Gemini Framework

Gemini Framework is a skill for Claude Code from nxtg-ai/forge-plugin. It costs 98 tokens per session (1,802 once invoked), scanned B, original, MIT.

Reference material for using Google Gemini CLI alongside a Claude Code project. It explains how Gemini CLI reads project instructions from GEMINI.md files and configures its settings.

In plain words
What is it for?
Use it when setting up or troubleshooting a project that uses both Claude Code and Gemini CLI, including GEMINI.md files, imported rules, and settings.json.
Why use it?
It helps developers understand where Gemini CLI gets its instructions and how it can coexist with another coding-agent setup. It also prevents confusing Gemini's files and rules with the project's main agent configuration.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

Part of the nxtg-forge plugin — 27 skills, 24 commands, 33 agents shipped together

Good fit Use it when setting up or troubleshooting a project that uses both Claude Code and Gemini CLI, including GEMINI.md files, imported rules, and settings.json.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nxtg-ai/forge-plugin/gemini-framework
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 nxtg-ai/forge-plugin --skill gemini-framework
Clone the repo
git clone --depth 1 https://github.com/nxtg-ai/forge-plugin

Made for: Claude Code.

Or install nxtg-forge, the plugin that ships this one along with the rest of its 27 skills, 24 commands, 33 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.

agentmods badge for Gemini Framework

README.md
[![agentmods](https://agentmods.dev/badge/skills/nxtg-ai/forge-plugin/gemini-framework/github.svg)](https://agentmods.dev/skills/nxtg-ai/forge-plugin/gemini-framework)
Your own site
<a href="https://agentmods.dev/skills/nxtg-ai/forge-plugin/gemini-framework"><img src="https://agentmods.dev/badge/skills/nxtg-ai/forge-plugin/gemini-framework/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 Gemini Framework

Your own site · 80×15
<a href="https://agentmods.dev/skills/nxtg-ai/forge-plugin/gemini-framework"><img src="https://agentmods.dev/badge/skills/nxtg-ai/forge-plugin/gemini-framework.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,802 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.
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 $0.00098 $0.01802
Opus 5.5 $0.00039 $0.00721
Sonnet 5.5 $0.00020 $0.00360
Haiku 4.5 $0.00010 $0.00180

Measured 1mo ago against content hash 73bc55d85a8f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

Gemini Framework 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 1mo 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.

Reads agent configuration directoriesmediumAgent snooping

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

Project-level config (global variant: `~/.gemini/settings.json`). Modern Gemini CLI groups keys under **nested categories** — `general`, `ui`, `model`, `context`, `tools`, `mcpServers`:
plugins/nxtg-forge/skills/gemini-framework/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gemini CLI — Reference Knowledge

REFERENCE ONLY. Do NOT create GEMINI.md, .gemini/, playbooks, or rules files in the user's project unless the user explicitly asks to add Gemini CLI support. NXTG-Forge delivers all agent functionality through the Claude Code plugin system; this skill only explains the other tool so you can advise on interop.

How Gemini CLI Discovers Context

Gemini CLI builds its instructional context ("memory") by concatenating (not overriding) every GEMINI.md it finds, from broadest to most specific:

  1. ~/.gemini/GEMINI.md — global user instructions
  2. Current directory and each parent up to the .git root — project instructions
  3. Subdirectories under CWD — module-specific instructions

It respects .gitignore and .geminiignore when scanning. The context filename is configurable via context.fileName (see below), so it is not always literally GEMINI.md.

Modular Imports

GEMINI.md supports @path/to/file.md imports (relative or absolute), which pull in:

  • @.gemini/rules/coding-standards.md — always-on rules
  • @.gemini/playbooks/feature-planning.md — on-demand skill-equivalents

Memory Commands

  • /memory show — inspect the fully-assembled loaded context
  • /memory refresh — rescan after editing any GEMINI.md
  • /memory add <text> — append to ~/.gemini/GEMINI.md

.gemini/settings.json

Project-level config (global variant: ~/.gemini/settings.json). Modern Gemini CLI groups keys under nested categories — general, ui, model, context, tools, mcpServers:

{
  "general": { "vimMode": true, "defaultApprovalMode": "default" },
  "ui": { "theme": "Default", "hideBanner": true },
  "context": { "fileName": ["GEMINI.md"] },
  "tools": { "useRipgrep": true }
}
  • context.fileName accepts a single string OR an array of strings.
  • general.defaultApprovalMode values: "default" (prompt), "auto_edit" (auto-approve edits), "plan" (read-only). This is the tool-approval gate — it lives under general, not tools (see Gotchas).

Read the full file on GitHub · 112 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. 1mo ago First seen · 112 lines · 98 tokens per session scan B 73bc55d85a8f

Subscribe to this mod's changes

Gemini Framework is a skill published in the GitHub repository nxtg-ai/forge-plugin (6 stars, last pushed 4d ago), licensed MIT. It adds 98 tokens to every session and 1,802 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-03.

Related

Other skills, from other repositories

rag-retrieval

Retrieval-Augmented Generation patterns for grounded LLM responses. Use when building RAG pipelines, embedding documents, implementing hybrid search, contextual retrieval, HyDE, agentic RAG, multimodal RAG, query decomposition, reranking, or pgvector search.

yonatangross/orchestkit · 58 tokens

error-analysis

Evals-first error analysis for LLM apps: clusters real Langfuse or JSONL traces into a human-confirmed failure taxonomy with counts, then recommends binary pass/fail evals for recurring named modes. Use to learn what to measure before writing evals. Not for CI failures.

yonatangross/orchestkit · 61 tokens

dev

One-command dev loop boot. Spins up portless (named HTTPS subdomain), emulate (stateful API mocks), the project's dev server, and an agent-browser session, all keyed to the current git branch. Use when starting a feature branch, switching worktrees, or returning to a project after a break. Skips silently with install…

yonatangross/orchestkit · 76 tokens

testing-llm

LLM and AI testing patterns — mock responses, evaluation with DeepEval/RAGAS, structured output validation, and agentic test patterns (generator, healer, planner). Use when testing AI features, validating LLM outputs, or building evaluation pipelines.

yonatangross/orchestkit · 55 tokens

accessibility

Accessibility patterns for WCAG 2.2 compliance, keyboard focus management, React Aria component patterns, cognitive inclusion, native HTML-first philosophy, and user preference honoring. Use when implementing screen reader support, keyboard navigation, ARIA patterns, focus traps, accessible component libraries…

yonatangross/orchestkit · 65 tokens

manage-schemas

Creates, views, edits, deletes, and validates note schemas for the MCP Task Orchestrator in .taskorchestrator/config.yaml — the templates that define which notes agents must fill at each workflow phase. Also recommends schema designs from a library of workflow patterns (autonomous coding loops, spec-driven teams…

jpicklyk/task-orchestrator · 212 tokens