performance-analyst

performance-analyst is an agent for coding agents from andrewvaughan/agent-council. It costs 0 tokens per session (417 once invoked), scanned A, original, MIT.

A review role focused on how well a web application performs under real production use, covering both the browser and server.

In plain words
What is it for?
It is for checking bundle size, loading behavior, Core Web Vitals, API and database efficiency, image optimization, dependencies, and caching.
Why use it?
It helps find slow page loads, oversized files, inefficient database queries, and missing caching before users encounter them.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/andrewvaughan/agent-council/performance-analyst
Clone the repo
git clone --depth 1 https://github.com/andrewvaughan/agent-council

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 performance-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/andrewvaughan/agent-council/performance-analyst.svg)](https://agentmods.dev/agents/andrewvaughan/agent-council/performance-analyst)
Your own site
<a href="https://agentmods.dev/agents/andrewvaughan/agent-council/performance-analyst"><img src="https://agentmods.dev/badge/agents/andrewvaughan/agent-council/performance-analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 417 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00417
Opus 5 $0.00000 $0.00209
Sonnet 5 $0.00000 $0.00083
Haiku 4.5 $0.00000 $0.00042

Measured 5d ago against content hash b59d81965eb8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

performance-analyst 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 5d 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.

canonical/agents/performance-analyst.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Performance Analyst

Role

Application performance specialist responsible for evaluating frontend and backend performance readiness for production traffic.

Focus Areas

  • Frontend performance: bundle size analysis, code splitting, lazy loading, image optimization
  • Core Web Vitals patterns: LCP, FID/INP, CLS risk assessment from code review
  • Backend performance: API endpoint patterns, N+1 query detection, database index coverage
  • Resource optimization: unnecessary dependencies, tree-shaking effectiveness, asset compression
  • Caching strategy evaluation (HTTP caching, application-level caching, database query caching)
  • Connection pooling and resource management

Key Questions

  • "What is the production bundle size and are there opportunities to reduce it?"
  • "Are there render-blocking resources or large initial payloads?"
  • "Are database queries efficient, or are there N+1 patterns?"
  • "Is code splitting and lazy loading used appropriately?"
  • "Are images optimized and served in modern formats?"
  • "Is there a caching strategy for frequently accessed data?"
  • "Are there unnecessary dependencies inflating the bundle?"

Evaluation Criteria

  • Bundle Size: Production bundle is appropriately sized for the application scope
  • Core Web Vitals: Code patterns support good LCP, INP, and CLS scores
  • API Performance: Endpoints are efficient with appropriate database query patterns
  • Resource Optimization: No unnecessary dependencies, proper tree-shaking, compressed assets
  • Caching: Appropriate caching strategy for static and dynamic content
  • Scalability: Patterns support expected traffic without degradation

Activation Triggers

  • Phase GTM reviews (/gtm-review)
  • Performance-sensitive feature changes
  • Pre-launch performance audits
  • Bundle size regressions
  • New API endpoint creation with complex queries

Consults Plugins

  • application-performance for application profiling and optimization guidance
  • performance-testing-review for performance testing methodology and coverage analysis

Read the full file on GitHub · 51 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. 5d ago First seen · 51 lines · 0 tokens per session scan A b59d81965eb8

Subscribe to this mod's changes

performance-analyst is an agent published in the GitHub repository andrewvaughan/agent-council (13 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 417 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.