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.
npx agentmods add skills/jmagly/aiwg/devkit-create-addonnpx skills add jmagly/aiwg --skill devkit-create-addongit clone --depth 1 https://github.com/jmagly/aiwgWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00016 | $0.00633 |
| Opus 5 | $0.00008 | $0.00316 |
| Sonnet 5 | $0.00003 | $0.00127 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade A, and why
devkit-create-addon scanned grade A with 0 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 2d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create AIWG Addon
Create a new standalone addon with AI assistance.
Usage
/devkit-create-addon <name> [--interactive]
Arguments
| Argument | Required | Description |
|---|---|---|
| name | Yes | Addon name (kebab-case recommended) |
Options
| Option | Description |
|---|---|
| --interactive | Enable interactive mode with guided questions |
What This Creates
agentic/code/addons/<name>/
├── manifest.json # Addon configuration
├── README.md # Documentation
├── agents/ # Agent definitions
├── commands/ # Slash commands
└── skills/ # Auto-triggered skills
Interactive Mode
When --interactive is specified, I will ask:
- Purpose: What is the primary purpose of this addon?
- Capabilities: What specific capabilities should it provide?
- Initial agents: Should I create any starter agents?
- Initial commands: Should I create any starter commands?
- Core status: Should this be a core addon (auto-installed)?
Examples
# Quick creation
/devkit-create-addon security-scanner
# Interactive guided creation
/devkit-create-addon code-metrics --interactive
Execution
- Validate name: Ensure name follows kebab-case convention
- Check existence: Verify addon doesn't already exist
- Gather info: In interactive mode, ask clarifying questions
- Generate manifest: Create manifest.json with appropriate fields
- Create structure: Build directory structure
- Generate README: Create documentation with usage instructions
- Optionally create components: If interactive, offer to create initial agents/commands
- Report success: Show created files and next steps
CLI Equivalent
For non-interactive creation, you can also use:
aiwg scaffold-addon <name> --description "..." --author "..."
Related Commands
/devkit-create-agent- Add agent to addon/devkit-create-command- Add command to addon/devkit-create-skill- Add skill to addon/devkit-validate- Validate addon structure
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.
- 2d ago First seen · 94 lines · 16 tokens per session scan A be8280e7c279
devkit-create-addon is a skill published in the GitHub repository jmagly/aiwg (205 stars, last pushed 4d ago), licensed MIT. It adds 16 tokens to every session and 633 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
nightshift
Run an accountable autonomous shift — work a punch list to completion, evolve a product from research, park decisions instead of asking, and leave receipts. Use when the user wants to work through a todo list autonomously, spend remaining agent usage, run overnight, polish or improve a product, research competitors…
role-dev
Use when exactly one approved work package (WORK card) should be implemented — including as a DEV subagent in autonomous-loop. Not for scope decisions, reviews, or when no approved card exists.
autopilot
Full autonomous execution from idea to working code.
graph
Deterministic orchestration graph runtime - declarative DAG pipelines with journal-based crash recovery.
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
deep-interview
Socratic deep interview with mathematical ambiguity gating before explicit execution approval.