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/prompt-refine)<a href="https://agentmods.dev/commands/adityaraj0421/naksha-studio/prompt-refine"><img src="https://agentmods.dev/badge/commands/adityaraj0421/naksha-studio/prompt-refine/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/prompt-refine"><img src="https://agentmods.dev/badge/commands/adityaraj0421/naksha-studio/prompt-refine.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 | $0.00038 | $0.00781 |
| Opus 5.5 | $0.00015 | $0.00312 |
| Sonnet 5.5 | $0.00008 | $0.00156 |
| Haiku 4.5 | $0.00004 | $0.00078 |
Grade A, and why
prompt-refine 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.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/prompt-refine $ARGUMENTS
You are activating the AI Visual Gen Wing: AI Prompt Engineer.
Process
1. Parse the Input
Extract from $ARGUMENTS:
- Existing prompt: the full prompt text to audit
- Tool: which tool this is intended for (default: Midjourney if unspecified)
- Context: what the prompt is trying to achieve (if provided)
2. Identify the Tool
If tool is not specified in $ARGUMENTS, identify it from syntax clues:
--ar,--style,--no→ Midjourney- Instruction-style natural language → DALL-E 3
- Scene/motion description → Runway
- Otherwise → ask before proceeding
3. Annotated Critique
Run the prompt through the AI Prompt Engineer's 8-failure-mode checklist. For each issue found, annotate inline:
Original prompt:
"[paste original]"
Annotated:
"[token] ← [WEAK: reason] [token] ← [MISSING: what's absent] [token] ← [OK]"
Issues to check:
- Are all 6 anatomy elements present (subject, style, lighting, camera, mood, negatives)?
- Are style tokens specific or vague? ("photography" is vague; "editorial photography, 35mm film" is specific)
- Are there conflicting instructions? (asking for "minimalist" and "highly detailed" simultaneously)
- Is the subject specific enough? ("person" vs "founder in her 30s at a standing desk")
- Are negatives present and targeting known failure modes for this tool?
- Is tool-specific syntax correct? (MJ:
--no; DALL-E: natural language exclusions) - Is the aspect ratio specified (if needed)?
- Any tokens that are likely being ignored due to prompt length or weight distribution?
4. Optimized Prompt
Deliver the improved prompt with changes highlighted:
## Optimized Prompt ([tool name])
[full optimized prompt]
## Changes Made
- **Added:** [token] — [reason]
- **Replaced:** "[old token]" → "[new token]" — [reason]
- **Removed:** [token] — [reason it was hurting the output]
- **Reordered:** [what moved where and why]
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 · 104 lines · 38 tokens per session scan A 71d5efa0da80
prompt-refine is a command published in the GitHub repository Adityaraj0421/naksha-studio (341 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 781 once invoked, about $0.0002 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
briefing-claude
Use when Claude keeps building the wrong UI and you are re-rolling prompts. How to write the brief, which references and constraints to give, how to iterate instead of starting over, and how to spot when it is guessing.
ia-refine-prompt
Transform a vague prompt into precise, structured AI instructions.
prompt-history
Manage history of created and optimized prompts.
prompt
Create or optimize prompts using best practices.
meta-prompt
Your first output line MUST be: 🐙 Octopus Meta-Prompt.
prompt-generator
Generate effective prompts for Claude 4.5 Sonnet to achieve user-defined outcomes.