ai-native-development

ai-native-development is a skill for Claude Code, Codex from ArieGoldkin/claude-forge. It costs 108 tokens per session (1,213 once invoked), scanned A, original, MIT.

A guide to building applications around AI models, including document retrieval, vector search, tool use, agent workflows, prompts, streaming, and cost control. It covers approaches such as RAG, where answers use retrieved documents.

In plain words
What is it for?
Use it when integrating an AI model, building search over documents, adding tools or agents, designing prompts, or handling streamed responses.
Why use it?
It brings common AI application design patterns together when adding model-based features to software.

Skill for Claude CodeCodex

Part of the atk plugin — 16 skills, 25 commands, 1 agent, 1 hook shipped together

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/ariegoldkin/claude-forge/ai-native-development
Any agent
npx skills add ArieGoldkin/claude-forge --skill ai-native-development
Clone the repo
git clone --depth 1 https://github.com/ArieGoldkin/claude-forge

Made for: Claude Code, Codex.

Or install atk, the plugin that ships this one along with the rest of its 16 skills, 25 commands, 1 agent, 1 hook.

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 ai-native-development

README.md
[![agentmods](https://agentmods.dev/badge/skills/ariegoldkin/claude-forge/ai-native-development.svg)](https://agentmods.dev/skills/ariegoldkin/claude-forge/ai-native-development)
Your own site
<a href="https://agentmods.dev/skills/ariegoldkin/claude-forge/ai-native-development"><img src="https://agentmods.dev/badge/skills/ariegoldkin/claude-forge/ai-native-development.svg" alt="Measured on agentmods" height="20"></a>
Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,213 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 5.1 $0.00108 $0.01213
Opus 5 $0.00054 $0.00607
Sonnet 5 $0.00022 $0.00243
Haiku 4.5 $0.00011 $0.00121

Measured 5d ago against content hash b29a7648b9cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

ai-native-development 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 5d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (examples/chatbot-with-rag-example.ts, templates/agent-workflow-template.ts, templates/rag-pipeline-template.ts), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/ai-toolkit/skills/ai-native-development/SKILL.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI-Native Development

Core Concepts

Embeddings & Vector Search

See ${CLAUDE_SKILL_DIR}/references/vector-databases.md for embeddings setup, cosine similarity, chunking strategies, and vector database guides (Pinecone, Chroma, Weaviate, Qdrant).

RAG (Retrieval-Augmented Generation)

See ${CLAUDE_SKILL_DIR}/references/rag-patterns.md for basic and advanced RAG patterns, citation strategies, hybrid search with Reciprocal Rank Fusion, conversation memory patterns, and error handling.

Function Calling & Tool Use

See ${CLAUDE_SKILL_DIR}/references/function-calling.md for tool definition patterns (OpenAI and Anthropic), function calling loops, parallel and streaming tool execution, input validation with Zod, and error handling.

Agentic Workflows

Enable LLMs to reason, plan, and take autonomous actions.

Patterns:

  • ReAct: Reasoning + Acting loop with observations
  • Tree of Thoughts: Explore multiple reasoning paths
  • Multi-Agent: Specialized agents collaborating on complex tasks
  • Autonomous Agents: Self-directed goal achievement
  • ML Experiment Loops: Autonomous iteration on ML metrics using /experiment for hyperparameter tuning, evaluation improvement, and model selection. See ${CLAUDE_SKILL_DIR}/references/ml-experiment-loops.md for patterns and worked examples.

Detailed Implementation: See ${CLAUDE_SKILL_DIR}/references/agentic-workflows.md for:

  • Complete ReAct loop implementation
  • Tree of Thoughts exploration
  • Multi-agent coordinator patterns
  • Agent memory management
  • Error recovery and safety guards

Multi-Agent Orchestration (Opus 4.5)

Advanced multi-agent patterns leveraging Opus 4.5's extended thinking capabilities.

When to Use Extended Thinking:

  • Coordinating 3+ specialized agents
  • Complex dependency resolution between agent outputs
  • Dynamic task allocation based on agent capabilities
  • Conflict resolution when agents produce contradictory results

Key Patterns:

  • Orchestrator with dependency graph execution
  • Task planning with extended thinking budget
  • Conflict detection and resolution
  • Adaptive agent selection based on task complexity
  • Agent communication bus for coordination

Read the full file on GitHub · 148 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. 5d ago First seen · 148 lines · 108 tokens per session scan A b29a7648b9cb

Subscribe to this mod's changes

ai-native-development is a skill published in the GitHub repository ArieGoldkin/claude-forge (6 stars, last pushed 28d ago), licensed MIT. It adds 108 tokens to every session and 1,213 once invoked, about $0.0005 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 2026-08-31.

Related

Other skills, from other repositories