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.
npx skills add nxtg-ai/forge-plugin --skill gemini-frameworkgit clone --depth 1 https://github.com/nxtg-ai/forge-pluginWrote 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.
[](https://agentmods.dev/skills/nxtg-ai/forge-plugin/gemini-framework)<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.
<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>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 | $0.00098 | $0.01802 |
| Opus 5.5 | $0.00039 | $0.00721 |
| Sonnet 5.5 | $0.00020 | $0.00360 |
| Haiku 4.5 | $0.00010 | $0.00180 |
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`: 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:
~/.gemini/GEMINI.md— global user instructions- Current directory and each parent up to the
.gitroot — project instructions - 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 anyGEMINI.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.fileNameaccepts a single string OR an array of strings.general.defaultApprovalModevalues:"default"(prompt),"auto_edit"(auto-approve edits),"plan"(read-only). This is the tool-approval gate — it lives undergeneral, nottools(see Gotchas).
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.
- 1mo ago First seen · 112 lines · 98 tokens per session scan B 73bc55d85a8f
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.
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.
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.
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…
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.
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…
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…