/u...    4.     22 hours ago   82           main                  pnpm dlx shadcn@latest add ...    5.     1 day ago      2            ankit/features        all tools support  you have    6.     2 days ago     20           ankit/commands        Update the content in each ... 
```

--------------------------------

### Create User-Level Skill Directory and SKILL.md

Source: https://commandcode.ai/docs/skills/manage

This command creates a directory for a user-level skill and a basic `SKILL.md` file with name and description metadata.

```bash
# Create the directory
mkdir -p ~/.commandcode/skills/my-skill  # Create the SKILL.md file  cat > ~/.commandcode/skills/my-skill/SKILL.md << 'EOF'  --- name: my-skill description: What this skill does and when to use it ---  # My Skill  Instructions for Claude... EOF 
```

--------------------------------

### Open a Local Taste Package

Source: https://commandcode.ai/docs/taste/commands/open

Opens the 'cli' taste package from your local project directory in your default editor.

```bash
npx taste open cli
```

--------------------------------

### Basic Usage of taste open

Source: https://commandcode.ai/docs/taste/commands/open

Use this command to open a specified taste package in your default editor. Replace `<package>` with the name of the package.

```bash
npx taste open <package>
```

--------------------------------

### Initialize AGENTS.md File

Source: https://commandcode.ai/docs/core-concepts/memory

Use the `/init` command to create a new AGENTS.md file in your project root. This file serves as a template for customizing Command Code's behavior for your project. Remember to commit this file to your Git repository.

```bash
/init 
```

--------------------------------

### Invalid Skill Names

Source: https://commandcode.ai/docs/skills/manage

Examples of bad skill names that violate the naming conventions.

```text
CodeReview       # uppercase not allowed
code_review      # underscores not allowed
-code-review     # cannot start with hyphen
code--review     # consecutive hyphens
```

--------------------------------

### Pull from Global

Source: https://commandcode.ai/docs/taste/commands

Retrieves a taste package from your global configuration into the current project. Use the -g flag.

```bash
npx taste pull cli -g 
```

--------------------------------

### Standard vs. Conditioned Generation

Source: https://commandcode.ai/docs/skills/skills-vs-taste

Illustrates the difference between standard LLM generation and conditioned generation using taste. Conditioned generation shapes the output distribution based on user-specific constraints.

```text
1// Standard generation
2output = LLM(prompt)
3
4// Conditioned generation with taste
5output = LLM(prompt | taste(user))
```

--------------------------------

### Get Specific MCP Server Details

Source: https://commandcode.ai/docs/mcp/quickstart

Inspect the configuration and status of a particular MCP server by its name.

```bash
cmd mcp get notion
```

--------------------------------

### Create API Guidelines Skill

Source: https://commandcode.ai/docs/skills/manage

Creates a new skill directory for API guidelines and defines its metadata and content in SKILL.md.

```bash
mkdir -p .commandcode/skills/api-guidelines
cat > .commandcode/skills/api-guidelines/SKILL.md << 'EOF'
---
name: api-guidelines
description: API design patterns and conventions for this project
---

# API Guidelines

## Endpoint naming
- Use plural nouns: `/users`, `/posts`
- Use kebab-case: `/user-profiles`
- Version in URL: `/v1/users`

## Response format
Always return JSON with this structure:
```json
{
  "data": { ... },
  "meta": { "count": 10, "page": 1 },
  "errors": []
}
```

## Error codes
- 400: Bad request (validation errors)
- 401: Unauthorized (missing/invalid token)
- 403: Forbidden (insufficient permissions)
- 404: Not found
- 500: Server error

## Authentication
All endpoints require Bearer token in Authorization header except:
- POST /v1/auth/login
- POST /v1/auth/register
EOF
```

--------------------------------

### Valid Skill Names

Source: https://commandcode.ai/docs/skills/manage

Examples of good skill names adhering to the naming conventions (lowercase, numbers, hyphens).

```text
code-review
api-guidelines
testing-patterns
commit-messages
```

--------------------------------

### Comment on Pull Request

Source: https://commandcode.ai/docs/workflows

Add a comment to a pull request, for example, to note missing error handling in a specific handler.

```bash
> add a comment on the PR about the missing error handling in the webhook handler 
```

--------------------------------

### Create Project-Level Skill Directory and SKILL.md

Source: https://commandcode.ai/docs/skills/manage

This command creates a directory for a project-level skill within the project's `.commandcode/skills/` directory and a basic `SKILL.md` file.

```bash
# Create the directory
mkdir -p .commandcode/skills/my-skill  # Create the SKILL.md file  cat > .commandcode/skills/my-skill/SKILL.md << 'EOF' --- name: my-skill description: What this skill does and when to use it ---  # My Skill  Instructions for Claude... EOF 
```

--------------------------------

### Run Command Code in Project

Source: https://commandcode.ai/docs

Navigate to your project directory and run the Command Code CLI.

```bash
cd your-project && cmd
```

--------------------------------

### Lint all packages from global

Source: https://commandcode.ai/docs/taste/commands/lint

Validates all taste packages installed globally. This command checks all taste packages available in your global environment.

```bash
npx taste lint --all -g 
```

--------------------------------

### Basic Usage of taste pull

Source: https://commandcode.ai/docs/taste/commands/pull

Demonstrates the fundamental syntax for pulling a taste package from a remote namespace and package.

```bash
npx taste pull <namespace>/<package> [options]
```

--------------------------------

### Lint a specific package from global

Source: https://commandcode.ai/docs/taste/commands/lint

Validates a specific taste package installed globally. Use this to check globally available packages.

```bash
npx taste lint cli -g 
```

--------------------------------

### List Project Packages

Source: https://commandcode.ai/docs/taste/commands/list

Lists all taste packages within the current project's `.commandcode/taste/` directory. This is the default behavior when no options are specified.

```bash
npx taste list 
```

--------------------------------

### List Available Models

Source: https://commandcode.ai/docs/core-concepts/interactive-mode

Run `cmd --list-models` to see all available model IDs that can be used.

```bash
cmd --list-models
```

--------------------------------

### Push Individual Package to Global

Source: https://commandcode.ai/docs/taste/commands/push

Uploads a specific package to the global taste directory on the local machine, making it accessible across all projects.

```bash
npx taste push cli -g 
```

--------------------------------

### Open Skills Browser

Source: https://commandcode.ai/docs/skills/manage

Use the `/skills` command in an interactive session to open the skills browser. Navigate with arrow keys and press Enter to open a skill in the editor.

```bash
# In Command Code interactive session /skills 
```

--------------------------------

### Manage Disabled Skills Configuration

Source: https://commandcode.ai/docs/skills/manage

Disabled skills are tracked in a `settings.json` file. This JSON snippet shows an example of how to list disabled skills.

```json
{  "disabledSkills": ["blogster", "r0"] }
```

--------------------------------

### Open a Global Taste Package

Source: https://commandcode.ai/docs/taste/commands/open

Opens the 'cli' taste package from your global taste directory (~/.commandcode/taste) in your default editor.

```bash
npx taste open cli -g
```

--------------------------------

### Summarize Changes

Source: https://commandcode.ai/docs/workflows

Use this command to get a summary of changes made to a specific module, useful for reviewing code before creating a pull request.

```bash
> summarize the changes I've made to the auth module and check for anything I missed 
```

--------------------------------

### Run First Prompt with Command Code

Source: https://commandcode.ai/docs/quickstart

Execute your first prompt in Command Code to build a date.js CLI using commander.js and pnpm.

```bash
Build a date.js CLI that tells ISO format of date. Use commander.js and pnpm. 
```

--------------------------------

### Set External Editor Environment Variable

Source: https://commandcode.ai/docs/workflows

Configures the default external editor for CommandCode AI. Examples include 'vim' or 'code --wait'.

```bash
export EDITOR=vim
```

```bash
export EDITOR="code --wait"
```

--------------------------------

### Open External Editor for Prompts

Source: https://commandcode.ai/docs/workflows

Opens your configured external editor for writing multi-line prompts. This is useful for complex prompts including code examples.

```bash
ctrl+g
```

--------------------------------

### Referencing Supporting Files in SKILL.md

Source: https://commandcode.ai/docs/skills/manage

Demonstrates how to link to supporting documentation and execute scripts from within the SKILL.md file.

```markdown
See [API Reference](references/API_REFERENCE.md) for details.

Run the validation script:
```bash
scripts/validate.sh
```
```

--------------------------------

### Push and Make Public

Source: https://commandcode.ai/docs/taste/commands/push

Uploads the package and makes it publicly discoverable by other Command Code users.

```bash
npx taste push cli --public 
```

--------------------------------

### MCP Tool Naming Convention

Source: https://commandcode.ai/docs/mcp

MCP tools follow the naming convention `mcp__<server>__<tool>`. Examples include `mcp__notion__search_page` and `mcp__github__create_issue`.

```bash
mcp__notion__search_page mcp__github__create_issue 
```

--------------------------------

### Using Quoted Arguments in Slash Commands

Source: https://commandcode.ai/docs/core-concepts/slash-commands

Arguments containing spaces must be wrapped in quotes. This example shows how arguments are parsed into numbered placeholders.

```bash
/create-component React "Login Form" "email validation and submit handler" 
```

--------------------------------

### Create a User-Level Command

Source: https://commandcode.ai/docs/reference/slash-commands

This command creates a user-level slash command named 'understand'. It is saved in the ~/.commandcode/commands/ directory and is available across all projects.

```bash
# Create a user-level command mkdir -p ~/.commandcode/commands echo "I am currently being onboarded on this project, help me understand it." > ~/.commandcode/commands/understand.md
```

--------------------------------

### Managing Taste Profiles with CLI

Source: https://commandcode.ai/docs/skills/skills-vs-taste

Shows commands for interacting with taste profiles using the `taste` CLI. This includes pushing local taste to a registry and pulling shared taste profiles into a project.

```bash
1# Push your project taste to the registry
2npx taste push --all
3
4# Pull someone's CLI taste into your project
5npx taste pull ahmadawais/cli
```

--------------------------------

### Example Trace ID for Bug Reporting

Source: https://commandcode.ai/docs/troubleshooting/telemetry

When reporting bugs, Command Code may display a Trace ID. Share this ID to help with issue investigation.

```text
Trace ID: abc123...
```

--------------------------------

### Configure Command Code Settings

Source: https://commandcode.ai/docs/core-concepts/interactive-mode

Modify Command Code's behavior by editing the `settings.json` file. This example shows how to disable the collapsing of pasted text.

```json
{
  "input": {
    "collapsePastedText": false
  }
}
```

--------------------------------

### Get Design Review and Critique

Source: https://commandcode.ai/docs/design

Provides a scored critique of a specified page or component, including a walkthrough and suggested fixes. Ideal for detailed feedback before shipping.

```bash
/design review src/pages/landing.tsx
```

--------------------------------

### Design Command Usage

Source: https://commandcode.ai/docs/design

Illustrates the basic usage of the /design command, including its modes and optional target arguments. Freeform prompts are also supported.

```bash
/design <mode> [target] 
Freeform prompts work too: /design make this hero stronger 
/design help shows the full usage guide
```

--------------------------------

### Adding Supporting Files to a Skill

Source: https://commandcode.ai/docs/skills/manage

Shows how to include additional files like scripts, references, and assets within a skill's directory.

```tree
my-skill/
├── SKILL.md          # Required
├── scripts/          # Executable code
│   ├── process.py
│   └── validate.sh
├── references/       # Additional docs
│   ├── API_REFERENCE.md
│   └── EXAMPLES.md
└── assets/           # Templates, resources
    ├── template.json
    └── schema.sql
```

--------------------------------

### Reference a directory for structure explanation

Source: https://commandcode.ai/docs/workflows

Include directories using '@' to understand their structure and how files within them relate. This is useful for grasping the organization of API routes or other modules.

```bash
> look at @src/app/api and explain the route structure 
```