Oracle Agent Spec Expert

Oracle Agent Spec Expert is a skill for Claude Code, Codex from frankxai/claude-code-oracle-skills. It costs 31 tokens per session (2,800 once invoked), scanned A, original, Apache-2.0.

A guide to Oracle’s Open Agent Specification, a JSON/YAML format for describing AI agents and workflows independently of a particular software framework. This makes the same design easier to use across compatible runtimes.

In plain words
What is it for?
Use it to define standalone agents, workflows, and multi-agent systems in portable JSON or YAML specifications.
Why use it?
It reduces duplicated work when an agent design may need to run in different frameworks or execution environments.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to define standalone agents, workflows, and multi-agent systems in portable JSON or YAML specifications.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/frankxai/claude-code-oracle-skills/oracle-agent-spec
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.

Any agent
npx skills add frankxai/claude-code-oracle-skills --skill oracle-agent-spec
Clone the repo
git clone --depth 1 https://github.com/frankxai/claude-code-oracle-skills

Made for: Claude Code, Codex.

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 Oracle Agent Spec Expert

README.md
[![agentmods](https://agentmods.dev/badge/skills/frankxai/claude-code-oracle-skills/oracle-agent-spec/github.svg)](https://agentmods.dev/skills/frankxai/claude-code-oracle-skills/oracle-agent-spec)
Your own site
<a href="https://agentmods.dev/skills/frankxai/claude-code-oracle-skills/oracle-agent-spec"><img src="https://agentmods.dev/badge/skills/frankxai/claude-code-oracle-skills/oracle-agent-spec/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for Oracle Agent Spec Expert

Your own site · 80×15
<a href="https://agentmods.dev/skills/frankxai/claude-code-oracle-skills/oracle-agent-spec"><img src="https://agentmods.dev/badge/skills/frankxai/claude-code-oracle-skills/oracle-agent-spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,800 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00031 $0.02800
Opus 5 $0.00015 $0.01400
Sonnet 5 $0.00006 $0.00560
Haiku 4.5 $0.00003 $0.00280

Measured 12d ago against content hash a241e6679a23, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

Oracle Agent Spec Expert 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 12d 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.

skills/oracle-agent-spec/SKILL.md · 488 lines

How it starts

The opening of the file, as written. The whole thing — 488 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Oracle Agent Spec Expert Skill

Purpose

Master Oracle's Open Agent Specification (Agent Spec) to design framework-agnostic, declarative AI agents that can be authored once and deployed across multiple frameworks and runtimes.

What is Agent Spec?

Open Agent Specification

Framework-agnostic declarative language for defining agentic systems, building blocks for standalone agents and structured workflows, plus composition patterns for multi-agent systems.

Key Innovation: Decouple design from execution - write agents once, run anywhere.

Release: Technical report published October 2025 (arXiv:2510.04173)

Core Philosophy

The Problem: Fragmented agent development - each framework requires different implementation.

The Solution: Unified representation - Agent Spec defines structure and behavior in JSON/YAML that any compatible runtime can execute.

Benefit: Author agents once → Deploy across frameworks → Reduce redundant development.

Architecture

Component Model

Agent Spec defines conceptual building blocks (components) that make up agent-based systems.

Key Property: All components are trivially serializable to JSON/YAML.

Core Components

1. LLMNode

Purpose: Text generation via LLM

Definition:

type: LLMNode
name: "text_generator"
model: "claude-sonnet-4-5"
system_prompt: "You are a helpful assistant"
temperature: 0.7
max_tokens: 2000
2. APINode

Purpose: External API calls

Definition:

type: APINode
name: "weather_api"
endpoint: "https://api.weather.com/v1/current"
method: "GET"
parameters:
  location: "{input.location}"
headers:
  Authorization: "Bearer {env.API_KEY}"
3. AgentNode

Purpose: Multi-round conversational agent

Definition:

type: AgentNode
name: "support_agent"
model: "gpt-4"
system_prompt: "You are a customer support specialist"
tools:
  - type: function
    name: "lookup_order"
  - type: function
    name: "process_refund"

Read the full file on GitHub · 488 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. 12d ago First seen · 488 lines · 31 tokens per session scan A a241e6679a23

Subscribe to this mod's changes

Oracle Agent Spec Expert is a skill published in the GitHub repository frankxai/claude-code-oracle-skills (2 stars, last pushed 15d ago), licensed Apache-2.0. It adds 31 tokens to every session and 2,800 once invoked, about $0.0002 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.