admin-assistant

admin-assistant is a skill for Claude Code, Codex from miticojo/ge-app-mcp. It costs 89 tokens per session (1,558 once invoked), scanned A, original, Apache-2.0.

A set of operating instructions for managing Gemini Enterprise applications in Google Cloud, including search and chat systems built over company data.

In plain words
What is it for?
Creating and managing data stores, data connections, schemas, documents, and related Gemini Enterprise resources.
Why use it?
It gives an agent a defined sequence for setting up and managing these cloud resources, reducing the chance of missing a required configuration step.

Skill for Claude CodeCodex

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

Good fit Creating and managing data stores, data connections, schemas, documents, and related Gemini Enterprise resources.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/miticojo/ge-app-mcp/admin-assistant
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 miticojo/ge-app-mcp --skill admin-assistant
Clone the repo
git clone --depth 1 https://github.com/miticojo/ge-app-mcp

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 admin-assistant

README.md
[![agentmods](https://agentmods.dev/badge/skills/miticojo/ge-app-mcp/admin-assistant/github.svg)](https://agentmods.dev/skills/miticojo/ge-app-mcp/admin-assistant)
Your own site
<a href="https://agentmods.dev/skills/miticojo/ge-app-mcp/admin-assistant"><img src="https://agentmods.dev/badge/skills/miticojo/ge-app-mcp/admin-assistant/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 admin-assistant

Your own site · 80×15
<a href="https://agentmods.dev/skills/miticojo/ge-app-mcp/admin-assistant"><img src="https://agentmods.dev/badge/skills/miticojo/ge-app-mcp/admin-assistant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,558 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 $0.00089 $0.01558
Opus 5.5 $0.00036 $0.00623
Sonnet 5.5 $0.00018 $0.00312
Haiku 4.5 $0.00009 $0.00156

Measured 13d ago against content hash c8d3d1e43463, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

admin-assistant 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 13d 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/admin-assistant/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gemini Enterprise Admin Assistant

Act as a careful Gemini Enterprise administrator. Every call runs with the identity of the person using you (local credentials, or their own OAuth token when this server runs inside Gemini Enterprise), so a 403 PERMISSION_DENIED means that person lacks the IAM role: explain which role is missing instead of retrying. USER_PROJECT_DENIED means they also need roles/serviceusage.serviceUsageConsumer.

1. Always inspect before you change

  • Always use gemini_enterprise_inspect and gemini_enterprise_inspect_licenses for every read, audit, or pre-change check — never call gemini_enterprise_manage_* or gemini_enterprise_configure_connector just to read (get, list, get-iam, list_runs, usage_stats). Both inspection tools are readOnlyHint: true, so inside Gemini Enterprise they run in parallel with zero user confirmation prompts.
  • Reserve gemini_enterprise_manage_* and gemini_enterprise_configure_connector strictly for actual changes, and call mutating tools one at a time (sequentially) inside Gemini Enterprise (tools that require user confirmation cannot run in parallel).
  • Report SERVER_DEFAULT values as "not overridden by an admin", not as on/off.
  • Long operations return status: RUNNING and an operation_name: poll it with gemini_enterprise_get_operation (also read-only) until DONE before the next dependent step.

2. Build a RAG app end to end

  1. gemini_enterprise_manage_datastore create (industry_vertical: GENERIC or MEDIA).
  2. Optional schema: gemini_enterprise_manage_schema create.
  3. Content: gemini_enterprise_manage_documents import (gcs_uri or bq_dataset), website crawling with gemini_enterprise_manage_target_sites, or a SaaS/custom MCP connector with gemini_enterprise_configure_connector.
  4. gemini_enterprise_manage_apps create with the data store IDs.

3. Connectors and citations

  • Inspect with gemini_enterprise_inspect (target: connector or connector_runs with collection_id); trigger a sync with gemini_enterprise_configure_connector start_run.
  • For custom MCP data stores, set citation chips with update_citation_mappings. The mapping is replaced entirely: start from the current citation_mappings, then edit. Keys are bare tool names ("" is the default entry); roles are items, uri (required), title, snippet, id; values are RFC 6901 JSON Pointers ("" or starting with /, ~1 for /, ~0 for ~). Changes apply to new chats.

Read the full file on GitHub · 91 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. 13d ago Changed · +18 lines · +60 tokens per session c8d3d1e43463
  2. 2mo ago First seen · 73 lines · 29 tokens per session scan A eb234d1ccf5e

Subscribe to this mod's changes

admin-assistant is a skill published in the GitHub repository miticojo/ge-app-mcp (0 stars, last pushed 13d ago), licensed Apache-2.0. It adds 89 tokens to every session and 1,558 once invoked, about $0.0004 per session on Opus 5.5. 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

admin-assistant compared with skills from other repositories

admin-assistant next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
admin-assistantmiticojo/ge-app-mcpSkill013d agoApache-2.0A89Claude Code, Codex
gke-compute-classesgoogle/skillsSkill24kyesterdayApache-2.0A83Claude Code, Codex
gke-reliabilitygoogle/skillsSkill24kyesterdayApache-2.0A85Claude Code, Codex
gke-workload-securitygoogle/skillsSkill24kyesterdayApache-2.0A171Claude Code, Codex
cloud-architectJeffallan/claude-skillsSkill12k8d agoMITA71Claude Code
nemo-automodel-launcher-configNVIDIA/skillsSkill3.9kyesterdayApache-2.0A30Claude Code
azure-mgmt-botservice-dotnetmicrosoft/skillsSkill3.2kyesterdayMITA78Claude Code