### Install Forge CLI

Source: https://github.com/tailcallhq/forgecode/blob/main/README.md

Installs the Forge command-line interface. This is the initial step to get Forge running on your system.

```bash
curl -fsSL https://forgecode.dev/cli | sh
```

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

### Session Flow Example

Source: https://github.com/tailcallhq/forgecode/blob/main/shell-plugin/README.md

Shows a typical session flow, starting with a general topic, asking specific questions, referencing files, and then starting a new conversation.

```bash
: I'm working on a Rust web API
: What are the best practices for error handling?
: Show me an example with @[src/errors.rs]
:info
:new
: New conversation starts here
```

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

### PDF Processing Quick Start Example

Source: https://github.com/tailcallhq/forgecode/blob/main/crates/forge_repo/src/skills/create-skill/SKILL.md

Demonstrates how to extract text from a PDF using the pdfplumber library. This is a basic example for getting started.

```markdown
# PDF Processing

## Quick start

Extract text with pdfplumber:
[code example]
```

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

### Documentation Query Test Case Example

Source: https://github.com/tailcallhq/forgecode/blob/main/benchmarks/evals/semantic_search_quality/README.md

Example of a test case for finding documentation, specifying expected and to-be-avoided file types.

```yaml
- task: "Find documentation on how to configure semantic search"
  intent: "documentation"
  expected_file_types: "markdown,txt"
  should_avoid: "rust,typescript,javascript"
```

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

### Forge YAML Configuration Example

Source: https://github.com/tailcallhq/forgecode/blob/main/README.md

Example Forge YAML configuration snippets for different AI models.

```yaml
# forge.yaml
model: meta-llama/Llama-3.3-70B-Instruct
```

```yaml
# forge.yaml
model: o3-mini-high
```

```yaml
# forge.yaml
model: claude-3.7-sonnet
```

```yaml
# forge.yaml
model: google/gemini-2.5-pro
```

```yaml
# forge.yaml
model: <provider-specific-model>
```

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

### Implementation Query Test Case Example

Source: https://github.com/tailcallhq/forgecode/blob/main/benchmarks/evals/semantic_search_quality/README.md

Example of a test case for finding implementation code, specifying expected and to-be-avoided file types.

```yaml
- task: "Find the retry mechanism with exponential backoff implementation"
  intent: "implementation"
  expected_file_types: "rust,typescript,javascript"
  should_avoid: "markdown,txt,documentation"
```

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

### Google Vertex AI Setup and Configuration (Deprecated)

Source: https://github.com/tailcallhq/forgecode/blob/main/README.md

Legacy environment variable setup for Google Vertex AI. This method is deprecated; use `forge provider login` instead. Requires project ID, location, and an auth token.

```bash
# .env
PROJECT_ID=<your_project_id>
LOCATION=<your_location>
VERTEX_AI_AUTH_TOKEN=<your_auth_token>
```

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

### Basic Command Examples

Source: https://github.com/tailcallhq/forgecode/blob/main/shell-plugin/README.md

Illustrates basic usage of the Forge shell plugin for various tasks like asking questions, explaining concepts, and planning projects.

```bash
: What's the weather like?
:sage Explain the MVC pattern
:planner Help me structure this project
```

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

### Install fd - Fast File Finder

Source: https://github.com/tailcallhq/forgecode/blob/main/shell-plugin/README.md

Installs the 'fd' command-line tool, a prerequisite for the Forge ZSH plugin, on Ubuntu/Debian systems.

```bash
# Ubuntu/Debian
sudo apt install fd-find
```

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

### Start Forge Application

Source: https://github.com/tailcallhq/forgecode/blob/main/README.md

Launches the Forge application after provider credentials have been configured. Forge will then be ready to assist with development tasks.

```bash
forge
```

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

### Install fd - Fast File Finder

Source: https://github.com/tailcallhq/forgecode/blob/main/shell-plugin/README.md

Installs the 'fd' command-line tool, a prerequisite for the Forge ZSH plugin, on macOS using Homebrew.

```bash
# macOS (using Homebrew)
brew install fd
```

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

### Task Configuration Example

Source: https://github.com/tailcallhq/forgecode/blob/main/benchmarks/evals/semantic_search_quality/README.md

Example of how to define a new task for semantic search evaluation in task.yml. Specify the task description, intent, expected file types, and file types to avoid.

```yaml
task: "Your task description"
intent: "implementation|flow_understanding|tests|documentation|debugging|modification|architecture|configuration"
expected_file_types: "comma,separated,extensions"
should_avoid: "comma,separated,extensions"
```

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

### Test Data Example (CSV)

Source: https://github.com/tailcallhq/forgecode/blob/main/benchmarks/README.md

Create a CSV file with columns matching your template variables for test cases.

```csv
prompt,expected_output
"Create a backup script","backup.sh"
"Generate API client","api_client.py"
```

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

### Install Forge CLI

Source: https://github.com/tailcallhq/forgecode/blob/main/README.md

Commands for installing the Forge CLI using curl or package managers.

```bash
# YOLO
curl -fsSL https://forgecode.dev/cli | sh
```

```bash
# Package managers
nix run github:tailcallhq/forgecode # for latest dev branch
```

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

### Flow Understanding Query Test Case Example

Source: https://github.com/tailcallhq/forgecode/blob/main/benchmarks/evals/semantic_search_quality/README.md

Example of a test case for understanding system flows, detailing expected and to-be-avoided file types.

```yaml
- task: "How does the authentication flow work from request to response?"
  intent: "flow_understanding"
  expected_file_types: "rust,typescript"
  should_avoid: "test,markdown"
```

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

### Install fd - Fast File Finder

Source: https://github.com/tailcallhq/forgecode/blob/main/shell-plugin/README.md

Installs the 'fd' command-line tool, a prerequisite for the Forge ZSH plugin, on Arch Linux.

```bash
# Arch Linux
sudo pacman -S fd
```

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

### Command Examples with File Tagging

Source: https://github.com/tailcallhq/forgecode/blob/main/shell-plugin/README.md

Demonstrates how to use file tagging with the '@[filename]' syntax to reference specific files in your commands. This is useful for code review, debugging, and configuration tasks.

```bash
: Review this implementation @[src/auth.rs]
: Debug the issue in @[logs/error.log] @[config/app.yml]
```

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

### Rust User Struct Initialization Examples

Source: https://github.com/tailcallhq/forgecode/blob/main/crates/forge_domain/src/snapshots/forge_domain__conversation_html__tests__conversation.snap.html

Illustrates preferred methods for initializing Rust structs using default, new, and custom test constructors, contrasting them with less idiomatic approaches.

```rust
User::default().age(12).is_happy(true).name("John")
User::new("Job").age(12).is_happy()
User::test() // Special test constructor
```

```rust
User {name: "John".to_string(), is_happy: true, age: 12}
User::with_name("Job") // Bad name, should stick to User::new() or User::test()
```

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

### Task Definition Example

Source: https://github.com/tailcallhq/forgecode/blob/main/benchmarks/README.md

Defines how to run an evaluation, including pre-run commands, the command to execute, parallelism, timeout, and validations.

```yaml
# Optional: Commands to run before evaluation starts
before_run:
  - cargo build
  - npm install

# Required: Command(s) to execute for each test case
# Single command
run: forgee -p '{{prompt}}'

# Or multiple commands (executed sequentially)
run:
  - echo "Step 1: {{task}}"
  - forgee -p '{{prompt}}'
  - echo "Step 2: Complete"

# Execution configuration
parallelism: 10  # Number of tasks to run in parallel (default: 1)
timeout: 60      # Timeout in seconds (optional)
early_exit: true # Stop execution when validations pass (optional)

# Optional: Validations to run on output
validations:
  - name: "Check success message"
    type: regex
    regex: "\[[0-9:]*\] Skill create-skill"

# Required: Data sources for test cases
sources:
  - csv: my_tasks.csv
```

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

### Start Interactive Forge Session with Specific Agent

Source: https://github.com/tailcallhq/forgecode/blob/main/README.md

Start an interactive Forge session with a specific agent pre-selected.

```bash
forge --agent <agent-id>
```

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

### Start Forge Session in Specific Directory

Source: https://github.com/tailcallhq/forgecode/blob/main/README.md

Initiate a Forge session, specifying the project directory to work within.

```bash
forge -C /path/to/project
```

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

### Rust Test Structure with Pretty Assertions

Source: https://github.com/tailcallhq/forgecode/blob/main/AGENTS.md

Illustrates the standard three-step process for writing Rust tests: setup, execution, and assertion. Always use `pretty_assertions` for enhanced error reporting.

```rust
use pretty_assertions::assert_eq; // Always use pretty assertions

fn test_foo() {
    let setup = ...; // Instantiate a fixture or setup for the test
    let actual = ...; // Execute the fixture to create an output
    let expected = ...; // Define a hand written expected result
    assert_eq!(actual, expected); // Assert that the actual result matches the expected result
}
```

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

### Groq API Key and URL Configuration (Deprecated)

Source: https://github.com/tailcallhq/forgecode/blob/main/README.md

Legacy environment variable setup for Groq. This method is deprecated; use `forge provider login` instead. Uses OpenAI compatible keys and a specific URL.

```bash
# .env
OPENAI_API_KEY=<your_groq_api_key>
OPENAI_URL=https://api.groq.com/openai/v1
```

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

### Setting Initial Parallelism

Source: https://github.com/tailcallhq/forgecode/blob/main/benchmarks/README.md

Advises starting with a low `parallelism` value (e.g., 1) in Forge for testing and gradually increasing it. This helps in debugging and performance tuning.

```yaml
parallelism: 1  # Start here
```

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

### Agent Context Compaction Configuration Example

Source: https://github.com/tailcallhq/forgecode/blob/main/plans/agent-context-compaction-2025-03-24-concise.md

Example of how to configure agent context compaction in the forge.yaml file. This configuration sets a maximum token limit and defines triggers for compaction based on token count, turn count, and message count.

```yaml
# Example in forge.yaml
agents:
  myAgent:
    id: myAgent
    model: gpt-4-turbo
    system_prompt: "You are a helpful assistant."
    compact:
      max_tokens: 4000
      token_threshold: 6000
      turn_threshold: 10
      message_threshold: 30

```

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

### Sample Error Response for Binary File Detection

Source: https://github.com/tailcallhq/forgecode/blob/main/plans/2025-04-27-large-file-read-range-support-v4.md

Example JSON response when a binary file is detected and not supported.

```json
{
  "error": "Binary files are not supported. File detected as image/png. Please use another tool or method to process this file."
}
```

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

### Simple Sequential Execution Example

Source: https://github.com/tailcallhq/forgecode/blob/main/benchmarks/README.md

A basic Forge task that sequentially executes a command for each item in a CSV source. Use this for straightforward, step-by-step processing.

```yaml
run: echo "Processing {{name}}"
sources:
  - csv: names.csv
```

```csv
name
Alice
Bob
Charlie
```

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

### Anti-pattern: Cumbersome Usage Example

Source: https://github.com/tailcallhq/forgecode/blob/main/AGENTS.md

Demonstrates the cumbersome usage that results from services with too many generic parameters and explicit type bounds in the constructor.

```rust
// BAD: Usage becomes cumbersome
let service = BadUserService::<PostgresRepo, RedisCache, FileLogger>::new(...);
```

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

### Amazon Bedrock Setup with Forge

Source: https://github.com/tailcallhq/forgecode/blob/main/README.md

Configure Forge to use Amazon Bedrock models via the Bedrock Access Gateway. Requires setting up the gateway and providing its API base URL.

```bash
forge provider login
# Select OpenAI-compatible provider and enter your Bedrock Gateway details
```

```dotenv
# .env
OPENAI_API_KEY=<your_bedrock_gateway_api_key>
OPENAI_URL=<your_bedrock_gateway_base_url>
```

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

### OpenAI-Compatible Providers Configuration (Deprecated)

Source: https://github.com/tailcallhq/forgecode/blob/main/README.md

Legacy environment variable setup for OpenAI-compatible providers. This method is deprecated; use `forge provider login` instead. Requires API key and URL.

```bash
# .env
OPENAI_API_KEY=<your_provider_api_key>
OPENAI_URL=<your_provider_url>
```

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

### x-ai API Key Configuration (Deprecated)

Source: https://github.com/tailcallhq/forgecode/blob/main/README.md

Legacy environment variable setup for x-ai. This method is deprecated; use `forge provider login` instead. Ensure the API key is correctly formatted.

```bash
# .env
XAI_API_KEY=<your_xai_api_key>
```

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

### OpenAI API Key Configuration (Deprecated)

Source: https://github.com/tailcallhq/forgecode/blob/main/README.md

Legacy environment variable setup for OpenAI. This method is deprecated; use `forge provider login` instead. Ensure the API key is correctly formatted.

```bash
# .env
OPENAI_API_KEY=<your_openai_api_key>
```

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

### Requesty API Key Configuration (Deprecated)

Source: https://github.com/tailcallhq/forgecode/blob/main/README.md

Legacy environment variable setup for Requesty. This method is deprecated; use `forge provider login` instead. Ensure the API key is correctly formatted.

```bash
# .env
REQUESTY_API_KEY=<your_requesty_api_key>
```

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

### IO Intelligence API Key Configuration (Deprecated)

Source: https://github.com/tailcallhq/forgecode/blob/main/README.md

Legacy environment variable setup for IO Intelligence. This method is deprecated; use `forge provider login` instead. Ensure the API key is correctly formatted.

```bash
# .env
IO_INTELLIGENCE_API_KEY=<your_io_intelligence_api_key>
```

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

### ZSH Plugin Mode Commands

Source: https://github.com/tailcallhq/forgecode/blob/main/README.md

After `forge setup`, use the `:` prefix for direct shell integration. This mode allows sending prompts, committing, suggesting commands, and managing conversations without leaving your shell.

```zsh
: refactor the auth module
:commit
:suggest "find large log files"
:conversation
```

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

### z.ai API Key Configuration (Deprecated)

Source: https://github.com/tailcallhq/forgecode/blob/main/README.md

Legacy environment variable setup for z.ai. This method is deprecated; use `forge provider login` instead. Supports both general and coding plan API keys.

```bash
# .env
ZAI_API_KEY=<your_zai_api_key>

# Or for coding plan subscription
ZAI_CODING_API_KEY=<your_zai_coding_api_key>
```

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

### OpenRouter API Key Configuration (Deprecated)

Source: https://github.com/tailcallhq/forgecode/blob/main/README.md

Legacy environment variable setup for OpenRouter. This method is deprecated; use `forge provider login` instead. Ensure the API key is correctly formatted.

```bash
# .env
OPENROUTER_API_KEY=<your_openrouter_api_key>
```

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

### Initialize Project-Local Skill

Source: https://github.com/tailcallhq/forgecode/blob/main/crates/forge_repo/src/skills/create-skill/SKILL.md

Creates a new skill in the project-local directory, including necessary subdirectories and the SKILL.md file with basic YAML frontmatter and markdown body. Also creates a sample script file and makes it executable.

```bash
mkdir -p {{local_skills_path}}/edit-pdf/{scripts,references,assets}
cat > {{local_skills_path}}/edit-pdf/SKILL.md << 'EOF'
---
name: edit-pdf
description: TODO - Describe what this skill does and when to use it
---

# Edit PDF

TODO - Add skill instructions here
EOF

cat > {{local_skills_path}}/edit-pdf/scripts/rotate.sh << 'EOF'
#!/bin/bash
# Rotate PDF using pdftk
pdftk "$1" cat 1-endright output "$2"
EOF

chmod +x {{local_skills_path}}/edit-pdf/scripts/rotate.sh
```

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

### Run Environment Diagnostics

Source: https://github.com/tailcallhq/forgecode/blob/main/shell-plugin/README.md

Execute comprehensive environment diagnostics with the :doctor command to check your Forge setup. This verifies ZSH, Forge installation, plugin status, dependencies, and more.

```bash
:doctor
```

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

### Git Operations Prompt

Source: https://github.com/tailcallhq/forgecode/blob/main/README.md

Use this prompt to get help with Git operations, like resolving merge conflicts. Forge guides you through conflict resolution and explains differences.

```plaintext
> I need to merge branch 'feature/user-profile' into main but there are conflicts
```

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

### Unix/Linux/macOS Environment Variable Examples

Source: https://github.com/tailcallhq/forgecode/blob/main/plans/2025-09-13-forge-history-file-env-var-v2.md

Examples of setting the FORGE_HISTORY_FILE environment variable on Unix-like systems. These paths can be relative or absolute.

```bash
# Unix/Linux/macOS examples
FORGE_HISTORY_FILE=./project-history
FORGE_HISTORY_FILE=../shared/team-history
FORGE_HISTORY_FILE=/home/user/forge-histories/project1
```

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

### Initialize Global Skill

Source: https://github.com/tailcallhq/forgecode/blob/main/crates/forge_repo/src/skills/create-skill/SKILL.md

Creates a new skill in the global directory, including necessary subdirectories and the SKILL.md file with basic YAML frontmatter and markdown body. Also creates a sample script file and makes it executable.

```bash
mkdir -p {{global_skills_path}}/edit-pdf/{scripts,references,assets}
cat > {{global_skills_path}}/edit-pdf/SKILL.md << 'EOF'
---
name: edit-pdf
description: TODO - Describe what this skill does and when to use it
---

# Edit PDF

TODO - Add skill instructions here
EOF

cat > {{global_skills_path}}/edit-pdf/scripts/rotate.sh << 'EOF'
#!/bin/bash
# Rotate PDF using pdftk
pdftk "$1" cat 1-endright output "$2"
EOF

chmod +x {{global_skills_path}}/edit-pdf/scripts/rotate.sh
```

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

### Start Forge Session in Isolated Sandbox

Source: https://github.com/tailcallhq/forgecode/blob/main/README.md

Create an isolated Git worktree and branch for experimentation before starting a Forge session.

```bash
forge --sandbox experiment-name
```

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

### Learning New Technologies Prompt

Source: https://github.com/tailcallhq/forgecode/blob/main/README.md

Use this prompt to learn how to integrate new technologies, like GraphQL with Express. Forge provides tailored tutorials based on your project structure.

```plaintext
> I want to integrate GraphQL into this Express application. Can you explain how to get started?
```

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

### Start a New Session

Source: https://github.com/tailcallhq/forgecode/blob/main/shell-plugin/README.md

Clears the current conversation context and starts a fresh session. This resets the session state and displays helpful information.

```bash
:new
# or use the alias
:n
```

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

### Windows Environment Variable Examples

Source: https://github.com/tailcallhq/forgecode/blob/main/plans/2025-09-13-forge-history-file-env-var-v2.md

Examples of setting the FORGE_HISTORY_FILE environment variable on Windows. Supports drive letters, UNC paths, and relative paths.

```bash
# Windows examples
FORGE_HISTORY_FILE=.\project-history
FORGE_HISTORY_FILE=..\shared\team-history
FORGE_HISTORY_FILE=C:\Users\Name\ForgeHistories\project1
FORGE_HISTORY_FILE=\\server\share\team-histories\project1
```

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

### Feature Addition PR Description Example

Source: https://github.com/tailcallhq/forgecode/blob/main/crates/forge_repo/src/skills/github-pr-description/SKILL.md

Example of a comprehensive PR description for a new feature, including summary, context, changes, implementation details, use cases, testing, and links.

```markdown
## Summary
Add semantic code search to enable searching codebase by concepts and behavior rather than exact string matching.

## Context
Currently, users can only search using exact string matching, which makes it difficult to find code based on functionality or behavior. This has been a recurring request in issues #123 and #456.

## Changes
- Implemented semantic search using vector embeddings
- Integrated with existing search interface
- Added support for multiple concurrent queries with result aggregation
- Configurable search scope (entire codebase or specific directories)

### Key Implementation Details
Uses OpenAI embeddings for code representation and cosine similarity for matching. Index is built incrementally to support large codebases. Search results are reranked based on code context and usage patterns.

## Use Cases
- Find authentication flow without knowing exact function names
- Locate retry logic across the codebase
- Search for "database connection" patterns

## Testing
```bash
# Run the search service
npm run search:dev

# Test semantic queries
curl -X POST http://localhost:3000/search \
  -H "Content-Type: application/json" \
  -d '{"query": "user authentication"}'
```

## Links
- Related issues: #123, #456
- Documentation: /docs/semantic-search.md
```

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

### Using before_run for Build Steps

Source: https://github.com/tailcallhq/forgecode/blob/main/benchmarks/README.md

Shows how to use the `before_run` directive in Forge to execute commands, such as building binaries, before the main task execution. This ensures dependencies are met.

```yaml
before_run:
  - cargo build
```

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

### Start a New Conversation

Source: https://github.com/tailcallhq/forgecode/blob/main/shell-plugin/README.md

Initiates a new conversation with the default Forge agent by prefixing a prompt with a colon.

```bash
: Get the current time
```

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

### Good Claude Tool Description Example (JSON)

Source: https://github.com/tailcallhq/forgecode/blob/main/docs/tool-guidelines.md

This JSON object demonstrates a well-formed tool description for Claude. It includes a detailed explanation of the tool's function, usage scenarios, limitations, and input schema, ensuring Claude can accurately interpret and use the tool.

```json
{
  "name": "get_stock_price",
  "description": "Retrieves the current stock price for a given ticker symbol. The ticker symbol must be a valid symbol for a publicly traded company on a major US stock exchange like NYSE or NASDAQ. The tool will return the latest trade price in USD. It should be used when the user asks about the current or most recent price of a specific stock. It will not provide any other information about the stock or company.",
  "input_schema": {
    "type": "object",
    "properties": {
      "ticker": {
        "type": "string",
        "description": "The stock ticker symbol, e.g. AAPL for Apple Inc."
      }
    },
    "required": ["ticker"]
  }
}
```

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

### Sample Error Response for Invalid Range

Source: https://github.com/tailcallhq/forgecode/blob/main/plans/2025-04-27-large-file-read-range-support-v4.md

Example JSON response indicating an invalid byte range was specified.

```json
{
  "error": "Invalid range specified: start_byte (5000) is greater than end_byte (4000)."
}
```

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

### Write PR Description to File

Source: https://github.com/tailcallhq/forgecode/blob/main/crates/forge_repo/src/skills/github-pr-description/SKILL.md

Use the `write` tool to create the `.forge/FORGE_PR_DESCRIPTION.md` file with the generated description content.

```bash
Use the `write` tool to create `.forge/FORGE_PR_DESCRIPTION.md` with the generated description content.
```

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

### CSV Data for Template Variables

Source: https://github.com/tailcallhq/forgecode/blob/main/benchmarks/README.md

Example CSV data providing values for template variables used in commands.

```csv
input_file,format
data1.txt,json
data2.txt,yaml
```

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

### Skill File Structure

Source: https://github.com/tailcallhq/forgecode/blob/main/crates/forge_repo/src/skills/create-skill/SKILL.md

Illustrates the required and optional components of a skill package, highlighting the SKILL.md file and its frontmatter.

```markdown
skill-name/
├── SKILL.md (required)
│   ├── YAML frontmatter metadata (required)
│   │   ├── name: (required)
│   │   └── description: (required)
│   └── Markdown instructions (required)
└── Bundled Resources (optional)
    ├── scripts/          - Executable code (Python/Bash/etc.)
    ├── references/       - Documentation intended to be loaded into context as needed
    └── assets/           - Files used in output (templates, icons, fonts, etc.)
```

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

### Poor Claude Tool Description Example (JSON)

Source: https://github.com/tailcallhq/forgecode/blob/main/docs/tool-guidelines.md

This JSON object illustrates a poorly written tool description for Claude. Its brevity lacks crucial details about the tool's functionality, usage, and parameter constraints, leading to potential misinterpretations by Claude.

```json
{
  "name": "get_stock_price",
  "description": "Gets the stock price for a ticker.",
  "input_schema": {
    "type": "object",
    "properties": {
      "ticker": {
        "type": "string"
      }
    },
    "required": ["ticker"]
  }
}
```

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

### Create Evaluation Directory

Source: https://github.com/tailcallhq/forgecode/blob/main/benchmarks/README.md

Create a new directory for your evaluation definitions.

```bash
mkdir -p evals/my_eval
```

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

### Other Forge CLI Commands

Source: https://github.com/tailcallhq/forgecode/blob/main/README.md

Miscellaneous Forge CLI commands for information, tool listing, diagnostics, updates, and setup.

```bash
forge info
```

```bash
forge list tool --agent <id>
```

```bash
forge doctor
```

```bash
forge update
```

```bash
forge setup
```

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

### Rust Hello World

Source: https://github.com/tailcallhq/forgecode/blob/main/crates/forge_display/src/fixtures/code-02.md

A basic 'Hello, world!' program in Rust.

```rust
fn main() {
    println!("Hello, world!");
}
```

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

### Use Specific Forge Agents

Source: https://github.com/tailcallhq/forgecode/blob/main/shell-plugin/README.md

Starts a conversation with a specific Forge agent by naming it after the colon. Tab completion is available for agent names.

```bash
:sage How does caching work in this system?
:muse Create a deployment strategy for my app
```

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

### Regex Validation Example

Source: https://github.com/tailcallhq/forgecode/blob/main/benchmarks/README.md

Utilize regex validations in Forge to verify task outputs against regular expressions. This is ideal for pattern matching in command output.

```yaml
run: cargo test {{test_name}}
validations:
  - name: "All tests passed"
    type: regex
    regex: test result:\s+ok
sources:
  - csv: tests.csv
```

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

### Multiple Commands Execution Example

Source: https://github.com/tailcallhq/forgecode/blob/main/benchmarks/README.md

Define a Forge task that executes a sequence of commands. This allows for more complex workflows within a single task definition.

```yaml
run:
  - echo "Starting task {{id}}"
  - ./process --input {{file}}
  - echo "Task {{id}} complete"
parallelism: 3
timeout: 120
sources:
  - csv: tasks.csv
```

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

### Text Input with ForgeSelect

Source: https://github.com/tailcallhq/forgecode/blob/main/crates/forge_select/README.md

Use this snippet to get text input from the user. You can specify whether empty input is allowed and provide a default value.

```rust
use forge_select::ForgeSelect;

let name = ForgeSelect::input("Enter your name:")
    .allow_empty(false)
    .with_default("John")
    .prompt()?;
```

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

### Sample Success Response for fs_read Tool

Source: https://github.com/tailcallhq/forgecode/blob/main/plans/2025-04-27-large-file-read-range-support-v4.md

Illustrates the JSON structure for a successful file read operation, including content and detailed metadata.

```json
{
  "content": "This is the file content within the requested range...",
  "metadata": {
    "file_size": 1024000,
    "requested_range": {
      "start_byte": 500,
      "end_byte": 1500
    },
    "actual_range": {
      "start_byte": 498,
      "end_byte": 1503
    },
    "boundary_adjustments": {
      "start_adjusted": true,
      "start_adjustment_reason": "UTF-8 character boundary alignment",
      "end_adjusted": true,
      "end_adjustment_reason": "UTF-8 character boundary alignment"
    },
    "is_partial": true,
    "percent_of_file": 0.1
  }
}
```

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

### Rust Service Constructor with Single Dependency

Source: https://github.com/tailcallhq/forgecode/blob/main/AGENTS.md

Example of a simple service implementation using a tuple struct pattern for a single infrastructure dependency, stored as `Arc<T>`.

```rust
struct Service<T>(Arc<T>);
```

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

### View System Information

Source: https://github.com/tailcallhq/forgecode/blob/main/shell-plugin/README.md

Displays system and project information, including system details, project details, and current configuration. Aliases :i are available.

```bash
:info
# or use the alias
:i
```