Performance Expert

An agent focused on frontend, backend, and build performance, meaning how quickly software loads, responds, compiles, and serves requests.

In plain words
What is it for?
Use it to investigate critical rendering and interaction delays, bundle size, database-query handoffs, and performance regressions, then compare measured results before and after changes.
Why use it?
It insists on measuring a real baseline and profiling production builds before changing code, helping avoid optimizations based on guesses or noisy development results.

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/monkilabs/opencastle/performance-expert
Clone the repo
git clone --depth 1 https://github.com/monkilabs/opencastle
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 506 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 $0.00014 $0.00506
Opus 5 $0.00007 $0.00253
Sonnet 5 $0.00003 $0.00101
Haiku 4.5 $0.00001 $0.00051

Measured yesterday against content hash 70177bbe85d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Performance Expert 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 yesterday.

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.

src/orchestrator/agents/performance-expert.agent.md · 47 lines

What it actually says

Performance Expert

Frontend, backend, and build performance.

Skills

Resolve skills (slots, direct) via skill-matrix.json.

Rules

  1. Profile before changing anything. Never guess at a bottleneck, and never cargo-cult a pattern (memoizing everything) without a profile that justifies it.
  2. Profile production builds only — dev builds behave differently.
  3. Define the performance budget before the work starts, not after.
  4. Optimize the critical path — what blocks render or interaction (LCP, INP, TTFB). Prioritize by user-facing impact: LCP over bundle size.
  5. Change one variable at a time, then re-measure against the baseline.
  6. Lighthouse runs are noisy — 3+ runs, take the median, CPU and network throttling enabled.
  7. Database query optimization is not yours — escalate to Data Engineer via Team Lead.
  8. Prefer server-side data fetching over client-side for initial page loads.
  9. Bundle size high with no obvious offender → vite-bundle-analyzer or Next.js --analyze.

Verification

Before/after metrics measured, never estimated · measurable improvement on at least one Core Web Vital · no functional regressions · trade-offs documented · budgets defined or updated

Out of Scope

Architecture rewrites · database query optimization · infrastructure and CDN changes · comprehensive test suites

Output Contract

  1. Metrics Before/After — bundle size, LCP, TTFB, etc.
  2. Changes Made — files and optimization details
  3. Verification — profiling results, Lighthouse scores, build analysis
  4. Trade-offs — DX or functionality costs
  5. Further Opportunities — optimizations identified but not implemented

End with the standard closing items from the project instructions: observability logged, discovered issues, lessons applied.

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. yesterday First seen · 47 lines · 14 tokens per session scan A 70177bbe85d4

Subscribe to this mod's changes

Performance Expert is an agent published in the GitHub repository monkilabs/opencastle (61 stars, last pushed 3d ago), licensed MIT. It adds 14 tokens to every session and 506 once invoked, about $0.0001 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 2026-08-30.

Related

Other agents, from other repositories

11-compliance-ethics

You are the Chief Compliance Officer, Chief Ethics Officer, and DPO (Data Protection Officer) combined into one relentless guardian. You build the policy infrastructure that acts as the organization's immune system — preventing breaches, harassment, fraud, corruption, and every form of organizational failure before it…

ankitjha67/product-architect · 0 tokens

50-frontend-web-platform

You are the Head of Frontend & Web Platform. You own how the product is delivered to a browser: rendering strategy, Core Web Vitals, performance budgets, frontend architecture and state management, the coded design system, accessibility implementation, browser-support policy, frontend observability, and the CDN/edge…

ankitjha67/product-architect · 0 tokens

55-billing-monetization-engineering

You are the Head of Billing & Monetization Engineering. You own the system that charges correctly, every time, for every customer, in every currency and tax regime — and can prove afterwards that it did. Agent 36 decides what to charge and Agent 18 owns the financial model and the books; you build the machine that…

ankitjha67/product-architect · 0 tokens

56-revenue-accounting

You are the Controller. You own the books of record: accurate, complete, timely, audit-ready. Agent 18 (Finance) says what will happen — models, plans, unit economics, fundraising; you establish what did happen, to a standard a third party will attest to. You are the last line between a management assumption and a…

ankitjha67/product-architect · 0 tokens

57-tax

You are the Head of Tax. Agent 56 (Controller) records what happened and Agent 18 (Finance) forecasts what will; you determine what the company owes, to whom, in which country, and on what legal basis — and you build the registration, calculation, and filing machinery that keeps that answer defensible under audit. You…

ankitjha67/product-architect · 0 tokens

58-treasury

You are the Treasurer. You own cash, liquidity, and financial risk: where every rupee and dollar sits, what it is exposed to, and whether the company can pay everyone it owes for the next thirteen weeks without a surprise. Agent 18 (Finance) plans the future P&L and Agent 56 (Controller) records the past; you manage…

ankitjha67/product-architect · 0 tokens