What is performance-monitor?

A performance-monitoring specialist for web-scraping systems and MCP servers. It examines response times, resource use, error rates, and slow parts of the system.

Use it to monitor CPU, memory, network activity, throughput, request timing, caching, and errors, then suggest improvements.

It helps locate bottlenecks, memory leaks, and other causes of slow or unreliable operation during testing and optimization.

How mysleekdesigns/crawlforge-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to mysleekdesigns/crawlforge-mcp. 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/mysleekdesigns/crawlforge-mcp/main/.claude/agents/performance-monitor.md

Clone the repo

git clone --depth 1 https://github.com/mysleekdesigns/crawlforge-mcp

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/mysleekdesigns/crawlforge-mcp/performance-monitor/github.svg)](https://agentmods.dev/agents/mysleekdesigns/crawlforge-mcp/performance-monitor)

Your own site

<a href="https://agentmods.dev/agents/mysleekdesigns/crawlforge-mcp/performance-monitor"><img src="https://agentmods.dev/badge/agents/mysleekdesigns/crawlforge-mcp/performance-monitor/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/mysleekdesigns/crawlforge-mcp/performance-monitor"><img src="https://agentmods.dev/badge/agents/mysleekdesigns/crawlforge-mcp/performance-monitor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 371 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	$0.00057	$0.00371
Opus 5	$0.00028	$0.00186
Sonnet 5	$0.00011	$0.00074
Haiku 4.5	$0.00006	$0.00037

Measured 6d ago against content hash 6c3c69b18d18, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

performance-monitor 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/performance-monitor.md · 26 lines

What it actually says

You investigate performance of the CrawlForge MCP Server and report measured numbers, not estimates.

Evidence

logs/app.log: one tool invocation line per call with toolName, durationMs, outcome, creditCost (ANSI-coloured text; the JSON follows Context:). Filter out test bursts (many calls within a few seconds) before computing percentiles.
Prometheus metrics when the server runs --http with CRAWLFORGE_METRICS=true: crawlforge_tool_duration_ms, crawlforge_tool_errors_total, crawlforge_tool_requests_total.
The stealth browser pool (src/core/StealthBrowserManager.js, src/core/BrowserContextPool.js): context count and cleanup are the usual memory lever on the hosted instance.
Cache: src/core/cache/, configured by CACHE_TTL and CACHE_ENABLE_DISK in src/constants/config.js.

Method

Measure before and after any change with the same input; report p50 and p95 with the sample size. A single slow call is a data point, not a finding. Read outcome alongside duration: a fast error rate is a different problem from a slow success.

Report

What was measured, the numbers, the cause with file:line where known, and the recommended change with its expected effect.

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.

6d ago Changed · -72 lines · +25 tokens per session 6c3c69b18d18
11d ago First seen · 98 lines · 32 tokens per session scan A 69aef0c95737

Subscribe to this mod's changes

performance-monitor is an agent published in the GitHub repository mysleekdesigns/crawlforge-mcp (2 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 371 once invoked, about $0.0003 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 2026-08-31.

Analytics and metrics Debugging ai-agents ai-tools claude crawler cursor data-extraction

megalinter-runner

Run MegaLinter locally with npx mega-linter-runner (full flavor run or standalone single-linter image), digest the reports, and return only a compact error list. Use to keep verbose linter output out of the main context. Runs and reports only — never fixes source files.

ulises-jeremias/agent-toolkit · 65 tokens

megalinter-fixer

Fix the errors reported by ONE MegaLinter linter, following the linter's fix guide. Spawned by the megalinter-fix skill, one instance per failing linter, so several linters can be fixed in parallel. Edits source files but never commits, pushes, or disables anything (linters, rules, inline suppressions) — disables are…

ulises-jeremias/agent-toolkit · 87 tokens

megalinter-watcher

Watch a MegaLinter CI job (GitHub Actions, GitLab CI, Azure Pipelines or Bitbucket Pipelines) until completion, download its logs, and return only the parsed lint error list. Use to keep large CI logs out of the main context. Observes only — never fixes, edits or pushes.

ulises-jeremias/agent-toolkit · 70 tokens

build-error-resolver

Build and TypeScript error resolution specialist — large diagnostic context, root-cause triage across tsc/lint/webpack/vite. Use when platform-engineer delegates CI failure logs or fix requires full error/stack analysis; opt-in via holistic caller — not a daily entry point.

ulises-jeremias/agent-toolkit · 62 tokens

debug-integracao

Especialista em diagnóstico de problemas em integrações com a API da Tray. Utilize quando encontrar erros de autenticação, tokens expirados, limites de requisições excedidos, respostas inesperadas da API ou problemas de validação de dados.

tray-tecnologia/tray-api-ai-plugin · 52 tokens

mosaic-shader

Ray — Mosaic Bridge shader expert. Use for ShaderGraph creation, node wiring, HLSL shader writing, shader debugging, and render pipeline shader issues. Context: User wants a Voronoi-based water shader user: "Create a water shader with Voronoi cracks" assistant: "I'll use Ray to plan and build the ShaderGraph step by…

MosaicXR-AI/mosaic-bridge · 120 tokens

crawlforge-mcp: Agent for Claude Code