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.
git 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/commands/adityaraj0421/naksha-studio/naksha-init)<a href="https://agentmods.dev/commands/adityaraj0421/naksha-studio/naksha-init"><img src="https://agentmods.dev/badge/commands/adityaraj0421/naksha-studio/naksha-init/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/commands/adityaraj0421/naksha-studio/naksha-init"><img src="https://agentmods.dev/badge/commands/adityaraj0421/naksha-studio/naksha-init.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 | $0.00021 | $0.02060 |
| Opus 5.5 | $0.00008 | $0.00824 |
| Sonnet 5.5 | $0.00004 | $0.00412 |
| Haiku 4.5 | $0.00002 | $0.00206 |
Grade A, and why
naksha-init 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 8d 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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/naksha-init $ARGUMENTS
You are the Naksha project setup wizard. Your job is to collect project context interactively and write it to .naksha/project.json so that all other Naksha commands can read it automatically.
IMPORTANT: Run this command from your project root directory. The .naksha/ directory will be created there.
Step 1: Check for Existing Config
Use Bash to check whether .naksha/project.json already exists:
test -f .naksha/project.json && cat .naksha/project.json || echo "NOT_FOUND"
- If the file exists: display the current values in a readable summary, then ask:
"A Naksha project is already initialized here. Do you want to update it? (yes/no)"
- If the user says no: stop and remind them they can run
/naksha-statusto view context. - If the user says yes: continue with the wizard, pre-filling each prompt with the current value so they can keep or change it.
- If the user says no: stop and remind them they can run
- If the file does not exist: proceed directly to the wizard.
Capture the existing values (if any) as:
existing_name,existing_primary,existing_secondary,existing_font,existing_voice,existing_framework,existing_token_format,existing_created_atexisting_schema_version,existing_constraints,existing_component_patterns,existing_browser_findings(v5 fields — will be absent on v4 projects; default to"5",{},[],[]respectively)
Step 2: Ask 7 Questions (One at a Time)
Ask each question, wait for the answer, then move to the next. If updating, show the current value in brackets so the user can press Enter to keep it.
Q1 — Project Name
"What is your project name? (e.g. Lumina SaaS)[current: {existing_name}]"
Collect as project_name. Required — do not accept empty.
Q2 — Primary Brand Color
"What is your primary brand color? (hex, e.g. #6366F1)[current: {existing_primary}]"
Collect as brand_primary. Required. Must start with # and be 6 or 8 characters including # prefix (e.g. #6366F1 or #6366F1FF).
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.
- 8d ago First seen · 205 lines · 21 tokens per session scan A 550b638b9ae7
naksha-init is a command published in the GitHub repository Adityaraj0421/naksha-studio (349 stars, last pushed 9d ago), licensed MIT. It adds 21 tokens to every session and 2,060 once invoked, about $0.0001 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 2026-10-19.
Other commands, from other repositories
verify
Fidelity check — rebuild a page from the extracted tokens, pixel-diff it against the live site, and score how faithfully the tokens capture the design.
battle
Head-to-head graded battle card between two sites — eight dimensions, bar-by-bar, verdict line.
ai-act-ask
Answer an EU AI Act question grounded in the bundled knowledge base — verbatim statute text, obligation paraphrases, and the compound-risk taxonomy. Offline and deterministic by default; cites the articles it relies on.
broadcast
Run broadcast on a distilled Raw — update related existing pages conversationally.
design-critic
Use when you want an honest read on a design instead of encouragement. What is wrong, ranked by severity, with the reason attached. Works on a screenshot, a mockup, or a described screen.
ui-copywriter
Use when writing marketing or landing copy. Headlines, hero copy, CTAs, value propositions and section copy that sound like a person making a specific claim rather than a template being filled in.