### Extension Setup Wizard

Source: https://github.com/nearai/ironclaw/blob/main/src/channels/web/CLAUDE.md

Initiates the setup wizard for an extension. Can be accessed via GET or POST.

```APIDOC
## GET/POST /api/extensions/{name}/setup

### Description
Initiates the setup wizard for an extension.

### Method
GET, POST

### Endpoint
/api/extensions/{name}/setup

### Parameters
#### Path Parameters
- **name** (string) - Required - The name of the extension to set up.
```

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

### Manual Quick Start for WebUI

Source: https://github.com/nearai/ironclaw/blob/main/docs/reborn-binary.md

Step-by-step guide to setting up and running the Reborn WebUI manually. This involves setting the Reborn home directory, configuring a model provider, and setting authentication environment variables.

```bash
# 1. For serve/run/repl the Reborn home must live OUTSIDE your current working
#    directory: these commands use the cwd as the local-dev workspace root and
#    reject overlap with it (see gotchas). Other commands have no such rule.
export IRONCLAW_REBORN_HOME="$HOME/.ironclaw-reborn-demo"

# 2. Configure a model route. NEAR AI shown here; swap the provider id and key
#    env var for any row in the table below. set-provider records the credential
#    env-var NAME in config.toml; the secret VALUE stays in the environment.
cargo run -q -p ironclaw_reborn_cli --features webui-v2-beta --bin ironclaw-reborn -- \
  models set-provider nearai
export NEARAI_API_KEY="your-key-here"

# 3. WebUI auth. serve REQUIRES both values or it refuses to start. The variable
#    NAMES below are the defaults; override them via [webui].env_token_var and
#    [webui].env_user_id_var in config.toml if you prefer different names.
export IRONCLAW_REBORN_WEBUI_TOKEN="$(openssl rand -hex 32)"   # bearer token you log in with
export IRONCLAW_REBORN_WEBUI_USER_ID="reborn-cli"             # must match [identity].default_owner

```

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

### Setup Virtual Environment and Install Dependencies

Source: https://github.com/nearai/ironclaw/blob/main/tests/e2e/CLAUDE.md

Commands to set up a Python virtual environment, activate it, and install project dependencies using pip. Also includes installing browser binaries for Playwright.

```bash
cd tests/e2e

# Create virtualenv (one-time)
python -m venv .venv
source .venv/bin/activate   # or .venv\Scripts\activate on Windows

# Install dependencies
pip install -e .

# Install browser binaries (one-time)
playwright install chromium
```

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

### Setup Live Canary Configuration

Source: https://github.com/nearai/ironclaw/blob/main/scripts/auth_live_canary/README.md

Copy the example configuration file and source it to load environment variables for the live canary tests. Ensure all necessary provider credentials are set.

```bash
cd scripts/auth_live_canary
cp config.example.env config.env
set -a && source config.env && set +a
```

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

### Mark CEO Setup Complete

Source: https://github.com/nearai/ironclaw/blob/main/skills/ceo-setup/SKILL.md

Writes a marker file to indicate that the CEO setup process is complete. This file includes details about installed missions and widgets. Deleting this file can re-trigger setup.

```shell
memory_write(
  target: "projects/commitments/.ceo-setup-complete",
  content: "# CEO Setup Complete\n\nCompleted: <today's UTC date>\n\nMissions installed: commitment-triage, commitment-digest\nWidgets installed: commitments-this-week, delegations-waiting\n",
  append: false
)
```

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

### Clone Repository and Setup Development Environment

Source: https://github.com/nearai/ironclaw/blob/main/CONTRIBUTING.md

Clone the Ironclaw repository and run the setup script to install necessary tools and dependencies.

```bash
git clone https://github.com/nearai/ironclaw.git
cd ironclaw
./scripts/dev-setup.sh
```

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

### Mark Content Creator Setup Complete

Source: https://github.com/nearai/ironclaw/blob/main/skills/content-creator-setup/SKILL.md

Writes a completion marker to prevent re-triggering setup. Delete this file to re-initiate setup.

```python
memory_write(
  target: "projects/commitments/.content-creator-setup-complete",
  content: "# Content Creator Setup Complete\n\nCompleted: <today's UTC date>\n\nMissions installed: creator-triage, creator-digest, creator-idea-resurface"
)
```

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

### Install Rust and Build IronClaw from Source

Source: https://github.com/nearai/ironclaw/blob/main/docs/drafts/platforms/macos.mdx

Install Rust using the official script and then build and install IronClaw using Cargo.

```bash
# Install Rust if needed
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh

# Build and install
cargo install ironclaw
```

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

### Local Coding Agent Startup Output

Source: https://github.com/nearai/ironclaw/blob/main/docs/reborn/contracts/runtime-profiles.md

Example output displayed when the local coding agent starts, indicating the active trust boundary and profile settings.

```text
IronClaw Local Coding Agent
Profile: local-dev
Filesystem: direct workspace writes under /repo
Shell: local host shell; approval for dangerous commands
Network: direct/logged
Secrets: inherited env limited by profile
Audit: enabled
```

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

### Local Setup for Live Canary Tests

Source: https://github.com/nearai/ironclaw/blob/main/scripts/live-canary/ACCOUNTS.md

Sets up the local environment for live canary tests by copying an example configuration file, sourcing environment variables, and listing available test cases for seeded and browser modes.

```bash
cd scripts/auth_live_canary
cp config.example.env config.env
set -a && source config.env && set +a
cd ../..

# List seeded cases:
python3 scripts/auth_live_canary/run_live_canary.py --mode seeded --list-cases

# List browser cases:
python3 scripts/auth_live_canary/run_live_canary.py --mode browser --list-cases
```

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

### Install Cloudflared as a Service

Source: https://github.com/nearai/ironclaw/blob/main/docs/drafts/install/vps.mdx

Installs cloudflared as a systemd service, enables it to start on boot, and starts the service immediately.

```bash
sudo cloudflared service install
sudo systemctl enable --now cloudflared
```

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

### Get Installed Extensions

Source: https://github.com/nearai/ironclaw/blob/main/src/channels/web/CLAUDE.md

Retrieves a list of all currently installed extensions.

```APIDOC
## GET /api/extensions

### Description
Retrieves a list of all currently installed extensions.

### Method
GET

### Endpoint
/api/extensions

### Response
#### Success Response (200)
- extensions (array) - A list of installed extensions.
```

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

### Quick Mode Database Setup

Source: https://github.com/nearai/ironclaw/blob/main/src/setup/README.md

Demonstrates the auto_setup_database() function in quick mode. It defaults to libsql at ~/.ironclaw/ironclaw.db if no existing env vars are set.

```rust
auto_setup_database()    → libsql at ~/.ironclaw/ironclaw.db (zero prompts)
```

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

### Install Service (macOS Homebrew)

Source: https://github.com/nearai/ironclaw/blob/main/docs/drafts/install/local.mdx

Installs and starts the IronClaw service using Homebrew services.

```bash
ironclaw service install
brew services start ironclaw
```

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

### Install and Enable Service (Linux)

Source: https://github.com/nearai/ironclaw/blob/main/docs/drafts/install/local.mdx

Installs the IronClaw service and enables it to start automatically on boot.

```bash
ironclaw service install
sudo systemctl enable --now ironclaw
```

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

### Basic WebUI Service Startup with Environment Variables

Source: https://github.com/nearai/ironclaw/blob/main/README.md

Starts the Reborn WebUI service using environment variables for configuration. Sets up the home directory, API key, bearer token, and user ID.

```bash
export IRONCLAW_REBORN_HOME="$PWD/.reborn-home"
export OPENAI_API_KEY="sk-..." # or the required env var for your configured provider
export IRONCLAW_REBORN_WEBUI_TOKEN="$(openssl rand -hex 32)"
export IRONCLAW_REBORN_WEBUI_USER_ID="reborn-cli"

cargo run -q -p ironclaw_reborn_cli --features webui-v2-beta --bin ironclaw-reborn -- serve
```

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

### POST /api/reborn/product-auth/oauth/google/start

Source: https://github.com/nearai/ironclaw/blob/main/docs/reborn/contracts/auth-product.md

Initiates a Google product-auth setup flow using configured Reborn Google OAuth client metadata. Returns a Google authorization URL with PKCE/offline consent and the invocation scope.

```APIDOC
## POST /api/reborn/product-auth/oauth/google/start

### Description
Open a Google product-auth setup flow from configured Reborn Google OAuth client metadata; returns a Google authorization URL with PKCE/offline consent and invocation scope.

### Method
POST

### Endpoint
/api/reborn/product-auth/oauth/google/start

### Parameters
#### Request Body
- **(Implicit)**: The request body is processed with `LocalGateway` + `BearerToken` + per-caller body and rate-limit posture.

### Response
#### Success Response (200)
- **authorization_url** (string) - The Google authorization URL with PKCE/offline consent.
- **invocation_scope** (object) - The invocation scope derived from the authenticated caller.
```

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

### Install GNOME Keyring in WSL2

Source: https://github.com/nearai/ironclaw/blob/main/docs/drafts/platforms/windows-wsl2.mdx

Installs the GNOME Keyring daemon and starts it for managing secrets within WSL2.

```bash
sudo apt install gnome-keyring

# Start the keyring daemon in your shell session
eval $(gnome-keyring-daemon --start --components=secrets)
export GNOME_KEYRING_CONTROL
```

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

### Skipping Setup Steps with `--channels-only`

Source: https://github.com/nearai/ironclaw/blob/main/src/setup/README.md

Demonstrates how to run only Step 6 (Channel Configuration) by using the `--channels-only` mode.

```text
--channels-only
```

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

### Install PostgreSQL and pgvector on macOS with Homebrew

Source: https://github.com/nearai/ironclaw/blob/main/docs/capabilities/database.mdx

Install PostgreSQL and the pgvector extension on macOS using Homebrew. Starts the PostgreSQL service.

```bash
brew install postgresql
brew install pgvector
brew services start postgresql
```

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

### Full SKILL.md Example

Source: https://github.com/nearai/ironclaw/blob/main/docs/drafts/agents/skills-format.mdx

A comprehensive example demonstrating the YAML frontmatter for skill activation and a markdown body with instructions and common commands.

```yaml
---
name: kubernetes-deploy
version: 0.2.0
description: Kubernetes deployment and operations guidance
activation:
  patterns:
    - "deploy to.*production"
    - "rollback.*deployment"
    - "kubectl.*error"
  keywords:
    - deployment
    - kubernetes
    - kubectl
    - k8s
    - pod
    - namespace
  max_context_tokens: 2000
metadata:
  ironclaw:
    requires:
      bins:
        - kubectl
        - docker
      env:
        - KUBECONFIG
---

# Kubernetes Deployment Skill

You are operating in a Kubernetes environment. Follow these guidelines:

## Deployment Checklist

Before deploying to production:
1. Verify the image tag is pinned (never use `latest`)
2. Check resource limits are set on all containers
3. Confirm readiness and liveness probes are defined
4. Review the rollout strategy (RollingUpdate recommended)

## Common Commands

```bash
# Check rollout status
kubectl rollout status deployment/<name> -n <namespace>

# Rollback to previous version
kubectl rollout undo deployment/<name> -n <namespace>

# View pod logs
kubectl logs -l app=<name> -n <namespace> --tail=100
```

## Error Patterns

- `ImagePullBackOff` → Check image name, tag, and registry credentials
- `CrashLoopBackOff` → Check container logs and resource limits
- `Pending` → Check node resources and PVC availability

```

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

### Install Dependencies

Source: https://github.com/nearai/ironclaw/blob/main/docs/architecture-video/README.md

Run this command once to install all necessary project dependencies.

```console
npm ci
```

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

### GET /api/extensions/tools

Source: https://github.com/nearai/ironclaw/blob/main/docs/drafts/ops/api.mdx

Lists the tools provided by installed extensions.

```APIDOC
## GET /api/extensions/tools

### Description
Lists the tools provided by installed extensions.

### Method
GET

### Endpoint
/api/extensions/tools
```

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

### webui.v2.setup_extension

Source: https://github.com/nearai/ironclaw/blob/main/crates/ironclaw_webui_v2/CLAUDE.md

Sets up or updates the configuration for a specific extension.

```APIDOC
## POST /api/webchat/v2/extensions/{package_id}/setup

### Description
Sets up or updates the configuration for a specific extension.

### Method
POST

### Endpoint
/api/webchat/v2/extensions/{package_id}/setup

### Parameters
#### Path Parameters
- **package_id** (string) - Required - The ID of the package to set up.

#### Request Body
- (type) - Required - The setup configuration for the extension.

### Request Example
{
  "example": "request body"
}

### Response
#### Success Response (200)
- (type) - Description

#### Response Example
{
  "example": "response body"
}
```

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

### Ironclaw Setup Steps Overview

Source: https://github.com/nearai/ironclaw/blob/main/src/setup/README.md

This outlines the sequential steps involved in setting up the Ironclaw project. Some steps can be skipped based on command-line flags.

```text
Step 1: Database Connection
Step 2: Security (master key)
Step 3: Inference Provider          ← skipped if --skip-auth
Step 4: Model Selection
Step 5: Embeddings
Step 6: Channel Configuration
Step 7: Extensions (tools)
Step 8: Docker Sandbox
Step 9: Background Tasks (heartbeat)
       ↓
   save_and_summarize()
```

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

### Install and Enable Fail2Ban

Source: https://github.com/nearai/ironclaw/blob/main/docs/infrastructure/droplet.mdx

Install Fail2Ban to protect your Droplet from brute-force attacks by monitoring logs and banning malicious IPs. Enable and start the service.

```bash
apt install fail2ban -y
systemctl enable fail2ban
systemctl start fail2ban
```

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

### Install Google Sheets Extension

Source: https://github.com/nearai/ironclaw/blob/main/docs/extensions/google/sheets.md

Install the Google Sheets extension using the IronClaw CLI. Ensure you have completed the Google OAuth setup beforehand.

```bash
ironclaw registry install google-sheets
```

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

### Run Setup and Bootstrap Tests

Source: https://github.com/nearai/ironclaw/blob/main/src/setup/README.md

Execute tests specifically for the setup and bootstrap modules within the library.

```bash
cargo test --lib -- setup
cargo test --lib -- bootstrap
```

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

### Develop and Preview Documentation Locally

Source: https://github.com/nearai/ironclaw/blob/main/CONTRIBUTING.md

Navigate to the docs directory and run this command to start a local development server for previewing documentation changes.

```bash
cd docs
mint dev
```

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

### Install and Configure PostgreSQL with pgvector

Source: https://github.com/nearai/ironclaw/blob/main/docs/drafts/install/vps.mdx

Install PostgreSQL and the pgvector extension, then create a dedicated user and database for IronClaw. This setup is recommended for production environments.

```bash
# Install PostgreSQL
sudo apt install postgresql postgresql-contrib

# Start PostgreSQL
sudo systemctl enable --now postgresql

# Create database and user
sudo -u postgres psql <<EOF
CREATE USER ironclaw WITH PASSWORD 'your-secure-password';
CREATE DATABASE ironclaw OWNER ironclaw;
EOF

# Detect PostgreSQL major version (e.g., 14, 15, 16)
PG_MAJOR=$(psql -V | awk '{print $3}' | cut -d. -f1)
# Install matching pgvector package for the detected PostgreSQL version
sudo apt install "postgresql-$PG_MAJOR-pgvector"
# Enable the vector extension in the ironclaw database
sudo -u postgres psql -d ironclaw -c "CREATE EXTENSION IF NOT EXISTS vector;"
```

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

### Onboard and import history

Source: https://github.com/nearai/ironclaw/blob/main/docs/reborn-binary.md

Initiates the onboarding process. Use `--dry-run` to preview, `--force` to override, or `--import-history` to attempt history import (not yet fully wired).

```bash
ironclaw-reborn onboard
```

```bash
ironclaw-reborn onboard --dry-run
```

```bash
ironclaw-reborn onboard --force
```

```bash
ironclaw-reborn onboard --import-history   # flag parsed, but history import not wired yet
```

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

### Install PostgreSQL and pgvector on Ubuntu/Debian

Source: https://github.com/nearai/ironclaw/blob/main/docs/capabilities/database.mdx

Install PostgreSQL version 15 and the pgvector extension on Ubuntu or Debian systems. Ensures the PostgreSQL service is enabled and started.

```bash
sudo apt install postgresql-15 postgresql-15-pgvector
sudo systemctl enable --now postgresql
```

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

### Run IronClaw in WSL2

Source: https://github.com/nearai/ironclaw/blob/main/docs/drafts/install/local.mdx

Starts IronClaw after installation within the WSL2 environment.

```bash
ironclaw onboard
ironclaw run
```

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

### Quick Mode Security Setup

Source: https://github.com/nearai/ironclaw/blob/main/src/setup/README.md

Illustrates the auto_setup_security() function in quick mode. It checks for existing environment variables or OS keychain keys, generating new ones if necessary.

```rust
auto_setup_security()    → keychain or env var (zero prompts)
```

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

### Level 1: Prompt Evolution Example

Source: https://github.com/nearai/ironclaw/blob/main/docs/plans/2026-03-23-self-improving-engine.md

This example shows how the engine can automatically update its prompt templates to guide LLM behavior, such as adding constraints or clarifying tool usage.

```markdown
- Adds "NEVER call web_fetch — use http() or llm_context()" to rules section
- Adds "freshness parameter: 'pd'=past day, 'pw'=past week, 'pm'=past month" to tool hints
- Adds "Always access previous step data via state['tool_name']" after repeated NameErrors
- Removes examples that reference nonexistent tools
```

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

### Setup Extension Lifecycle Projection

Source: https://github.com/nearai/ironclaw/blob/main/crates/ironclaw_webui_v2/CLAUDE.md

Initiates the extension onboarding process via a lifecycle projection. Manages extension setup through distinct phases and blockers.

```APIDOC
## setup_extension

### Description
Entrypoint for extension onboarding, exposing the setup surface as a lifecycle projection. Responses include phase, blockers, optional payload, and package reference. Does not perform production setup side effects.

### Method
(Not explicitly specified, but implied to be a POST-like operation for initiating setup)

### Endpoint
(Not explicitly specified, but implied to be a native facade call)

### Parameters
#### Request Body
- **package_ref** (object) - Required - Specifies the extension package to set up. Should contain `kind: "extension"` and `id`.
  - **kind** (string) - Required - Must be "extension".
  - **id** (string) - Required - The unique identifier for the extension package.

### Request Example
```json
{
  "package_ref": {
    "kind": "extension",
    "id": "example-extension-id"
  }
}
```

### Response
#### Success Response (200)
- **phase** (string) - The current phase of the extension setup.
- **blockers** (array) - A list of blockers that must be resolved for setup to proceed.
- **payload** (object) - Optional - Additional data related to the setup process.
- **package_ref** (object) - The reference to the lifecycle package.

#### Error Response
- **400 invalid_request**: If the `package_id` in `package_ref` is malformed.
  - **field** (string) - "package_id"
  - **validation_code** (string) - "invalid_id"

#### Response Example
```json
{
  "phase": "pending_approval",
  "blockers": [
    {
      "service": "auth",
      "message": "Authentication required"
    }
  ],
  "package_ref": {
    "kind": "extension",
    "id": "example-extension-id"
  }
}
```
```

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

### GET /api/extensions

Source: https://github.com/nearai/ironclaw/blob/main/docs/drafts/ops/api.mdx

Lists installed extensions, including MCP servers and WASM modules.

```APIDOC
## GET /api/extensions

### Description
Lists installed extensions, including MCP servers and WASM modules.

### Method
GET

### Endpoint
/api/extensions
```

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

### webui.v2.operator.run_setup

Source: https://github.com/nearai/ironclaw/blob/main/crates/ironclaw_webui_v2/CLAUDE.md

Runs the operator setup process.

```APIDOC
## POST /api/webchat/v2/operator/setup

### Description
Runs the operator setup process.

### Method
POST

### Endpoint
/api/webchat/v2/operator/setup

### Parameters
#### Request Body
- (type) - Required - The operator setup configuration.

### Request Example
{
  "example": "request body"
}

### Response
#### Success Response (200)
- (type) - Description

#### Response Example
{
  "example": "response body"
}
```

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

### Install Caddy Web Server

Source: https://github.com/nearai/ironclaw/blob/main/docs/drafts/platforms/vps.mdx

Installs the Caddy web server, which automatically handles TLS certificate provisioning and renewal using Let's Encrypt. This simplifies secure HTTPS setup.

```bash
sudo apt install -y debian-keyring debian-archive-keyring apt-transport-https
curl -1sLf 'https://dl.cloudsmith.io/public/caddy/stable/gpg.key' \
  | sudo gpg --dearmor -o /usr/share/keyrings/caddy-stable-archive-keyring.gpg
curl -1sLf 'https://dl.cloudsmith.io/public/caddy/stable/debian.deb.txt' \
  | sudo tee /etc/apt/sources.list.d/caddy-stable.list
sudo apt update && sudo apt install caddy
```

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

### Write Developer Setup Completion Marker

Source: https://github.com/nearai/ironclaw/blob/main/skills/developer-setup/SKILL.md

This code snippet writes a marker to memory to indicate that the developer setup is complete. It includes details about the completion date, repositories, maintainers, and installed missions. This is a one-time operation.

```python
memory_write(
  target: "projects/commitments/.developer-setup-complete",
  content: "# Developer Setup Complete\n\nCompleted: <today's UTC date>\n\nRepos: <list of repo slugs>\nMaintainers: <maintainers>\nMissions installed: wf-issue-plan, wf-maintainer-gate, wf-pr-monitor, wf-ci-fix, wf-learning, plus 6 personal productivity missions (commitment-triage, commitment-digest, dev-stale-pr-check, dev-weekly-retro, dev-tech-debt-resurface, dev-decision-outcome-check)"
)
```

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

### POST /api/reborn/product-auth/oauth/start

Source: https://github.com/nearai/ironclaw/blob/main/docs/reborn/contracts/auth-product.md

Initiates an OAuth setup flow. It returns a redacted authorization URL and the invocation scope for the authenticated caller.

```APIDOC
## POST /api/reborn/product-auth/oauth/start

### Description
Open an OAuth setup flow; returns redacted authorization URL + invocation scope.

### Method
POST

### Endpoint
/api/reborn/product-auth/oauth/start

### Parameters
#### Request Body
- **(Implicit)**: The request body is processed with `LocalGateway` + `BearerToken` + per-caller body and rate-limit posture.

### Response
#### Success Response (200)
- **authorization_url** (string) - Redacted authorization URL.
- **invocation_scope** (object) - The invocation scope derived from the authenticated caller.
```

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

### Setup E2E Tests Environment

Source: https://github.com/nearai/ironclaw/blob/main/docs/plans/2026-02-24-e2e-infrastructure.md

Install necessary Python dependencies and Playwright browsers for running E2E tests.

```bash
cd tests/e2e
pip install -e .
playwright install chromium
```

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

### Build Configurations for Database Module

Source: https://github.com/nearai/ironclaw/blob/main/src/db/CLAUDE.md

Commands to build the project with different backend configurations. Use `--features libsql` for libSQL/Turso support, or `--features "postgres,libsql"` for both.

```bash
cargo build

cargo build --no-default-features --features libsql

cargo build --features "postgres,libsql"

cargo check                                           
cargo check --no-default-features --features libsql   
cargo check --all-features                            
```

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

### Manage Homebrew Services

Source: https://github.com/nearai/ironclaw/blob/main/docs/drafts/platforms/macos.mdx

Use these commands to start, stop, restart, or check the status of IronClaw when installed via Homebrew.

```bash
# Start now and on login
brew services start ironclaw
```

```bash
# Stop
brew services stop ironclaw
```

```bash
# Restart
brew services restart ironclaw
```

```bash
# View status
brew services list | grep ironclaw
```

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

### Mock LLM Server Manual Start

Source: https://github.com/nearai/ironclaw/blob/main/tests/e2e/CLAUDE.md

Starts the mock LLM server manually. The port is auto-selected and printed to standard output.

```bash
python mock_llm.py --port 0
```

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

### Setup E2E Python Environment

Source: https://github.com/nearai/ironclaw/blob/main/scripts/telegram_smoke/README.md

Installs the necessary Python dependencies for the end-to-end tests, including the Telegram specific components.

```bash
cd tests/e2e
python -m venv .venv
source .venv/bin/activate
pip install -e '.[telegram]'
```

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

### Install Slack Tool (Database Storage)

Source: https://github.com/nearai/ironclaw/blob/main/tools-src/slack/README.md

Install the Slack tool using the agent CLI, storing the WASM and capabilities in the database.

```bash
ironclaw tool install \
  --name slack \
  --wasm target/wasm32-wasip2/release/slack_tool.wasm \
  --capabilities slack.capabilities.json
```

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

### Get Slack User Info

Source: https://github.com/nearai/ironclaw/blob/main/tools-src/slack/README.md

Example JSON payload for retrieving information about a specific Slack user. Requires 'user_id'.

```json
{
  "action": "get_user_info",
  "user_id": "U1234567890"
}
```

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

### Setup IFrame with Options

Source: https://github.com/nearai/ironclaw/blob/main/tests/test-pages/cnn/source.html

Initializes an iframe with specified options, including setting size limits, ensuring an ID, and configuring scrolling behavior.

```javascript
function setupIFrame(options) {
  function setLimits() {
    function addStyle(style) {
      if ((Infinity !== settings[iframeId][style]) && (0 !== settings[iframeId][style])) {
        iframe.style[style] = settings[iframeId][style] + 'px';
        log(' Set ' + style + ' = ' + settings[iframeId][style] + 'px');
      }
    }
    addStyle('maxHeight');
    addStyle('minHeight');
    addStyle('maxWidth');
    addStyle('minWidth');
  }
  function ensureHasId(iframeId) {
    if ('' === iframeId) {
      iframe.id = iframeId = 'iFrameResizer' + count++;
      logEnabled = (options || {}).log;
      log(' Added missing iframe ID: ' + iframeId + ' (' + iframe.src + ')');
    }
    return iframeId;
  }
  function setScrolling() {
    log(' IFrame scrolling ' + (settings[iframeId].scrolling ? 'enabled' : 'disabled') + ' for ' + iframeId);
    iframe.style.overflow = false === settings[iframeId].scrolling ? 'hidden' : 'auto';
    iframe.scrolling = false === settings[iframeId].scrolling ? 'no' : 'yes';
  }
  function setupBodyMarginValues() {
    if (('number' === typeof(settings[iframeId].bodyMargin)) || ('0' === settings[iframeId].bodyMargin)) {
      settings[iframeId].bodyMarginV1 = settings[iframeId].bodyMargin;
      settings[iframeId].bodyMargin = '' + settings[iframeId].bodyMargin + 'px';
    }
  }
  function createOutgoingMsg() {
    return iframeId + ':' + settings[iframeId].bodyMarginV1 + ':' + settings[iframeId].sizeWidth + ':' + settings[iframeId].log + ':' + settings[iframeId].interval + ':' + settings[ifr
}
```

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

### Get Slack Channel History

Source: https://github.com/nearai/ironclaw/blob/main/tools-src/slack/README.md

Example JSON payload for retrieving recent messages from a Slack channel. Requires 'channel' and an optional 'limit'.

```json
{
  "action": "get_channel_history",
  "channel": "C1234567890",
  "limit": 10
}
```

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

### Environment File Example

Source: https://github.com/nearai/ironclaw/blob/main/docs/capabilities/configuration.mdx

Example of a .env file for configuring IronClaw settings, including database, LLM, gateway, sandbox, and heartbeat.

```bash
# Database
DATABASE_BACKEND=libsql
LIBSQL_PATH=/home/user/.ironclaw/ironclaw.db

# LLM (NEAR AI)
LLM_BACKEND=nearai

# Web Gateway
GATEWAY_ENABLED=true
GATEWAY_HOST=127.0.0.1
GATEWAY_PORT=3000

# Optional: Persistent auth token
GATEWAY_AUTH_TOKEN=your-secure-token-here

# Sandbox
SANDBOX_ENABLED=true
SANDBOX_POLICY=workspace_write

# Heartbeat
HEARTBEAT_ENABLED=true
HEARTBEAT_INTERVAL_SECS=1800
```

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

### Bootstrap Environment Variables (PostgreSQL)

Source: https://github.com/nearai/ironclaw/blob/main/src/setup/README.md

Example of bootstrap environment variables stored in '~/.ironclaw/.env' for PostgreSQL backend. These are essential for initial setup before database connection.

```env
IRONCLAW_PROFILE="local"
DATABASE_BACKEND="postgres"
DATABASE_URL="postgres://user:pass@localhost/ironclaw"
SECRETS_MASTER_KEY="..."
ONBOARD_COMPLETED="true"
```

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

### Onboard IronClaw Setup

Source: https://github.com/nearai/ironclaw/blob/main/docs/drafts/reference/cli.mdx

Launches the interactive setup wizard for configuring database, LLM, channels, and security settings. Use `--skip-auth` to bypass authentication or `--channels-only` to configure only channels.

```bash
ironclaw onboard [OPTIONS]
```

```bash
ironclaw onboard
```

```bash
ironclaw onboard --skip-auth
```

```bash
ironclaw onboard --channels-only
```