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.
curl -O https://raw.githubusercontent.com/magendooro/n98-magerun2-performance-review/main/.claude/agents/README.mdgit clone --depth 1 https://github.com/magendooro/n98-magerun2-performance-reviewWrote 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.
[](https://agentmods.dev/agents/magendooro/n98-magerun2-performance-review/readme)<a href="https://agentmods.dev/agents/magendooro/n98-magerun2-performance-review/readme"><img src="https://agentmods.dev/badge/agents/magendooro/n98-magerun2-performance-review/readme/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.
<a href="https://agentmods.dev/agents/magendooro/n98-magerun2-performance-review/readme"><img src="https://agentmods.dev/badge/agents/magendooro/n98-magerun2-performance-review/readme.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.02437 |
| Opus 5 | $0.00000 | $0.01218 |
| Sonnet 5 | $0.00000 | $0.00487 |
| Haiku 4.5 | $0.00000 | $0.00244 |
Grade A, and why
README 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 440 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Review Sub-agents
This directory contains 6 specialized Claude Code sub-agents for working with the Performance Review module.
What Are Sub-agents?
Sub-agents are specialized AI assistants that Claude Code can delegate tasks to. Each operates with its own context window and specialized expertise, making them more efficient and focused than using the main Claude instance for everything.
Available Sub-agents
| Sub-agent | Purpose | When Used | File Size |
|---|---|---|---|
| analyzer-creator | Create new custom analyzers | User wants to add performance checks | 16KB |
| analyzer-debugger | Debug analyzer issues | Analyzer not loading or not working | 13KB |
| test-writer | Write PHPUnit tests | Need test coverage for analyzers | 18KB |
| code-reviewer | Review analyzer code quality | Before committing changes | 14KB |
| documentation-updater | Update documentation | After code changes | 10KB |
| performance-optimizer | Optimize slow analyzers | Analyzer has performance issues | 14KB |
Total: 6 agents, ~85KB of specialized expertise
How They Work
Automatic Invocation
Claude Code automatically selects the right sub-agent based on your request:
"Create a custom analyzer to check Redis memory"
→ analyzer-creator agent automatically invoked
"My analyzer isn't showing up in --list-analyzers"
→ analyzer-debugger agent automatically invoked
"Write tests for my analyzer"
→ test-writer agent automatically invoked
Explicit Invocation
You can also explicitly request a specific agent:
"Use the analyzer-creator agent to create a new analyzer"
"Use the code-reviewer agent to review my code"
"Use the performance-optimizer agent to optimize this analyzer"
Sub-agent Details
1. analyzer-creator
Expertise: Creating new custom analyzers from requirements
Workflow:
- Gathers requirements (what to check, thresholds, priority)
- Designs analyzer structure (interfaces, dependencies)
- Implements complete PHP class
- Creates YAML configuration
- Provides testing commands
- Documents usage
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.
- 10d ago First seen · 440 lines · 0 tokens per session scan A 39a82d580364
README is an agent published in the GitHub repository magendooro/n98-magerun2-performance-review (22 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,437 tokens. 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.