gemini-cli

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 adbertram/cli-tools --skill gemini-cli

Clone the repo

git clone --depth 1 https://github.com/adbertram/cli-tools

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/adbertram/cli-tools/gemini-cli/github.svg)](https://agentmods.dev/skills/adbertram/cli-tools/gemini-cli)

Your own site

<a href="https://agentmods.dev/skills/adbertram/cli-tools/gemini-cli"><img src="https://agentmods.dev/badge/skills/adbertram/cli-tools/gemini-cli/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/adbertram/cli-tools/gemini-cli"><img src="https://agentmods.dev/badge/skills/adbertram/cli-tools/gemini-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 138 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,474 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.

Model	Per session	Once invoked
Fable 5.1	$0.00138	$0.01474
Opus 5.5	$0.00055	$0.00590
Sonnet 5.5	$0.00028	$0.00295
Haiku 4.5	$0.00014	$0.00147

Measured today against content hash 6e1c9d233929, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gemini-cli 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 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.

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.

_repo/skills/gemini-cli/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<quick_start> The repo-owned Gemini API CLI follows this pattern:

gemini-api <command-group> <action> [arguments] [options]

Task	Command
Chat with Gemini	`gemini-api chat new "Your prompt here"`
Chat with file attachment	`gemini-api chat new "Describe this" --file image.jpg`
Generate an image	`gemini-api image generate "A sunset over mountains" -o sunset.png`
Analyze a video	`gemini-api video analyze video.mp4 --prompt "Summarize this"`
Start deep research	`gemini-api research start "Research topic"`
List models	`gemini-api models list --table`
Show API usage	`gemini-api usage show --table`
Check auth status	`gemini-api auth status`
Add API credits (open billing page)	`gemini-api account topup` (`--no-open` prints URL only)
</quick_start>

<essential_principles> MANDATORY: Consult the adjacent usage.json at <cli-tools-root>/_repo/skills/<tool>-cli/usage.json before executing ANY gemini-api command. This file contains complete command syntax, all arguments, all options, and usage instructions for every command. Never guess at command syntax.

<reference_index> usage.json -- Complete command tree with arguments, options, defaults, and usage instructions for every command. </reference_index>

<success_criteria>

Command executes without error
Output is displayed in requested format
Correct command and flags used (verified against usage.json) </success_criteria>

Deep Research (Interactions API)

gemini-api research start|status|resume drives the Gemini Deep Research Agent through the Google GenAI Interactions API. As of the May 2026 breaking change (legacy schema removed by the API on 2026-06-08), this requires:

google-genai >= 2.0.0 (the gemini CLI pins >=2.0.0 in gemini/pyproject.toml). SDK 1.x sends the legacy Interactions schema and the API rejects it with HTTP 400: "The legacy Interactions API schema is no longer supported … adopt the new 'steps' schema." If research fails with that 400, the SDK is too old — reinstall with the cli-tool install script so uv resolves google-genai >= 2.0.0.
The new "steps" schema: a completed Interaction exposes steps (not the legacy outputs) and the convenience property output_text. The CLI reads interaction.output_text for the final report. Streamed events use event_type values interaction.created, step.start, step.delta, step.stop, interaction.status_update, interaction.completed, error (replacing legacy interaction.start / content.delta / interaction.complete). step.delta deltas are typed by delta.type (text → delta.text, thought_summary → delta.content.text).
Deep Research is background-only and paid-tier-only; a single task can run 5-20+ minutes. gemini-api research start defaults to --stream; callers that capture stdout (e.g. the ClientContentWriter research_article.js) use --no-stream, which prints the synthesized report to stdout and exits 0.
Valid --agent values (SDK Literal): deep-research-pro-preview-12-2025 (default), deep-research-preview-04-2026, deep-research-max-preview-04-2026.

Read the full file on GitHub · 109 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

usage.json 36 KB

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 First seen · 109 lines · 138 tokens per session scan A 6e1c9d233929

Subscribe to this mod's changes

gemini-cli is a skill published in the GitHub repository adbertram/cli-tools (6 stars, last pushed today), licensed MIT. It adds 138 tokens to every session and 1,474 once invoked, about $0.0006 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 2026-11-07.

Backend and APIs Debugging Python Testing api-client automation browser-automation cli developer-tools

gemini-cli next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
gemini-cliadbertram/cli-tools	Skill	6	today	MIT	A	138	Claude Code, Codex
x402browser-use/browser-use	Skill	120k	yesterday	MIT	A	175	Claude Code
mem0-statusmem0ai/mem0	Skill	68k	2d ago	Apache-2.0	A	44	Claude Code, Codex
cloudbrowser-use/browser-use	Skill	120k	yesterday	MIT	A	177	Claude Code
opencli-autofixjackwener/OpenCLI	Skill	31k	yesterday	Apache-2.0	A	61	Claude Code
open-sourcebrowser-use/browser-use	Skill	120k	yesterday	MIT	A	137	Claude Code
eveComposioHQ/composio	Skill	31k	yesterday	MIT	A	47	Claude Code, Codex