devkit-create-agent

An AI-assisted scaffolding tool for creating a new software agent, including its area of expertise, workflow, and capabilities. It follows a set of design rules for production agents.

In plain words
What is it for?
It helps create single-purpose, more complex, or coordinating agents for an add-on or framework, with optional guided questions.
Why use it?
It removes the need to design the agent structure and supporting files from scratch.

Skill for Claude CodeCodex

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 skills/jmagly/aiwg/devkit-create-agent
Any agent
npx skills add jmagly/aiwg --skill devkit-create-agent
Clone the repo
git clone --depth 1 https://github.com/jmagly/aiwg

Made for: Claude Code, Codex.

Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,276 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00020 $0.01276
Opus 5 $0.00010 $0.00638
Sonnet 5 $0.00004 $0.00255
Haiku 4.5 $0.00002 $0.00128

Measured 3d ago against content hash e5608549c571, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

devkit-create-agent 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 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.

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.

agentic/code/addons/aiwg-dev/skills/devkit-create-agent/SKILL.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create AIWG Agent

Create a new agent with AI assistance to define expertise, workflow, and capabilities.

Follows: Agent Design Bible - 10 Golden Rules for production-grade agents.

Research Foundation: REF-001 (Bandara et al.), REF-002 (Roig 2025) failure archetype prevention.

Usage

/devkit-create-agent <name> --to <target> [options]

Arguments

Argument Required Description
name Yes Agent name (kebab-case recommended)

Required Options

Option Description
--to Target addon or framework

Optional Options

Option Description
--template Agent template: simple (default), complex, orchestrator
--interactive Enable interactive mode with guided questions

Templates

Templates are in ~/.local/share/ai-writing-guide/templates/agent-scaffolding/.

simple (default)

Single-purpose, focused agent with minimal structure (Rule 1: Single Responsibility).

  • Best for: Utility agents, single-task specialists
  • Model: haiku (efficiency tier)
  • Tools: Read, Write (Rule 2: Minimal Tools)

complex

Full reasoning agent with all safeguards including failure archetype prevention.

  • Best for: Subject matter experts, reviewers, analysts
  • Model: sonnet/opus (based on complexity)
  • Tools: Read, Write, Grep (Rule 2: 0-3 tools)
  • Includes: Grounding, uncertainty handling, recovery protocol

orchestrator

Multi-agent coordination with workflow patterns and agent assignment tables.

  • Best for: Workflow coordinators, phase managers
  • Model: opus (Rule 8: reasoning tier for coordination)
  • Tools: Task only (Rule 2: single tool for delegation)

validator

Read-only validation agent that doesn't modify state.

  • Best for: Quality gates, compliance checks, code review
  • Model: haiku/sonnet
  • Tools: Read, Grep (read-only)

Interactive Mode

When --interactive is specified, I will ask:

Read the full file on GitHub · 178 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 · 178 lines · 20 tokens per session scan A e5608549c571

Subscribe to this mod's changes

devkit-create-agent is a skill published in the GitHub repository jmagly/aiwg (205 stars, last pushed 5d ago), licensed MIT. It adds 20 tokens to every session and 1,276 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.