appendix-agentspace

appendix-agentspace is a skill for Claude Code, Codex from hajekim/agentic-design-patterns-extension. It costs 421 tokens per session (3,227 once invoked), scanned A, a copy of appendix-agentspace, MIT.

A guide to Google AgentSpace, a no-code Google Cloud platform for building enterprise AI agents through a visual interface. It connects agent instructions with company data sources and Knowledge Graph, Google's system for linking information.

In plain words
What is it for?
Use it to prototype or deploy business agents, connect Google Workspace or other enterprise data, and configure agents for non-developer teams.
Why use it?
It helps teams build context-aware agents without writing a full application when their needs can be described through instructions and data connections.

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/hajekim/agentic-design-patterns-extension/appendix-agentspace
Any agent
npx skills add hajekim/agentic-design-patterns-extension --skill appendix-agentspace
Clone the repo
git clone --depth 1 https://github.com/hajekim/agentic-design-patterns-extension

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 appendix-agentspace

README.md
[![agentmods](https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-extension/appendix-agentspace.svg)](https://agentmods.dev/skills/hajekim/agentic-design-patterns-extension/appendix-agentspace)
Your own site
<a href="https://agentmods.dev/skills/hajekim/agentic-design-patterns-extension/appendix-agentspace"><img src="https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-extension/appendix-agentspace.svg" alt="Measured on agentmods" height="20"></a>
Per session 421 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,227 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00421 $0.03227
Opus 5 $0.00211 $0.01614
Sonnet 5 $0.00084 $0.00645
Haiku 4.5 $0.00042 $0.00323

Measured 4d ago against content hash 3f993ef7f633, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

appendix-agentspace 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 4d 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.

Origin

This is a copy

100% identical to appendix-agentspace — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/appendix-agentspace/SKILL.md · 300 lines

How it starts

The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Appendix D - Google AgentSpace

Overview

Google AgentSpace is a no-code enterprise agent platform that enables organizations to build and deploy AI agents without deep programming expertise. It provides a graphical user interface for agent construction, integrating Google Cloud's AI capabilities, enterprise datastores, and Knowledge Graph into a unified, configurable system.

AgentSpace abstracts the underlying technical complexity — autonomous reasoning, knowledge graph mapping, data source integration — into a visual interface where users define agent behavior through prompts, configure knowledge sources, and deploy agents accessible via web interface.

Core Principle: Not all agents need code. AgentSpace enables business teams to deploy context-aware AI agents by configuring prompts and data sources — democratizing agent development beyond engineering teams.

When This Skill Applies

Activate this pattern when:

  • Business teams (not just developers) need to deploy AI agents
  • Agents need deep integration with enterprise Google Workspace data
  • The use case is well-defined and can be specified through prompts
  • Rapid prototyping is needed before committing to code-based agents
  • Organization uses Google Cloud and wants native integration
  • The agent needs Knowledge Graph enrichment for factual accuracy
  • Analytics and monitoring of agent usage is required without custom instrumentation

Rule of thumb: If the agent's behavior can be described in a system prompt and the data sources are Google Cloud datastores, AgentSpace is faster than code. If you need custom logic, loops, or non-Google integrations, use ADK or LangGraph.

AgentSpace Architecture

┌─────────────────────────────────────────────────────┐
│                 Google AgentSpace                    │
│                                                      │
│  ┌──────────────┐  ┌─────────────┐  ┌────────────┐ │
│  │ Prompt Gallery│  │  Agent      │  │ Analytics  │ │
│  │ (Google-made +│  │  Designer   │  │ Dashboard  │ │
│  │  Custom)      │  │  (No-code)  │  │            │ │
│  └──────┬───────┘  └──────┬──────┘  └────────────┘ │
│         │                 │                          │
│  ┌──────▼─────────────────▼──────────────────────┐  │
│  │              Agent Runtime                     │  │
│  │  (Gemini model + Prompt + Knowledge + Data)    │  │
│  └──────────────────────┬─────────────────────────┘  │
│                         │                            │
│  ┌──────────┐  ┌────────▼────────┐  ┌────────────┐  │
│  │ Google   │  │ Connected Data  │  │ Web UI     │  │
│  │ Knowledge│  │ Stores          │  │ (Chat)     │  │
│  │ Graph    │  │ (BigQuery, GCS) │  │            │  │
│  └──────────┘  └─────────────────┘  └────────────┘  │
└─────────────────────────────────────────────────────┘

Read the full file on GitHub · 300 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. 4d ago First seen · 300 lines · 421 tokens per session scan A 3f993ef7f633

Subscribe to this mod's changes

appendix-agentspace is a skill published in the GitHub repository hajekim/agentic-design-patterns-extension (1 stars, last pushed 5mo ago), licensed MIT. It adds 421 tokens to every session and 3,227 once invoked, about $0.0021 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to appendix-agentspace, differing in 3 lines, and is treated as a copy.