Skip to content
Agentmart
Submit a tool

gemini-cli

Invoke Gemini models non-interactively through the installed CLI, check subscription quota, and consume agent responses.

Skill by 0tomi

IndexedMIT★ 3
Write a review

Chalk Labs

Need help deploying gemini-cli?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/0tomi-gemini-cli

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Invoke Gemini models non-interactively through the installed CLI, check subscription quota, and consume agent responses.

Use cases: agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 26, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/gemini-cli

What's inside

Skill name
gemini-cli
Description
Invoke Gemini models non-interactively through the installed CLI, check subscription quota, and consume agent responses.
License
MIT
Instructions
146 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Gemini CLI

Use the installed `agy` CLI to invoke Gemini models non-interactively.

## Default invocation

Invoke Gemini with:

```bash
agy -p "<PROMPT>" \
  --model <MODEL> \
  --print-timeout 30m
```

The command waits for Gemini to complete, prints its final response to `stdout`, and exits.

Diagnostics and errors are written to `stderr`.

Use the normal text output by default. Do not request JSON output for ordinary Gemini invocations.

## Models

Use one of these Gemini model slugs:

```text
gemini-3.7-flash-high
gemini-3.1-pro-high
gemini-3.8-flash-high
```

These model variants already select high reasoning effort. Do not add an `--effort` flag.

Gemini 4 Argon is also available, with three reasoning effort levels: `low`, `medium`, and `high`. The user chooses the level. Use the slug `gemini-4-argon-<EFFORT>`, for example `gemini-4-argon-high`.

Inspect currently available models with:

```bash
agy models
```

Do not invent model slugs.

If an explicitly selected model is unavailable or invalid, treat it as an execution failure rather than silently substituting another model.

## Quota failure handling

If a Gemini invocation later fails, refuses to execute, times out unexpectedly, or produces no usable response, verify subscription quota:

```bash
agy -p "/usage"
```

If `/usage` confirms exhausted Gemini quota:

* Stop using Gemini.
* Do not retry the failed request.
* Do not repeatedly probe Gemini.
* Treat Gemini as unavailable for the remainder of the current orchestration run.

If `/usage` reports remaining quota, do not classify the failure as quota exhaustion.

Handle it as a normal execution, model, permission, timeout, configuration, or service failure.

Temporary service or capacity failures must not disable Gemini unless `/usage` confirms exhausted quota.

## Conversations

Continue the latest conversation with:

```bash
agy -p "<PROMPT>" --continue
```

or:

```bash
agy -p "<PROMPT>" -c
```

Resume a known conversation with:

```bash
agy -p "<PROMPT>" \
  --conversation <CONVERSATION_ID>
```

Prefer independent invocations unless previous Gemini conversation context is useful or required.

## Timeout

Override the headless timeout with:

```bash
--print-timeout <DURATION>
```

Recommended default:

```bash
--print-timeout 30m
```

## Permissions

Headless execution cannot answer interactive permission prompts.

The CLI applies its configured permission rules during execution.

Automatically approve safe actions with:

```bash
--mode auto
```

Use `--dangerously-skip-permissions` only when the user explicitly asks for it. It auto-approves every tool permission request without prompting:

```bash
--dangerously-skip-permissions
```

From 0tomi/skills, MIT.

Signals

Stars
3
Forks
0
Open issues
0
Last commit (this folder)
Oct 20, 2026 (11 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from 0tomi

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get gemini-cli running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying gemini-cli?

CallGet help
Cite this page

gemini-cli skill. Agent Mart. https://agentmart.dev/skills/0tomi-gemini-cli (last updated 2026-10-24)