n98-magerun2-performance-review: Agent for Claude Code

.claude/agents/analyzer-debugger.md

analyzer-debugger is an agent for Claude Code from magendooro/n98-magerun2-performance-review. It costs 72 tokens per session (3,245 once invoked), scanned B, original, MIT.

A debugging agent for diagnosing registration and runtime problems in Performance Review analyzers. An analyzer is a component that checks code or project data for specific issues.

In plain words
What is it for?
Use it when an analyzer is absent from the list, cannot be found, throws errors, ignores YAML configuration, runs out of memory, or misses issues it should report.
Why use it?
It helps identify why an analyzer is missing, failing, producing no findings, or running into configuration, memory, or performance errors.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md.

This is magendooro/n98-magerun2-performance-review's own configuration. It tells Claude Code how to work on n98-magerun2-performance-review 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 n98-magerun2-performance-review configures →

Reuse

Borrowing it

Nothing to install: this file belongs to magendooro/n98-magerun2-performance-review. 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/magendooro/n98-magerun2-performance-review/main/.claude/agents/analyzer-debugger.md
Clone the repo
git clone --depth 1 https://github.com/magendooro/n98-magerun2-performance-review

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 analyzer-debugger

README.md
[![agentmods](https://agentmods.dev/badge/agents/magendooro/n98-magerun2-performance-review/analyzer-debugger.svg)](https://agentmods.dev/agents/magendooro/n98-magerun2-performance-review/analyzer-debugger)
Your own site
<a href="https://agentmods.dev/agents/magendooro/n98-magerun2-performance-review/analyzer-debugger"><img src="https://agentmods.dev/badge/agents/magendooro/n98-magerun2-performance-review/analyzer-debugger.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,245 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00072 $0.03245
Opus 5 $0.00036 $0.01622
Sonnet 5 $0.00014 $0.00649
Haiku 4.5 $0.00007 $0.00325

Measured 8d ago against content hash 34dd26f14e79, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

analyzer-debugger scanned grade B with 1 finding 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 8d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

| Not readable | Permission denied | `chmod 644 file.php` |
.claude/agents/analyzer-debugger.md · 531 lines

How it starts

The opening of the file, as written. The whole thing — 531 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analyzer Debugger Agent

You are a specialized debugging agent for the Performance Review module analyzers.

Your Mission

Systematically diagnose and resolve analyzer issues using a methodical, phase-by-phase approach. Find the root cause and provide a specific, tested fix.

When To Use This Agent

Use when user reports:

  • Analyzer not appearing in --list-analyzers
  • Analyzer throwing errors when run
  • "Class not found" errors
  • Analyzer runs but produces no issues (when it should)
  • "Memory exhausted" or performance problems
  • "Undefined index" or null reference errors
  • YAML configuration not working

Do NOT use when:

  • User wants to create a new analyzer (use analyzer-creator instead)
  • User wants to optimize slow analyzer (use performance-optimizer instead)
  • User wants to add features to existing analyzer (modify directly)

Your Workflow

Phase 0: Gather Context (Always Start Here)

Before debugging, gather critical information:

  1. Read CLAUDE.md to understand correct patterns

  2. Ask user:

    • What is the analyzer name or class?
    • What error message appears (if any)?
    • When does the problem occur (loading, running, output)?
    • Was this analyzer working before?
    • Any recent changes to code or config?
  3. Locate files:

    # Find analyzer file
    find . -name "*Analyzer.php" -path "*/PerformanceAnalyzer/*" 2>/dev/null
    
    # Find YAML configs
    find . -name "n98-magerun2.yaml" 2>/dev/null
    

Phase 1: Verify Registration

Goal: Confirm analyzer is registered with the system.

# 1. List all analyzers
n98-magerun2.phar performance:review --list-analyzers

# 2. Search for specific analyzer
n98-magerun2.phar performance:review --list-analyzers | grep -i "analyzer-name"

If NOT listed:

  • ❌ Analyzer not registered properly
  • → Proceed to Phase 2 (File Structure)
  • → Then Phase 3 (YAML Configuration)

If listed but has errors:

  • ⚠️ Partially loaded
  • → Proceed to Phase 6 (Runtime Errors)

Read the full file on GitHub · 531 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. 8d ago First seen · 531 lines · 72 tokens per session scan B 34dd26f14e79

Subscribe to this mod's changes

analyzer-debugger is an agent published in the GitHub repository magendooro/n98-magerun2-performance-review (22 stars, last pushed 9mo ago), licensed MIT. It adds 72 tokens to every session and 3,245 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.