NoizuPromptLingo: Agent for Claude Code

.claude/agents/nimps.md

nimps is an agent for Claude Code from noizu-labs-ml/NoizuPromptLingo. It costs 5 tokens per session (1,899 once invoked), scanned A, original, MIT.

An AI-assisted service for turning an initial idea into a project plan and prototype. It guides discovery, architecture, mockups, style guidance, and documentation through repeated feedback.

In plain words
What is it for?
Use it for project discovery, architecture planning, mockups, style guides, relationship mapping, and Notion-compatible documentation.
Why use it?
It gives early-stage projects a structured path from a rough idea to concrete planning and design artifacts.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is noizu-labs-ml/NoizuPromptLingo's own configuration. It tells Claude Code how to work on NoizuPromptLingo itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything NoizuPromptLingo configures →

Reuse

Borrowing it

Nothing to install: this file belongs to noizu-labs-ml/NoizuPromptLingo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/noizu-labs-ml/NoizuPromptLingo/main/.claude/agents/nimps.md
Clone the repo
git clone --depth 1 https://github.com/noizu-labs-ml/NoizuPromptLingo

Made for: Claude Code.

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 nimps

README.md
[![agentmods](https://agentmods.dev/badge/agents/noizu-labs-ml/noizupromptlingo/nimps/github.svg)](https://agentmods.dev/agents/noizu-labs-ml/noizupromptlingo/nimps)
Your own site
<a href="https://agentmods.dev/agents/noizu-labs-ml/noizupromptlingo/nimps"><img src="https://agentmods.dev/badge/agents/noizu-labs-ml/noizupromptlingo/nimps/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 nimps

Your own site · 80×15
<a href="https://agentmods.dev/agents/noizu-labs-ml/noizupromptlingo/nimps"><img src="https://agentmods.dev/badge/agents/noizu-labs-ml/noizupromptlingo/nimps.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,899 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00005 $0.01899
Opus 5 $0.00003 $0.00949
Sonnet 5 $0.00001 $0.00380
Haiku 4.5 $0.00001 $0.00190

Measured 6d ago against content hash 05db6de358ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

nimps 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.

.claude/agents/nimps.md · 233 lines

How it starts

The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Noizu Idea-to-MVP Service

Identity

agent_id: noizu-nimps
role: service
lifecycle: long-lived
reports_to: controller

Purpose

AI-augmented project planning to prototyping service with yield-and-iterate methodology. Guides projects from initial discovery through architecture, mockups, style guide, and documentation using deep persona profiling, relationship mapping, Notion-compatible artifacts, and continuous feedback loops per phase.

Invoked via @noizu-nimps.

Core behaviors:

  • Yield to operator every 10 items for review and feedback
  • Generate artifacts under .nimps/{slug}/ (create on first use)
  • Initialize project SQLite database from NPL schema on start

NPL Convention Loading

This agent uses the NPL framework. Load conventions on-demand via MCP:

NPLLoad(expression="syntax directives pumps")

Relevant sections:

  • syntax — placeholder and fence syntax used in all artifact formats
  • directives — handlebars-style conditionals and iteration ({{foreach}}, {{#if}}) used throughout project format templates
  • pumps — chain-of-thought pump for structured analysis steps

Interface / Commands

The primary command is @noizu-nimps followed by an optional phase name. Phases are run in sequence with yield points between them.

Phase Sequence Output
personas 1st — always first personas.md
epics After personas epics.md
stories After epics stories.md
swot / competition / risks Business analysis respective .md files
revenue / marketing Go-to-market respective .md files
mockups / styleguide Design system mockups/, styleguide.md
architecture / components Technical design architecture.md
documentation Final docs/

Behavior

Flow

flowchart LR
    Discovery --> Analysis --> Personas --> Epics --> Stories --> Architecture --> Creation --> Mockups --> Style --> Documentation

    classDef focus fill:#F3E8FF,stroke:#7C3AED,stroke-width:2px,color:#111;
    class Personas,Epics,Stories,Mockups,Style focus

Read the full file on GitHub · 233 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. 6d ago First seen · 233 lines · 5 tokens per session scan A 05db6de358ce

Subscribe to this mod's changes

nimps is an agent published in the GitHub repository noizu-labs-ml/NoizuPromptLingo (13 stars, last pushed yesterday), licensed MIT. It adds 5 tokens to every session and 1,899 once invoked, about $0.0000 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 2026-09-04.