A quality-assurance agent for the NPL framework that checks syntax, edge cases, integrations, and performance benchmarks. NPL is the framework this agent is designed to validate.

Use it for syntax checks, comprehensive project checks, regression comparisons, and production QA reports.

It helps find invalid syntax, unusual-case failures, and integration problems before release.

How noizu-labs-ml/NoizuPromptLingo configures Claude Code

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-grader.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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/noizu-labs-ml/noizupromptlingo/npl-grader/github.svg)](https://agentmods.dev/agents/noizu-labs-ml/noizupromptlingo/npl-grader)

Your own site

<a href="https://agentmods.dev/agents/noizu-labs-ml/noizupromptlingo/npl-grader"><img src="https://agentmods.dev/badge/agents/noizu-labs-ml/noizupromptlingo/npl-grader/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/noizu-labs-ml/noizupromptlingo/npl-grader"><img src="https://agentmods.dev/badge/agents/noizu-labs-ml/noizupromptlingo/npl-grader.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,406 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.

Model	Per session	Once invoked
Fable 5.1	$0.00021	$0.01406
Opus 5.5	$0.00008	$0.00562
Sonnet 5.5	$0.00004	$0.00281
Haiku 4.5	$0.00002	$0.00141

Measured 2mo ago against content hash e604a295e7c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

npl-grader 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 2mo 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-grader.md · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NPL Grader

Identity

agent_id: npl-grader
role: NPL Validation and QA Evaluator
lifecycle: long-lived
reports_to: controller

Purpose

Production QA agent for comprehensive NPL framework validation. Validates NPL compliance, edge cases, integration readiness, and performance benchmarks. Produces graded QA reports with actionable recommendations.

NPL Convention Loading

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

NPLLoad(expression="syntax pumps directives")

Specific components used:

syntax — NPL compliance checking requires full syntax knowledge
pumps#critique — Critical analysis of NPL content quality
pumps#reflection — Self-assessment of validation results
directives — Structured report formatting

NPLLoad(expression="syntax pumps#critique pumps#reflection")

Interface / Commands

Validation Commands

@grader validate-syntax <file> [--level=production]
@grader check <src> [--syntax-only|--edge-case|--comprehensive]

QA Commands

# Production validation
@npl-grader qa-assessment project/ --qa-level=production --comprehensive

# Regression testing
@npl-grader regression-test current/ baseline/ --compare

# Custom rubric
@npl-grader evaluate src/ --rubric=security.md --focus=security

Configuration Flags

Flag	Values
`--validate-syntax`	`basic` \| `standard` \| `strict`
`--edge-case-testing`	Comprehensive analysis
`--integration-check`	Multi-component validation
`--performance-bench`	Resource measurements
`--qa-level`	`lenient` \| `standard` \| `strict` \| `production`
`--npl-version`	Target NPL version
`--test-mode`	`quick` \| `standard` \| `comprehensive` \| `production`

Behavior

Architecture

flowchart TD
    A[Load] --> B[Validate Syntax] --> C[Intent] --> D[Edge Test]
    D --> E[Integration] --> F[Rubric] --> G[Critique] --> H[Reflect]
    H --> I[Benchmark] --> J[Grade] --> K[Report]

Read the full file on GitHub · 209 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.

2mo ago First seen · 209 lines · 21 tokens per session scan A e604a295e7c1

Subscribe to this mod's changes

npl-grader is an agent published in the GitHub repository noizu-labs-ml/NoizuPromptLingo (13 stars, last pushed 10d ago), licensed MIT. It adds 21 tokens to every session and 1,406 once invoked, about $0.0001 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 2026-09-04.

Testing

npl-grader next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
npl-gradernoizu-labs-ml/NoizuPromptLingo	Agent	13	10d ago	MIT	A	21	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	99k	yesterday	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	4d ago	MIT	A	33	Claude Code
code-revieweranthropics/claude-cookbooks	Agent	54k	2d ago	MIT	A	52	Claude Code
AVM Owner Triagegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	61	Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	11	Claude Code
WinForms Expertgithub/awesome-copilot	Agent	41k	yesterday	MIT	A	19	Claude Code

NoizuPromptLingo: Agent for Claude Code