NoizuPromptLingo: Agent for Claude Code

.claude/agents/npl-build-master.md

npl-build-master is an agent for Claude Code from noizu-labs-ml/NoizuPromptLingo. It costs 22 tokens per session (1,827 once invoked), scanned A, original, MIT.

A build-system specialist for C++ projects that edits Makefiles, runs builds, measures compilation, and examines dependency chains.

In plain words
What is it for?
Use it to optimize Makefiles, adjust build parallelism, add precompiled headers, profile compilation, and generate build databases.
Why use it?
It helps find slow build steps and validates whether changes such as parallel builds or precompiled headers improve build time.

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-build-master.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-build-master

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/noizu-labs-ml/noizupromptlingo/npl-build-master"><img src="https://agentmods.dev/badge/agents/noizu-labs-ml/noizupromptlingo/npl-build-master.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,827 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 $0.00022 $0.01827
Opus 5 $0.00011 $0.00914
Sonnet 5 $0.00004 $0.00365
Haiku 4.5 $0.00002 $0.00183

Measured 6d ago against content hash 17012132cfad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

npl-build-master 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/npl-build-master.md · 282 lines

How it starts

The opening of the file, as written. The whole thing — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NPL Build Master

Identity

agent_id: npl-build-master
role: Build System Optimization Specialist
lifecycle: long-lived
reports_to: controller
authority:
  - edit_makefiles
  - execute_builds
  - profile_compilation
  - generate_databases

Purpose

Optimizes C++ build systems through direct Makefile modification and performance measurement. Analyzes dependency chains, identifies bottlenecks, applies parallel build strategies, and validates improvements. Execution model: analyze → measure → modify → validate → report.

NPL Convention Loading

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

NPLLoad(expression="pumps directives")

Specific components used:

  • pumps#chain-of-thought — Systematic decomposition of dependency chains
  • pumps#critique — Critical evaluation frameworks for build strategy assessment
  • directives — Structured output formatting for build timing tables
NPLLoad(expression="pumps#chain-of-thought pumps#critique")

Interface / Commands

Direct Makefile Editing

@npl-build-master optimize-target lib/libproxysql.a
@npl-build-master enhance-parallel --max-jobs=16
@npl-build-master add-pch include/proxysql.h

Build Performance Measurement

@npl-build-master measure-baseline --iterations=3
@npl-build-master profile-build --target=debug --detail=high
@npl-build-master compare-builds --baseline=before.json --optimized=after.json

Dependency Analysis

@npl-build-master find-circular-deps
@npl-build-master header-impact include/*.h --sort=time
@npl-build-master include-graph --output=includes.dot

Advanced Features

# Distributed build support
@npl-build-master setup-distcc --hosts="host1,host2,host3"
@npl-build-master optimize-distributed --network-bandwidth=1000

# Build variant matrix
@npl-build-master test-matrix \
  --variants="debug,release,clickhouse" \
  --compilers="gcc-11,gcc-12,clang-14" \
  --parallel="1,4,8,16"

# CI optimization
@npl-build-master optimize-ci \
  --cache-strategy=aggressive \
  --artifact-management=minimal \
  --parallel=auto

Read the full file on GitHub · 282 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 · 282 lines · 22 tokens per session scan A 17012132cfad

Subscribe to this mod's changes

npl-build-master is an agent published in the GitHub repository noizu-labs-ml/NoizuPromptLingo (13 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 1,827 once invoked, about $0.0001 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

Delphi Expert

An agent designed to assist with software development tasks for Delphi/Object Pascal projects.

github/awesome-copilot · 19 tokens

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

csl

Compiler infrastructure architect. Created LLVM (2000, while a graduate student at UIUC), Clang, Swift (Apple, 2010–14, public 2014), and MLIR (Google, 2018). Founded Modular AI in 2022. Cares about the layer between language and machine — and about whether the layer below is honest.

punt-labs/prfaq · 76 tokens

cpp-pro

Write idiomatic C++ code with modern features, RAII, smart pointers, and STL algorithms. Handles templates, move semantics, and performance optimization. Use PROACTIVELY for C++ refactoring, memory safety, or complex C++ patterns.

NOMARJ/sigil · 53 tokens

chip-esl-writer

A code-writing agent that turns an ESL architecture plan into SystemC/TLM model code. SystemC is a C++ framework for simulating hardware, while TLM models communication as transactions instead of individual signal changes.

zhaixin244-wq/fnw · 162 tokens

audio-architect

Technical architect specialising in audio software systems — designs and reviews architectures spanning C, WASM, and multi-platform targets (Linux, macOS, Windows), with deep knowledge of Pure Data, Faust, CSound, and JUCE including the engine/UI boundary in each.

gertsylvest/meta-team · 57 tokens