docs: edit commands

This commit is contained in:
Jay V
2025-08-26 14:03:56 -04:00
parent f4b69df7a3
commit 11de2e59f3
3 changed files with 218 additions and 70 deletions

View File

@@ -3,7 +3,13 @@ title: Commands
description: Create custom commands for repetitive tasks.
---
Define custom commands to automate repetitive coding tasks.
Custom commands let you specify a prompt you want to run when that command is executed in the TUI.
```bash frame="none"
/my-command
```
Custom commands are in addition to the built-in commands like `/init`, `/undo`, `/redo`, `/share`, `/help`. [Learn more](/docs/tui#commands).
---
@@ -34,12 +40,78 @@ Use the command by typing `/` followed by the command name.
---
## Use arguments
## Configure
You can add custom commands through the opencode config or by creating markdown files in the `command/` directory.
---
### JSON
Use the `command` option in your opencode [config](/docs/config):
```json title="opencode.jsonc" {4-12}
{
"$schema": "https://opencode.ai/config.json",
"command": {
// This becomes the name of the command
"test": {
// This is the prompt that will be sent to the LLM
"template": "Run the full test suite with coverage report and show any failures.\nFocus on the failing tests and suggest fixes.",
// This is show as the description in the TUI
"description": "Run tests with coverage",
"agent": "build",
"model": "anthropic/claude-3-5-sonnet-20241022"
},
}
}
```
Now you can run this command in the TUI:
```bash frame="none"
/test
```
---
### Markdown
You can also define commands using markdown files. Place them in:
- Global: `~/.config/opencode/command/`
- Per-project: `.opencode/command/`
```markdown title="~/.config/opencode/command/test.md"
---
description: Run tests with coverage
agent: build
model: anthropic/claude-3-5-sonnet-20241022
---
Run the full test suite with coverage report and show any failures.
Focus on the failing tests and suggest fixes.
```
The markdown file name becomes the command name. For example, `test.md` lets
you run:
```bash frame="none"
/test
```
---
## Prompt config
The prompts for the custom commands support several special placeholders and syntax.
---
### Arguments
Pass arguments to commands using the `$ARGUMENTS` placeholder.
Create `.opencode/command/component.md`:
```md title=".opencode/command/component.md"
---
description: Create a new component
@@ -52,16 +124,18 @@ Include proper typing and basic structure.
Run the command with arguments:
```bash frame="none"
"/component Button"
/component Button
```
And `$ARGUMENTS` will be replaced with `Button`.
---
## Inject shell output
### Shell output
Use !`command` to inject shell command output into your prompt.
Use _!`command`_ to inject [bash command](/docs/tui#bash-commands) output into your prompt.
Create `.opencode/command/analyze-coverage.md`:
For example, to create a custom command that analyzes test coverage:
```md title=".opencode/command/analyze-coverage.md"
---
@@ -74,7 +148,7 @@ Here are the current test results:
Based on these results, suggest improvements to increase coverage.
```
Create `.opencode/command/review-changes.md`:
Or to review recent changes:
```md title=".opencode/command/review-changes.md"
---
@@ -91,12 +165,10 @@ Commands run in your project's root directory and their output becomes part of t
---
## Reference files
### File references
Include files in your command using `@` followed by the filename.
Create `.opencode/command/review-component.md`:
```md title=".opencode/command/review-component.md"
---
description: Review component
@@ -110,47 +182,90 @@ The file content gets included in the prompt automatically.
---
## Command properties
## Options
Configure commands with these optional frontmatter properties:
Let's look at the configuration options in detail.
- **description**: Brief explanation of what the command does
- **agent**: Agent to use (defaults to "build")
- **model**: Specific model to use for this command
Create `.opencode/command/code-review.md`:
```md title=".opencode/command/code-review.md"
---
description: Code review assistant
agent: build
model: anthropic/claude-3-5-sonnet-20241022
---
Review the code for best practices and suggest improvements.
### Template
The `template` option defines the prompt that will be sent to the LLM when the command is executed.
```json title="opencode.json"
{
"command": {
"test": {
"template": "Run the full test suite with coverage report and show any failures.\nFocus on the failing tests and suggest fixes."
}
}
}
```
---
## Command directory
Store command files in these locations:
- `.opencode/command/` - Project-specific commands
- `command/` - Global commands in config directory
Project commands take precedence over global ones.
This is a **required** config option.
---
## Built-in commands
### Description
opencode includes several built-in commands:
Use the `description` option to provide a brief description of what the command does.
- `/init` - Initialize project and create AGENTS.md
- `/undo` - Revert the last changes
- `/redo` - Restore reverted changes
- `/share` - Share the current conversation
- `/help` - Show available commands and keybinds
```json title="opencode.json"
{
"command": {
"test": {
"description": "Run tests with coverage"
}
}
}
```
Use `/help` to see all available commands in your setup.
This is shown as the description in the TUI when you type in the command.
---
### Agent
Use the `agent` config to optionally specify which [agent](/docs/agents) should execute this command.
```json title="opencode.json"
{
"command": {
"review": {
"agent": "plan"
}
}
}
```
This is an **optional** config option. If not specified, defaults to "build".
---
### Model
Use the `model` config to override the default model for this command.
```json title="opencode.json"
{
"command": {
"analyze": {
"model": "anthropic/claude-3-5-sonnet-20241022"
}
}
}
```
This is an **optional** config option.
---
## Built-in
opencode includes several built-in commands like `/init`, `/undo`, `/redo`, `/share`, `/help`; [learn more](/docs/tui#commands).
:::note
Custom commands can override built-in commands.
:::
If you define a custom command with the same name, it will override the built-in command.

View File

@@ -152,6 +152,32 @@ By default, sharing is set to manual mode where you need to explicitly share con
---
### Commands
You can configure custom commands for repetitive tasks through the `command` option.
```jsonc title="opencode.jsonc"
{
"$schema": "https://opencode.ai/config.json",
"command": {
"test": {
"template": "Run the full test suite with coverage report and show any failures.\nFocus on the failing tests and suggest fixes.",
"description": "Run tests with coverage",
"agent": "build",
"model": "anthropic/claude-3-5-sonnet-20241022"
},
"component": {
"template": "Create a new React component named $ARGUMENTS with TypeScript support.\nInclude proper typing and basic structure.",
"description": "Create a new component"
}
}
}
```
You can also define commands using markdown files in `~/.config/opencode/command/` or `.opencode/command/`. [Learn more here](/docs/commands).
---
### Keybinds
You can customize your keybinds through the `keybinds` option.
@@ -220,6 +246,11 @@ You can configure permissions to control what AI agents can do in your codebase
}
```
This allows you to configure explicit approval requirements for sensitive operations:
- `edit` - Controls whether file editing operations require user approval (`"ask"` or `"allow"`)
- `bash` - Controls whether bash commands require user approval (can be `"ask"`/`"allow"` or a pattern map)
[Learn more about permissions here](/docs/permissions).
---
@@ -259,13 +290,6 @@ about rules here](/docs/rules).
You can disable providers that are loaded automatically through the `disabled_providers` option. This is useful when you want to prevent certain providers from being loaded even if their credentials are available.
The `disabled_providers` option accepts an array of provider IDs. When a provider is disabled:
- It won't be loaded even if environment variables are set
- It won't be loaded even if API keys are configured through `opencode auth login`
- The provider's models won't appear in the model selection list
```json title="opencode.json"
{
"$schema": "https://opencode.ai/config.json",
@@ -273,12 +297,11 @@ The `disabled_providers` option accepts an array of provider IDs. When a provide
}
```
The permissions system allows you to configure explicit approval requirements for sensitive operations:
The `disabled_providers` option accepts an array of provider IDs. When a provider is disabled:
- `edit` - Controls whether file editing operations require user approval (`"ask"` or `"allow"`)
- `bash` - Controls whether bash commands require user approval (can be `"ask"`/`"allow"` or a pattern map)
[Learn more about permissions here](/docs/permissions).
- It won't be loaded even if environment variables are set.
- It won't be loaded even if API keys are configured through `opencode auth login`.
- The provider's models won't appear in the model selection list.
---

View File

@@ -25,6 +25,12 @@ Once you're in the TUI, you can prompt it with a message.
Give me a quick summary of the codebase.
```
---
## File references
You can reference files in your messages using `@`. This does a fuzzy file search in the current working directory.
:::tip
You can also use `@` to reference files in your messages.
:::
@@ -33,6 +39,20 @@ You can also use `@` to reference files in your messages.
How is auth handled in @packages/functions/src/api/index.ts?
```
The content of the file is added to the conversation automatically.
---
## Bash commands
Start a message with `!` to run a shell command.
```bash frame="none"
!ls -la
```
The output of the command is added to the conversation as a tool result.
---
## Commands
@@ -235,18 +255,6 @@ Unshare current session. [Learn more](/docs/share#un-sharing).
---
## Bash commands
Start a message with `!` to run a shell command.
```bash frame="none"
!ls -la
```
The output of the command is added to the conversation as a tool result.
---
## Editor setup
Both the `/editor` and `/export` commands use the editor specified in your `EDITOR` environment variable.
@@ -300,6 +308,8 @@ Popular editor options include:
- `notepad` - Windows Notepad
- `subl` - Sublime Text
:::tip
Some editors need command-line arguments to run in blocking mode. The --wait flag makes the editor process block until closed, which is necessary for opencode to function correctly.
:::note
Some editors like VS Code need to be started with the `--wait` flag.
:::
Some editors need command-line arguments to run in blocking mode. The `--wait` flag makes the editor process block until closed.