### Install CQ Go SDK

Source: https://github.com/mozilla-ai/cq/blob/main/sdk/go/README.md

Install the CQ Go SDK using the go get command.

```bash
go get github.com/mozilla-ai/cq/sdk/go
```

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

### Initial Project Setup

Source: https://github.com/mozilla-ai/cq/blob/main/DEVELOPMENT.md

Clone the repository and run the initial setup script.

```bash
git clone https://github.com/mozilla-ai/cq.git
cd cq
make setup
```

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

### Install cq CLI with Go

Source: https://github.com/mozilla-ai/cq/blob/main/cli/README.md

Install the cq CLI using the Go programming language's install command.

```bash
# Go install.
go install github.com/mozilla-ai/cq/cli@latest
```

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

### Install Pi

Source: https://github.com/mozilla-ai/cq/blob/main/DEVELOPMENT.md

Install the Pi component. For a specific project, use `PROJECT=/path/to/your/project`.

```bash
make install-pi
```

```bash
make install-pi PROJECT=/path/to/your/project
```

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

### Install CQ SDK with pip

Source: https://github.com/mozilla-ai/cq/blob/main/sdk/python/README.md

Install the CQ SDK using pip.

```bash
pip install cq-sdk
```

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

### Install Windsurf

Source: https://github.com/mozilla-ai/cq/blob/main/DEVELOPMENT.md

Install the Windsurf component. This is a global install only.

```bash
make install-windsurf
```

```bash
make uninstall-windsurf
```

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

### Install Cursor

Source: https://github.com/mozilla-ai/cq/blob/main/DEVELOPMENT.md

Install the Cursor component. For a specific project, use `PROJECT=/path/to/your/project`.

```bash
make install-cursor
```

```bash
make uninstall-cursor PROJECT=/path/to/your/project
```

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

### Install OpenCode

Source: https://github.com/mozilla-ai/cq/blob/main/DEVELOPMENT.md

Install the OpenCode component. For a specific project, use `PROJECT=/path/to/your/project`.

```bash
make install-opencode
```

```bash
make install-opencode PROJECT=/path/to/your/project
```

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

### Install CQ SDK with uv

Source: https://github.com/mozilla-ai/cq/blob/main/sdk/python/README.md

Install the CQ SDK using the uv package manager.

```bash
uv add cq-sdk
```

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

### Install Cursor using Direct Installer

Source: https://github.com/mozilla-ai/cq/blob/main/DEVELOPMENT.md

Invoke the installer directly to install the Cursor component globally on Windows.

```bash
cd scripts\install
uv run python -m cq_install install --target cursor --global
```

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

### cq CLI MCP Server Start

Source: https://github.com/mozilla-ai/cq/blob/main/cli/README.md

Start the MCP server on standard input/output.

```bash
# Start the MCP server on stdio.
cq mcp
```

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

### Clone Repository and Setup Go SDK

Source: https://github.com/mozilla-ai/cq/blob/main/sdk/go/DEVELOPMENT.md

Clone the CQ repository and navigate to the Go SDK directory. Run 'make sync-prompts' to copy canonical prompts.

```bash
git clone https://github.com/mozilla-ai/cq.git
cd cq/sdk/go
make sync-prompts
```

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

### Clone Repository and Setup Environment

Source: https://github.com/mozilla-ai/cq/blob/main/sdk/python/DEVELOPMENT.md

Clone the CQ repository and set up the Python development environment using make.

```bash
git clone https://github.com/mozilla-ai/cq.git
cd cq/sdk/python
make setup
```

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

### Install cq CLI from Source

Source: https://github.com/mozilla-ai/cq/blob/main/cli/README.md

Clone the cq repository and build the CLI from source.

```bash
# From source.
git clone https://github.com/mozilla-ai/cq.git
cd cq/cli
make build
```

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

### Quick Start: CQ Go SDK Usage

Source: https://github.com/mozilla-ai/cq/blob/main/sdk/go/README.md

Demonstrates basic client creation, querying, proposing, confirming, and flagging knowledge units using the CQ Go SDK. Ensure the context (ctx) is properly managed.

```go
import cq "github.com/mozilla-ai/cq/sdk/go"

// Create a client (auto-discovers config, falls back to local-only).
c, err := cq.NewClient()
if err != nil {
    log.Fatal(err)
}
defer c.Close()

// Query.
result, _ := c.Query(ctx, cq.QueryParams{
    Domains:   []string{"api", "stripe"},
    Languages: []string{"go"},
})

// Propose.
ku, _ := c.Propose(ctx, cq.ProposeParams{
    Summary: "Stripe 402 means card_declined",
    Detail:  "Check error.code, not error.type.",
    Action:  "Handle card_declined explicitly.",
    Domains: []string{"api", "stripe"},
})

// Confirm / flag.
c.Confirm(ctx, ku)
c.Flag(ctx, ku, cq.Stale)
c.Flag(ctx, ku, cq.Duplicate, cq.WithDuplicateOf("ku_..."))
```

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

### CQ SDK Quick Start

Source: https://github.com/mozilla-ai/cq/blob/main/sdk/python/README.md

Demonstrates basic usage of the CQ Python SDK including querying, proposing, confirming, and flagging knowledge units, as well as retrieving agent prompts.

```python
from cq import Client, FlagReason

cq = Client()  # Auto-discovers config; falls back to local-only.

# Query.
results = cq.query(domains=["api", "stripe"], language="python")

# Propose.
ku = cq.propose(
    summary="Stripe 402 means card_declined",
    detail="Check error.code, not error.type.",
    action="Handle card_declined explicitly.",
    domains=["api", "stripe"],
)

# Confirm / flag.
cq.confirm(ku.id)
cq.flag(ku.id, reason=FlagReason.STALE)

# Get the canonical agent prompts.
from cq import prompts

skill_prompt = prompts.skill()
reflect_prompt = prompts.reflect()
```

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

### Install CQ via Python Installer

Source: https://github.com/mozilla-ai/cq/blob/main/docs/architecture.md

Use this command to install CQ on non-Claude-Code hosts. It resolves the target directory, writes MCP config, and installs shared skill commons.

```bash
python -m cq_install install --target <host>
```

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

### Install cq CLI with Homebrew

Source: https://github.com/mozilla-ai/cq/blob/main/cli/README.md

Install the cq CLI using the Homebrew package manager.

```bash
# Homebrew.
brew install --cask mozilla-ai/tap/cq
```

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

### Install Development Dependencies

Source: https://github.com/mozilla-ai/cq/blob/main/sdk/python/README.md

Install development dependencies using uv sync with the dev group.

```bash
uv sync --group dev
```

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

### Install cq CLI with Scoop

Source: https://github.com/mozilla-ai/cq/blob/main/cli/README.md

Install the cq CLI using the Scoop package manager.

```bash
# Scoop.
scoop install cq
```

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

### Install OpenCode using PowerShell

Source: https://github.com/mozilla-ai/cq/blob/main/DEVELOPMENT.md

Install the OpenCode component globally on Windows using the PowerShell wrapper script.

```powershell
.\scripts\install.ps1 install --target opencode --global
```

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

### Start Local CQ Server with Docker Compose

Source: https://github.com/mozilla-ai/cq/blob/main/README.md

Use these commands to quickly set up a local CQ server environment using Docker Compose and seed initial users.

```bash
make compose-up
make seed-users USER=demo PASS=demo123
```

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

### Install Windsurf using PowerShell

Source: https://github.com/mozilla-ai/cq/blob/main/DEVELOPMENT.md

Install the Windsurf component globally on Windows using the PowerShell wrapper script.

```powershell
.\scripts\install.ps1 install --target windsurf --global
```

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

### Install OpenCode Plugin

Source: https://github.com/mozilla-ai/cq/blob/main/README.md

Installs the OpenCode plugin for CQ. This command is part of the Makefile targets and requires the project to be cloned locally.

```bash
make install-opencode
```

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

### Install Cursor using PowerShell

Source: https://github.com/mozilla-ai/cq/blob/main/DEVELOPMENT.md

Install the Cursor component globally on Windows using the PowerShell wrapper script.

```powershell
.\scripts\install.ps1 install --target cursor --global
```

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

### Install CQ Claude Plugin

Source: https://github.com/mozilla-ai/cq/blob/main/README.md

Installs the CQ plugin for Claude using the plugin marketplace. Requires uv and Python 3.11+.

```bash
claude plugin marketplace add mozilla-ai/cq
claude plugin install cq
```

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

### Run Local Development Services

Source: https://github.com/mozilla-ai/cq/blob/main/DEVELOPMENT.md

Start all services using Docker Compose and seed the database with sample data. The remote API will be available at http://localhost:3000.

```bash
export CQ_JWT_SECRET=dev-secret
make compose-up
```

```bash
make seed-all USER=demo PASS=demo123
```

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

### Node Discovery Document Example (Reverse Proxy)

Source: https://github.com/mozilla-ai/cq/blob/main/docs/node-discovery-protocol.md

This example shows a discovery document when a reverse proxy strips path prefixes. The api_base_url points to the public-facing URL, and the proxy handles the internal routing.

```json
{
  "version": 1,
  "api_base_url": "https://api.example.com",
  "api_version": "v1"
}
```

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

### Install cq Plugin for Claude Code

Source: https://github.com/mozilla-ai/cq/blob/main/docs/CQ-Proposal.md

This command installs the cq plugin for Claude Code. The plugin bundles all necessary components for agent integration.

```bash
/plugin install cq@mozilla-ai-plugins
```

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

### Node Discovery Document Example (Split Origin)

Source: https://github.com/mozilla-ai/cq/blob/main/docs/node-discovery-protocol.md

This JSON document is served at /.well-known/cq-node.json for split-origin deployments. It specifies the full API base URL and protocol version.

```json
{
  "version": 1,
  "api_base_url": "https://api.example.com/api/v1",
  "api_version": "v1",
  "node_name": "example"
}
```

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

### Common CQ CLI Development Tasks

Source: https://github.com/mozilla-ai/cq/blob/main/cli/DEVELOPMENT.md

A list of common make targets for development. Use these for linting, testing, building, installing, cleaning artifacts, or viewing help.

```bash
make test      # Lint + test.
make build     # Build the cq binary.
make lint      # Run golangci-lint.
make install   # Copy binary to /usr/local/bin.
make clean     # Remove build artifacts.
make help      # Show all available targets.
```

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

### Install Claude Code

Source: https://github.com/mozilla-ai/cq/blob/main/DEVELOPMENT.md

Install the Claude Code component. To uninstall, use `make uninstall-claude`.

```bash
make install-claude
```

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

### Configure CQ Client with Options

Source: https://github.com/mozilla-ai/cq/blob/main/sdk/go/README.md

Instantiate the CQ client with specific configuration options for remote address and local database path.

```go
c, err := cq.NewClient(
    cq.WithAddr("http://localhost:3000"),
    cq.WithLocalDBPath("~/.local/share/cq/local.db"),
)
```

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

### Server Backend Development Commands

Source: https://github.com/mozilla-ai/cq/blob/main/server/backend/README.md

Run these commands from the repository root to set up, develop, test, and lint the server backend.

```bash
make setup-server-backend   # uv sync
make dev-api                # run against a local SQLite DB
make test-server-backend    # pytest
make lint-server-backend    # pre-commit (ruff, ty, uv lock check)
```

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

### Configure CQ Client Directly

Source: https://github.com/mozilla-ai/cq/blob/main/sdk/python/README.md

Instantiate the CQ client by passing configuration parameters directly.

```python
from pathlib import Path

cq = Client(
    addr="http://localhost:3000",
    local_db_path=Path("~/.local/share/cq/local.db").expanduser(),
)
```

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

### Clone CQ Repository and Download Go Modules

Source: https://github.com/mozilla-ai/cq/blob/main/cli/DEVELOPMENT.md

Clone the CQ repository and navigate to the CLI directory. Download the Go module dependencies required for development.

```bash
git clone https://github.com/mozilla-ai/cq.git
cd cq/cli
go mod download
```

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

### Webpack 5 Node.js Polyfill Fallback Configuration

Source: https://github.com/mozilla-ai/cq/blob/main/plugins/cq/skills/cq/SKILL.md

Example configuration for webpack 5 to add Node.js polyfills, specifically for the 'stream' module, when they are no longer built-in.

```javascript
resolve.fallback: { stream: require.resolve("stream-browserify") }
```

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

### Load and Use CQ Schemas and Constants

Source: https://github.com/mozilla-ai/cq/blob/main/schema/python/README.md

Demonstrates how to import and use parsed constants like DOMAIN_WEIGHT, INITIAL_CONFIDENCE, and CONFIRMATION_BOOST. It also shows how to load raw schema documents (as Python dict or bytes) for use with external validation libraries like jsonschema.

```python
import json

import jsonschema

from cq_schema import (
    CONFIRMATION_BOOST,
    DOMAIN_WEIGHT,
    INITIAL_CONFIDENCE,
    load_schema,
    load_schema_bytes,
)

# Parsed constants (immutable; treat as read-only).
print(DOMAIN_WEIGHT, INITIAL_CONFIDENCE, CONFIRMATION_BOOST)

# Raw schema documents.
schema = load_schema("knowledge_unit")
jsonschema.validate(instance=my_unit, schema=schema)

# Or as bytes if your validator prefers.
raw = load_schema_bytes("scoring")
```

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

### Confirming a Knowledge Unit

Source: https://github.com/mozilla-ai/cq/blob/main/sdk/python/src/cq/prompts/SKILL.md

Call `confirm` with the knowledge unit's ID after verifying its behavior. This is typically done after a successful integration or fix guided by a knowledge unit.

```python
confirm(knowledge_unit_id="ku_a1b2c3d4e5f6a1b2c3d4e5f6a1b2c3d4")
```

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

### Querying Before API Integration

Source: https://github.com/mozilla-ai/cq/blob/main/plugins/cq/skills/cq/SKILL.md

Use this pattern when integrating external APIs. Call `query` with relevant domain and language tags before starting the integration to retrieve potential knowledge units.

```text
query with domains: ["api", "payments", "stripe"] and languages: ["python"]
```

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

### Sync Canonical Prompts for Go SDK

Source: https://github.com/mozilla-ai/cq/blob/main/cli/DEVELOPMENT.md

Navigate to the Go SDK directory and sync the canonical prompts. This is a prerequisite for building the CLI due to a `replace` directive in `go.mod`.

```bash
cd ../sdk/go && make sync-prompts
```

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

### Run Linting

Source: https://github.com/mozilla-ai/cq/blob/main/sdk/python/README.md

Perform linting on the project using the make lint command.

```bash
make lint
```

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

### Accessing Agent Prompts

Source: https://github.com/mozilla-ai/cq/blob/main/sdk/go/README.md

Import and access predefined agent prompts like Skill and Reflect using the prompts package.

```go
import "github.com/mozilla-ai/cq/sdk/go/prompts"

skillPrompt := prompts.Skill()
reflectPrompt := prompts.Reflect()
```

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

### Display cq Knowledge Store Statistics

Source: https://github.com/mozilla-ai/cq/blob/main/plugins/cq/commands/status.md

Call the status MCP tool to get a summary of the cq knowledge store. This includes tier counts, domains, recent local additions, and confidence distribution.

```bash
mcp cq:status
```

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

### Configure CQ Client with Environment Variables

Source: https://github.com/mozilla-ai/cq/blob/main/sdk/python/README.md

The client reads configuration from environment variables. Default values are provided for each variable.

```bash
# Environment variables:
# CQ_ADDR: Remote cq API address (Default: None (local-only))
# CQ_API_KEY: API key (Default: None)
# CQ_LOCAL_DB_PATH: Local SQLite path (Default: ~/.local/share/cq/local.db)
```

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

### Knowledge Unit Schema Example

Source: https://github.com/mozilla-ai/cq/blob/main/docs/CQ-Proposal.md

Defines the structured format for knowledge units, ensuring interoperability between agents. This schema includes fields for ID, version, domain, insight summary/detail/action, context (language, frameworks, environment, pattern), and evidence.

```json
{
  "$schema": "https://cq.mozilla.ai/schemas/knowledge-unit/v1.json",
  "id": "ku_a1b2c3d4e5f6",
  "version": "1.0.0",
  "domain": ["api", "payments", "error-handling"],
  "insight": {
    "summary": "Stripe API v2024-12 returns HTTP 200 with error body for rate-limited requests instead of 429",
    "detail": "When rate-limited, the response status is 200 but the JSON body contains an error object. Agents should check the response body for an error field regardless of HTTP status code.",
    "action": "Always parse response body for error field before treating 2xx as success"
  },
  "context": {
    "language": ["typescript", "python", "go"],
    "frameworks": [],
    "environment": "server-side",
    "pattern": "api-integration"
  },
  "evidence": {
    "type": "object",
    "properties": {
      "page_title": {
        "type": "string",
        "description": "Concise title for the documentation page"
      },
      "page_description": {
        "type": "string",
        "description": "Brief description of the page content"
      },
      "page_summary": {
        "type": "string",
        "description": "Summary of the main concepts covered"
      },
      "codeSnippets": [
        {
          "title": "string",
          "description": "string",
          "language": "string",
          "codeList": [
            {
              "language": "string",
              "code": "string"
            }
          ]
        }
      ]
    },
    "required": [
      "page_title",
      "page_description",
      "page_summary",
      "codeSnippets"
    ]
  }
}
```

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

### Run Tests

Source: https://github.com/mozilla-ai/cq/blob/main/sdk/python/README.md

Execute tests for the project using the make test command.

```bash
make test
```

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

### Add CQ Skill to Agent

Source: https://github.com/mozilla-ai/cq/blob/main/docs/CQ-Proposal.md

Installs the cq skill and MCP server configuration for agents that support skills but not the full plugin format. This enables agents to query knowledge commons before executing unfamiliar API calls and propose new learnings.

```bash
npx skills add mozilla-ai/cq --skill cq
```