What is gemini-delegate?

A workflow for delegating tasks to Gemini CLI, Google's command-line AI tool, using multiple sign-in accounts and their usage limits.

Switch between stored Gemini accounts, pass context to Gemini, run repetitive visual or data tasks, and use Gemini to inspect very large files or logs.

It provides another AI system for second opinions, large-file reading, bulk work, or shifting work when another service reaches its limit.

gemini-delegate — Skill for Claude Code by AnastasiyaW

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 AnastasiyaW/codex-claude-code-config --skill gemini-delegate

Clone the repo

git clone --depth 1 https://github.com/AnastasiyaW/codex-claude-code-config

Made for: Claude Code.

Or install claude-code-config, the plugin that ships this one along with the rest of its 57 skills, 8 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/anastasiyaw/codex-claude-code-config/gemini-delegate.svg)](https://agentmods.dev/skills/anastasiyaw/codex-claude-code-config/gemini-delegate)

Your own site

<a href="https://agentmods.dev/skills/anastasiyaw/codex-claude-code-config/gemini-delegate"><img src="https://agentmods.dev/badge/skills/anastasiyaw/codex-claude-code-config/gemini-delegate.svg" alt="Measured on agentmods" height="20"></a>

Per session 119 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,341 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

high Agent Snooping · line 67
Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.

Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
medium analysis-evasion · line 1
Suspicious Unicode normalization or mixed-script content

Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00119	$0.02341
Opus 5	$0.00060	$0.01171
Sonnet 5	$0.00024	$0.00468
Haiku 4.5	$0.00012	$0.00234

Measured today against content hash 9811f5bd69e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

gemini-delegate scanned grade B with 1 finding 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 today.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- Gemini сам подхватывает `GEMINI.md`/`AGENTS.md` из cwd, если в `~/.gemini/settings.json`

skills/operational/gemini-delegate/SKILL.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gemini Delegate — capability preflight, квоты, передача контекста

Gemini CLI — внешний harness только после preflight установленного CLI, доступной модели, auth-path и наблюдаемой квоты. Его можно использовать как: (а) исполнителя bulk-задач (vision-курация, разметка, массовые однотипные prompts), (б) независимое second opinion другого вендора (Generator-Evaluator с настоящей независимостью — другая модель, другой провайдер), (в) читалку больших файлов/логов, (г) дополнительный исполнитель при подтверждённой доступности. Не считать его бесплатным OAuth fallback, гарантированным 1M-контекстом или автоматическим quota failover.

Preflight перед делегированием

Выполнять перед provider-вызовом только после явного запроса пользователя на Gemini. Preflight не устанавливает CLI, не логинится и не переключает аккаунт.

Снять статический факт: gemini --version и gemini --help. Если CLI не запускается, остановиться до делегирования и записать ошибку как локальный blocker.
Зафиксировать intended auth-path, но не считать наличие локального OAuth-stash доказательством доступа. В announcement Google от 2026-06-18 сказано, что Gemini CLI перестал обслуживать individual free/Pro/Ultra accounts; enterprise Gemini Code Assist и API-key auth затронуты не были. Это не является доказательством успешного текущего вызова.
Если owner явно выбрал модель, сохранить её exact slug. До вызова подтвердить, что этот slug доступен установленному CLI/current auth-path через его актуальный selector/документацию. Если slug не предложен или доступность нельзя проверить без неразрешённого account interaction, отклонить делегирование до task invocation — не подменять модель. Если модель не выбрана, записать только auto, а не предполагаемый конкретный slug. --model не задаёт модели subagent'ов.
Для batch снять timestamped /stats model после разрешённой аутентифицированной сессии; это наблюдение конкретной сессии, не обещание дневного бюджета. Quota error завершает попытку: без автоматического switch/failover.

Read the full file on GitHub · 135 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.

today Changed · +24 lines · -30 tokens per session 9811f5bd69e4
7d ago First seen · 111 lines · 149 tokens per session scan B d1d8491dd46a

Subscribe to this mod's changes

gemini-delegate is a skill published in the GitHub repository AnastasiyaW/codex-claude-code-config (149 stars, last pushed today), licensed MIT. It adds 119 tokens to every session and 2,341 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents Claude Code LLM ai-agents claude machine-learning prompt-engineering

gemini-delegate

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade B, and why

Reads agent configuration directoriesmediumAgent snooping

How it starts

Gemini Delegate — capability preflight, квоты, передача контекста

Preflight перед делегированием

What this file has done since we first saw it

Other skills, from other repositories

ai-content-filter

ai-product-manager

embedding-architect

few-shot-architect

hallucination-detector

model-card-writer