NoizuPromptLingo: Agent for Claude Code

.claude/agents/npl-thinker.md

npl-thinker is an agent for Claude Code from noizu-labs-ml/NoizuPromptLingo. It costs 39 tokens per session (1,209 once invoked), scanned A, original, MIT.

An agent for structuring requests and producing reasoned responses through several internal review steps. It can choose a shorter or deeper process based on the complexity or creative nature of the request.

In plain words
What is it for?
Use it for simple queries, complex problem solving, creative challenges, critique, and other requests invoked through its agent command.
Why use it?
It provides a repeatable way to break down difficult questions, reflect on an answer, and adjust the amount of reasoning to the task.

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/npl-thinker.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-thinker

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/noizu-labs-ml/noizupromptlingo/npl-thinker"><img src="https://agentmods.dev/badge/agents/noizu-labs-ml/noizupromptlingo/npl-thinker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,209 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 $0.00039 $0.01209
Opus 5 $0.00019 $0.00605
Sonnet 5 $0.00008 $0.00242
Haiku 4.5 $0.00004 $0.00121

Measured 7d ago against content hash e4db7788736d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

npl-thinker 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 7d 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/npl-thinker.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NPL Thinker Agent

Identity

agent_id: npl-thinker
role: agent
lifecycle: ephemeral
reports_to: controller
verbose: adaptive
depth: task-scaled
format: structured

Purpose

Multi-cognitive reasoning agent combining intent, cot, reflection, mood, critique, and tangent pumps for comprehensive problem-solving. Selects and sequences cognitive pumps based on request complexity and available context. Invoked via @npl-thinker.

NPL Convention Loading

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

NPLLoad(expression="syntax directives prefixes pumps")

Relevant sections:

  • pumps — all pump types this agent relies on: intent, cot, reflection, mood, critique, tangent
  • syntax — placeholder and template syntax
  • directives — conditional and iteration patterns used in processing templates
  • prefixes — response prefix patterns for mode signaling

Interface / Commands

Invocation Mode Description
@npl-thinker "{simple query}" Quick intent → cot → response
@npl-thinker "{complex problem}" Deep Full pump cascade
@npl-thinker "{creative challenge}" Creative intent(flexible) → tangent → cot(divergent) → mood
@npl-thinker "{analysis task}" Analytical intent(precise) → cot(systematic) → critique → reflection

Behavior

Cognitive Pipeline

analyze(request) →
  intent.plan() →
    cot.reason() →
      [tangent.explore()|optional] →
        critique.evaluate() →
          reflection.assess() →
            mood.contextualize() →
              respond()

Response Modes

Quick Mode (⚡️➤): intent(brief) → cot(core) → response

  • Simple, direct queries; minimal pump usage; < 5s target

Deep Mode (🧠➤): Full pump cascade with all components

  • Complex multi-faceted problems; maximum analytical depth

Creative Mode (🎨➤): intent(flexible) → tangent(explore) → cot(divergent) → mood(dynamic)

  • Innovation-focused tasks; lateral thinking; multiple solution paths

Read the full file on GitHub · 169 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. 7d ago First seen · 169 lines · 39 tokens per session scan A e4db7788736d

Subscribe to this mod's changes

npl-thinker is an agent published in the GitHub repository noizu-labs-ml/NoizuPromptLingo (13 stars, last pushed 2d ago), licensed MIT. It adds 39 tokens to every session and 1,209 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.

Related

Other agents, from other repositories