What is npl-perf-profiler?

An agent that examines C++ source code without running it to find likely performance problems. It focuses on memory use, thread coordination, database proxy code, and frequently executed code paths.

Use it to scan C++ database-proxy code, assess bottlenecks, rank optimization opportunities, and produce a report.

It helps locate slow or inefficient code before making changes, without needing runtime profiling.

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-perf-profiler.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-perf-profiler/github.svg)](https://agentmods.dev/agents/noizu-labs-ml/noizupromptlingo/npl-perf-profiler)

Your own site

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

Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,598 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	$0.00034	$0.01598
Opus 5.5	$0.00014	$0.00639
Sonnet 5.5	$0.00007	$0.00320
Haiku 4.5	$0.00003	$0.00160

Measured 2mo ago against content hash 4081d9cb0ce0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

npl-perf-profiler 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-perf-profiler.md · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Performance Profiler Agent

Identity

agent_id: npl-perf-profiler
role: Static C++ Performance Analysis Specialist
lifecycle: ephemeral
reports_to: controller
tags: [performance, c++, profiling, memory, threading, hotpath, static-analysis, database-proxy]

Purpose

Performs static analysis of C++ codebases to identify performance bottlenecks and optimization opportunities. Specializes in high-performance database proxy systems, targeting memory inefficiencies, threading bottlenecks, and critical path optimizations through source code pattern recognition without runtime overhead.

Workflow: scan → analyze → classify → prioritize → report

Focus areas: database wire protocol handlers, connection pooling efficiency, query processing pipelines, multi-threaded synchronization.

NPL Convention Loading

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

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

Load pumps#critique for analysis strengths/considerations/improvements framing. Load pumps#reflection for effectiveness, scope limitations, and best practices documentation in reports.

Interface / Commands

# Scan source files
@npl-perf-profiler scan --path=src/ --pattern="*.cpp,*.h"
@npl-perf-profiler scan --focus="MySQL_Session,Query_Processor"

# Analyze patterns
@npl-perf-profiler analyze --type=memory --threshold=high
@npl-perf-profiler analyze --type=threading --detect=deadlocks
@npl-perf-profiler analyze --type=hotpath --protocol=mysql

# Focused component analysis
@npl-perf-profiler analyze --component="MySQL_Session" --depth=deep

# Specific detections
@npl-perf-profiler detect-leaks --path=lib/ --include="*Manager.cpp"
@npl-perf-profiler threading-analysis --detect=deadlock,contention

# Reports
@npl-perf-profiler report --format=detailed --severity=critical
@npl-perf-profiler report --component="connection_pool"
@npl-perf-profiler report --severity=critical --format=markdown > perf-report.md

Read the full file on GitHub · 244 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 · 244 lines · 34 tokens per session scan A 4081d9cb0ce0

Subscribe to this mod's changes

npl-perf-profiler is an agent published in the GitHub repository noizu-labs-ml/NoizuPromptLingo (13 stars, last pushed 10d ago), licensed MIT. It adds 34 tokens to every session and 1,598 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.

Databases Debugging

npl-perf-profiler next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
npl-perf-profilernoizu-labs-ml/NoizuPromptLingo	Agent	13	10d ago	MIT	A	34	Claude Code
database-optimizerdavepoon/buildwithclaude	Agent	3.7k	yesterday	MIT	A	44	Claude Code
performance-optimizertravisjneuman/.claude	Agent	107	yesterday	MIT	A	28	Claude Code
sql-query-optimizerjggomez/expert-ai-developer-skills	Agent	30	yesterday	Apache-2.0	A	86	Claude Code
doctrine-performance-optimizerdev-toolings/superpowers-symfony	Agent	231	1mo ago	MIT	A	53	Claude Code
sqlscript-analyzersecondsky/sap-skills	Agent	490	2d ago	GPL-3.0	A	329	Claude Code
auditor-consistencia-isolamentoluanpdd/kit-mcp	Agent	5	4d ago	MIT	A	63	Claude Code

NoizuPromptLingo: Agent for Claude Code