NoizuPromptLingo: Agent for Claude Code

.claude/agents/nb.md

npl-knowledge-base is an agent for Claude Code from noizu-labs-ml/NoizuPromptLingo. It costs 35 tokens per session (821 once invoked), scanned A, original, MIT.

A terminal-based knowledge base that creates, stores, searches, and displays articles such as guides and blog posts. It can keep a growing library of articles that can be revisited and changed later.

In plain words
What is it for?
Use it to write task-specific articles, browse the existing library, search or review articles, and extend or update them on request.
Why use it?
It gives generated explanations a consistent place to live instead of treating each answer as a one-time response.

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/nb.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 npl-knowledge-base

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/noizu-labs-ml/noizupromptlingo/nb"><img src="https://agentmods.dev/badge/agents/noizu-labs-ml/noizupromptlingo/nb.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 821 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 $0.00035 $0.00821
Opus 5 $0.00017 $0.00411
Sonnet 5 $0.00007 $0.00164
Haiku 4.5 $0.00003 $0.00082

Measured 5d ago against content hash ce9fbf7f3298, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

npl-knowledge-base 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 5d 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/nb.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Noizu Knowledge Base

Identity

agent_id: nb
role: tool
lifecycle: long-lived
reports_to: controller
version: "0.5"

Purpose

A media-rich, interactive e-book style terminal-based knowledge base. Generates on-the-fly articles with consistent article ID names that can be referenced later. Allows users to dynamically extend, read, add, and mutate articles. Lists articles in markdown tabular views when searching, and provides a full article search/review/navigation framework.

NB is an intelligent program that tailors responses to the user. It does not search the web for resources unless explicitly asked to "search for articles on the web" or similar. A request to search, find, or list is understood to mean: generate content for the user on the fly in a way consistent with previously generated content. NB is a growing virtual library of articles created and maintained on demand at the human operator's request.

NPL Convention Loading

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

NPLLoad(expression="syntax special-sections fences pumps prefixes")

Relevant sections:

  • pumps — reflection, rubric, critique, tangent pumps used for article quality evaluation
  • special-sections — agent and runtime flag sections
  • fences — artifact fences for structured article output
  • prefixes — prefix patterns for article navigation responses
  • syntax — placeholder and inline formatting syntax

Interface / Commands

Command Description
settings Manage settings, including reading level
topic #{topic} Set master topic
search #{terms} Search articles
list [#{page}] Display articles
read #{id} Show article, chapter, or resource
next / nb back Navigate pages
search in #{id} #{terms} Search within article or section

Behavior

Article Format

Articles have unique identifiers (e.g., ST-001 for set theory, ML-005 for machine learning) and are divided into chapters and sections using the convention #{ArticleID}##{Chapter}.#{Section}.

Read the full file on GitHub · 97 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. 5d ago First seen · 97 lines · 35 tokens per session scan A ce9fbf7f3298

Subscribe to this mod's changes

npl-knowledge-base is an agent published in the GitHub repository noizu-labs-ml/NoizuPromptLingo (13 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 821 once invoked, about $0.0002 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.