agent-spec

agent-spec is a command for Claude Code from frankxai/claude-code-oracle-skills. It costs 10 tokens per session (216 once invoked), scanned A, original, Apache-2.0.

A command that creates an Oracle Agent Spec, a framework-independent description of an AI agent’s components, tools, and workflow, in YAML or JSON.

In plain words
What is it for?
Use it to describe agents such as research assistants or customer-support agents, including their nodes, tools, workflow, and entry point.
Why use it?
It separates the agent’s design from the software framework used to run it, making the design easier to compile for different frameworks.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the oracle-agent-spec plugin — 1 command shipped together

Good fit Use it to describe agents such as research assistants or customer-support agents, including their nodes, tools, workflow, and entry point.

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

Clone the repo
git clone --depth 1 https://github.com/frankxai/claude-code-oracle-skills

Made for: Claude Code.

Or install oracle-agent-spec, the plugin that ships this one along with the rest of its 1 command.

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 agent-spec

README.md
[![agentmods](https://agentmods.dev/badge/commands/frankxai/claude-code-oracle-skills/agent-spec.svg)](https://agentmods.dev/commands/frankxai/claude-code-oracle-skills/agent-spec)
Your own site
<a href="https://agentmods.dev/commands/frankxai/claude-code-oracle-skills/agent-spec"><img src="https://agentmods.dev/badge/commands/frankxai/claude-code-oracle-skills/agent-spec.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 216 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 $0.00010 $0.00216
Opus 5 $0.00005 $0.00108
Sonnet 5 $0.00002 $0.00043
Haiku 4.5 $0.00001 $0.00022

Measured 8d ago against content hash d2c4a55f1647, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

agent-spec 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 8d 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.

plugins/oracle-agent-spec/commands/agent-spec.md · 38 lines

What it actually says

Context

You are generating an Oracle Agent Spec definition that can be compiled to any framework.

Available formats:

  • yaml - YAML specification (default)
  • json - JSON specification

Your Task

  1. Ask what the agent should do if not clear
  2. Read the oracle-agent-spec skill: plugins/oracle-agent-spec/skills/SKILL.md
  3. Design the agent structure (nodes, tools, workflow)
  4. Generate the specification in requested format
  5. Explain how to compile to different frameworks

Generated Output

A complete Agent Spec including:

  • Agent metadata (name, version, description)
  • Component definitions (LLMNode, AgentNode, etc.)
  • Tool specifications
  • Workflow orchestration
  • Entry point

Example Invocations

/agent-spec research-assistant yaml
/agent-spec customer-support json
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. 8d ago First seen · 38 lines · 0 tokens per session scan A d2c4a55f1647

Subscribe to this mod's changes

agent-spec is a command published in the GitHub repository frankxai/claude-code-oracle-skills (2 stars, last pushed 11d ago), licensed Apache-2.0. It adds 10 tokens to every session and 216 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 2026-08-31.