The agent Markdown format in this repository is fully compatible with Factory AI's custom droid system. AIWG agents are automatically transformed to Factory's native droid format during deployment.
Deploys AIWG agents to Factory AI's droid system with automatic tool mapping and model configuration. Use to convert Claude Code agents into Factory-compatible droids with multi-agent orchestration capabilities.
/plugin marketplace add jmagly/ai-writing-guide/plugin install sdlc@aiwgThe agent Markdown format in this repository is fully compatible with Factory AI's custom droid system. AIWG agents are automatically transformed to Factory's native droid format during deployment.
---
name: architecture-designer
description: Designs scalable, maintainable system architectures
model: opus
---
[System prompt...]
---
name: Architecture Designer
description: Designs scalable, maintainable system architectures and makes critical technical decisions for software projects
model: claude-opus-4-1-20250805
tools: ["Read", "LS", "Grep", "Glob", "Edit", "Create", "Execute"]
---
[System prompt...]
Key Differences:
tools array.factory/droids/) and personal (~/.factory/droids/) locationsAIWG defaults (Claude shorthand):
opussonnethaikuFactory defaults (full identifiers):
agentic/code/frameworks/sdlc-complete/config/models.jsonModel Configuration:
models.json configuration filemodels.json > User ~/.config/aiwg/models.json > AIWG defaultsModel mapping is automatic during deployment. The deploy script detects the original model type and maps to the appropriate Factory model using the configuration.
Use the deployment script to deploy agents for Factory:
# Deploy to current project
aiwg -deploy-agents --provider factory --mode sdlc
# Deploy commands too
aiwg -deploy-commands --provider factory --mode sdlc
# Or deploy everything at once
aiwg -deploy-agents --provider factory --mode both --deploy-commands
Override model mappings if needed:
aiwg -deploy-agents --provider factory --mode sdlc \
--reasoning-model claude-opus-4-1-20250805 \
--coding-model claude-sonnet-4-5-20250929 \
--efficiency-model claude-haiku-3-5
Deploy to your personal droids directory for cross-project use:
aiwg -deploy-agents --provider factory --mode sdlc --target ~/.factory
.claude/agents/*.md.codex/agents/*.md.factory/droids/*.md~/.factory/droids/*.mdFactory droids require explicit tool declarations. AIWG automatically maps Claude Code tools to Factory equivalents during deployment.
Claude Code → Factory (Anthropic Tools):
Factory uses Anthropic's tool naming conventions. AIWG maps Claude Code tools to these standard names:
| Claude Code | Factory/Anthropic Equivalent | Notes |
|---|---|---|
Bash | Execute | Shell command execution |
Write | Create, Edit | File creation and modification |
WebFetch | FetchUrl, WebSearch | Web content retrieval |
MultiEdit | MultiEdit, ApplyPatch | Multiple file edits and patch application |
Read, Grep, Glob, LS | Same names | Already Anthropic tools |
Note: Factory respects Anthropic's tool naming, so all mapped tools use standard Anthropic tool IDs.
Orchestration agents automatically receive additional tools:
Orchestration agents include:
Original (Claude Code):
---
name: Architecture Designer
description: Designs scalable, maintainable system architectures
model: opus
tools: Bash, Glob, Grep, MultiEdit, Read, WebFetch, Write
---
Deployed (Factory):
---
name: Architecture Designer
description: Designs scalable, maintainable system architectures
model: claude-opus-4-1-20250805
tools: ["ApplyPatch", "Create", "Edit", "Execute", "FetchUrl", "Glob", "Grep", "MultiEdit", "Read", "Task", "TodoWrite", "WebSearch"]
---
Changes:
Bash → Execute (Anthropic tool)Write → Create + Edit (Anthropic tools)WebFetch → FetchUrl + WebSearch (Anthropic tools)MultiEdit → MultiEdit + ApplyPatch (Anthropic tools)Task (Factory tool for invoking subagents)TodoWrite (Anthropic tool for progress tracking)You can further restrict tools after deployment:
# Edit a droid
code .factory/droids/architecture-designer.md
# Modify tools array in frontmatter
tools: ["Read", "LS", "Grep", "Glob", "Edit", "Create"] # Removed Execute
Common tool restrictions:
["Read", "LS", "Grep", "Glob"]["Read", "LS", "Grep", "Glob", "Edit", "Create", "ApplyPatch"]["Read", "LS", "Grep", "Glob", "Edit", "Create", "MultiEdit", "ApplyPatch", "Execute"]["Read", "LS", "Grep", "Glob", "Edit", "Create", "MultiEdit", "ApplyPatch", "Execute", "Task", "TodoWrite"]["Read", "LS", "Grep", "Glob", "Edit", "Create", "MultiEdit", "ApplyPatch", "Execute", "Task", "TodoWrite", "WebSearch", "FetchUrl"]All tools are Anthropic standard tools, ensuring compatibility across Factory and other Anthropic-based platforms.
Factory droids can be invoked directly via natural language:
"Use architecture-designer to create the SAD"
"Ask security-architect to review authentication"
"Have test-engineer create test plan"
Factory handles multi-agent workflows automatically:
"Create architecture baseline"
→ Factory coordinates:
1. architecture-designer (draft)
2. security-architect (review)
3. test-architect (review)
4. requirements-analyst (review)
5. documentation-synthesizer (merge)
Factory provides a Task tool for explicit droid invocation with structured prompts.
Claude Code:
.claude/agents/<agent> tagsFactory:
.factory/droids/ (project) or ~/.factory/droids/ (personal)OpenAI/Codex:
.codex/agents/Factory:
.factory/droids/See the comprehensive Factory quickstart guide:
Location: docs/integrations/factory-quickstart.md
Quick Commands:
# Install AIWG
curl -fsSL https://raw.githubusercontent.com/jmagly/ai-writing-guide/main/tools/install/install.sh | bash
# Deploy to Factory project
cd /path/to/project
aiwg -deploy-agents --provider factory --mode sdlc --deploy-commands
# Verify deployment
ls .factory/droids/ # Should show 53 SDLC droids
ls .factory/commands/ # Should show 42+ commands
docs/integrations/factory-quickstart.mdtools/agents/deploy-agents.mjsFor Factory-specific questions:
For AIWG integration questions:
You are an elite AI agent architect specializing in crafting high-performance agent configurations. Your expertise lies in translating user requirements into precisely-tuned agent specifications that maximize effectiveness and reliability.