droid

droid is an agent for coding agents from a5c-ai/babysitter. It costs 0 tokens per session (1,600 once invoked), scanned C, original, MIT.

A command-line AI coding agent from Factory AI that can work with a terminal and automate software-development workflows.

In plain words
What is it for?
Use it for end-to-end coding work, debugging, refactoring, and CI/CD tasks through the Droid command-line program.
Why use it?
It gives developers a way to ask an AI agent for help with tasks such as debugging or refactoring, either interactively or without a live chat.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/a5c-ai/babysitter/droid
Clone the repo
git clone --depth 1 https://github.com/a5c-ai/babysitter

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for droid

README.md
[![agentmods](https://agentmods.dev/badge/agents/a5c-ai/babysitter/droid.svg)](https://agentmods.dev/agents/a5c-ai/babysitter/droid)
Your own site
<a href="https://agentmods.dev/agents/a5c-ai/babysitter/droid"><img src="https://agentmods.dev/badge/agents/a5c-ai/babysitter/droid.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,600 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01600
Opus 5 $0.00000 $0.00800
Sonnet 5 $0.00000 $0.00320
Haiku 4.5 $0.00000 $0.00160

Measured 3d ago against content hash 069af4d5f17e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

droid scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://get.factory.ai/droid | bash

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

### curl (Universal)
docs/adapters/reference/agents/droid.md · 257 lines

How it starts

The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Droid

Factory AI's enterprise-grade AI coding agent with terminal integration and sophisticated workflow automation.

Overview

Factory Droid is a top-performing AI coding agent built by Factory AI that provides end-to-end development workflows, debugging, refactoring, and CI/CD integration. Droid scores 58.75% on terminal benchmarks and supports both interactive chat and headless automation modes.

Installation

NPM (Recommended)

npm install -g @factory/cli

Homebrew (macOS)

brew install factory/tap/droid

curl (Universal)

curl -fsSL https://get.factory.ai/droid | bash

Authentication

Factory AI Account Setup

  1. Sign up at factory.ai/signup
  2. Install Droid CLI (see Installation above)
  3. Authenticate with Factory AI:
    droid auth login
    
  4. Verify authentication:
    droid whoami
    

Environment Variables

export DROID_API_KEY=your_factory_api_key

Usage with adapters

Basic Chat

adapters run droid --prompt "Help me refactor this API endpoint"

Resume Session

adapters run droid --session-id abc123 --prompt "Continue with the optimization"

Model Selection

adapters run droid --model gpt-5-turbo --prompt "Generate a complete REST API"
adapters run droid --model claude-sonnet --prompt "Review this code for security issues"
adapters run droid --model gemini-flash --prompt "Create unit tests for this module"

Auto-approve Tools (Yolo Mode)

adapters run droid --tool-approval-mode yolo --prompt "Fix all linting errors in src/"

Working Directory

adapters run droid --cwd /path/to/project --prompt "Analyze the codebase structure"

Supported Models

Model ID Alias Context Window Output Tokens Input Price Output Price
gpt-5-turbo gpt-5-turbo 256,000 16,384 $2.00/1M $8.00/1M
claude-3-5-sonnet-20241022 claude-sonnet 200,000 8,192 $3.00/1M $15.00/1M
gemini-2-flash gemini-flash 1,000,000 8,192 $0.075/1M $0.30/1M

Read the full file on GitHub · 257 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 257 lines · 0 tokens per session scan C 069af4d5f17e

Subscribe to this mod's changes

droid is an agent published in the GitHub repository a5c-ai/babysitter (1,762 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,600 tokens. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

development-workflows-research-agent

Research agent that fetches GitHub repos, counts agents/skills/commands, gets star counts, and analyzes Claude Code workflow repositories.

shanraisshan/claude-code-best-practice · 33 tokens

rn-code-architect

Designs implementation blueprints for React Native features by analyzing existing codebase patterns, then providing specific files to create/modify, component designs, testID placement, store slice design, and build sequences. Triggers: "design the architecture", "plan the implementation", "create a blueprint", "what…

Lykhoyda/rn-dev-agent · 238 tokens

rn-code-reviewer

Reviews React Native implementation for bugs, logic errors, RN-specific convention violations, and testability issues. Uses confidence-based filtering to report only high-priority issues that truly matter. Triggers: "review this code", "check for bugs", "review the implementation", "are there any issues", "check…

Lykhoyda/rn-dev-agent · 234 tokens

design-author

Use after research is complete to draft the approach before any code is written. Drafts a 200-line design document covering current state, desired end state, patterns to follow, and decisions made. Resolves its own open questions autonomously, recording each as an explicit, auditable assumption in the design.

bostonaholic/team · 64 tokens

security-reviewer

Use when a security review is needed after implementation. Applies OWASP-style checks with fresh context. Critical findings are a hard gate — they block shipping until resolved. Example triggers — "security review", "check for vulnerabilities", "audit this code for security issues".

bostonaholic/team · 56 tokens

planner

Use after the structure is produced to create the tactical implementation plan. Translates each vertical slice in structure.md into precise file-level steps with acceptance test mappings. The plan is a tactical artifact for the implementer — neither the structure nor the plan is human-reviewed (the design passed…

bostonaholic/team · 61 tokens