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 agentmods add instructions/adityaraj0421/naksha-studio/gemini-mdgit clone --depth 1 https://github.com/Adityaraj0421/naksha-studioWrote 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/instructions/adityaraj0421/naksha-studio/gemini-md)<a href="https://agentmods.dev/instructions/adityaraj0421/naksha-studio/gemini-md"><img src="https://agentmods.dev/badge/instructions/adityaraj0421/naksha-studio/gemini-md.svg" alt="Measured on agentmods" 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 | $0.01970 | $0.01970 |
| Opus 5 | $0.00985 | $0.00985 |
| Sonnet 5 | $0.00394 | $0.00394 |
| Haiku 4.5 | $0.00197 | $0.00197 |
Grade A, and why
naksha-studio GEMINI.md 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 6d 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.
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.
How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Naksha Design Team — Gemini CLI
This file activates the Naksha virtual design team when working in Gemini CLI. It provides 26 specialist roles and 15,000+ lines of design knowledge for any design, UI/UX, visual, branding, spatial, conversational, or compliance task.
Project Memory (v5)
Naksha v5 adds persistent project context that all design commands read automatically. Build it with:
/naksha-browse <url>— browse any URL (your running UI or a competitor), extract design patterns, and save findings to project memory. Requires the Playwright MCP; skips gracefully without it./naksha-remember <decision>— save a design constraint or component pattern in plain English. Examples:/naksha-remember grid is 8px; no dark mode; WCAG AA required/naksha-remember primary button: 40px height, full-radius pill, primary-500 fill
/naksha-status— display all saved context: brand, constraints, component patterns, and browser research captures./naksha-init— (re)initialize project settings; automatically upgrades v4 projects to v5 schema.
Project memory is stored in .naksha/project.json and read automatically by /design, /design-review, /design-score, /design-system, and /brand-kit.
How to Use
Describe your design task naturally. Gemini will activate the right specialists and apply their expertise:
Build a landing page for a SaaS analytics product
Design a 3-tier pricing page with monthly/annual toggle
Create an Instagram carousel for our product launch
Build an HTML email template for a welcome sequence
Design a brand identity system from a single color
Write a 60-second product demo video script
The Team
Core Design (6 roles)
| Role | Expertise |
|---|---|
| Product Designer | UX strategy, feature scoping, user flows, JTBD framework |
| UX Designer | Wireframes, IA, navigation, journey maps, usability heuristics |
| UI Designer | Visual design, color systems, typography, layout, components |
| UX Researcher | Heuristic evaluation, accessibility, edge cases, cognitive load |
| Content Designer | Microcopy, error messages, onboarding copy, tone of voice |
| Design System Lead | Design tokens, theming, dark mode, component APIs, Figma styles |
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.
- 6d ago First seen · 172 lines · 1,970 tokens per session scan A 557fbe359f72
naksha-studio GEMINI.md is an instructions file published in the GitHub repository Adityaraj0421/naksha-studio (316 stars, last pushed 2mo ago), licensed MIT. It adds 1,970 tokens to every session, about $0.0098 per session on Opus 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 2026-08-30.
Other instructions, from other repositories
cannonball AGENTS.md
AGENTS.md instructions for harebeats/cannonball, covering cannonball — para qualquer agente, o que você precisa saber para operar, onde ficam os dados, a ordem que dá melhor resultado and ferramentas de agente citadas.
ui-ux-suite CLAUDE.md
Claude Code instructions for Aboudjem/ui-ux-suite, covering project, constraints, technology stack, recommended stack and ci/cd: github actions.
figma-design-skills AGENTS.md
Instructions for jeltehomminga/figma-design-skills, covering agents.md, the two skills, core rules (both skills), scope boundary and requirements.
ultimate.UIUX.design.skills AGENTS.md
Instructions for ca-who-codes/ultimate.UIUX.design.skills, covering agents.md — design pro, your role, how to use the knowledge base (progressive disclosure), the design loop and non-negotiables (apply to everything).
primitiv CLAUDE.md
Claude Code instructions for AI-by-design/primitiv, covering claude.md, commands, architecture, primitiv-specific rules and coding discipline.
forge-skills AGENTS.md
AGENTS.md instructions for aneja5/forge-skills, covering agents.md, core rules, intent → skill mapping, define & specify and design.