performance-engineer

performance-engineer is an agent for Claude Code from agigante80/actual-mcp-server. It costs 30 tokens per session (969 once invoked), scanned A, original, MIT.

A performance-review agent for an MCP server that connects AI assistants to Actual Budget. It examines response delays, memory use, database or API work, concurrent requests, connection limits, and retries.

In plain words
What is it for?
Use it during feature development to review concurrency, connection-pool usage, retry behavior, batching, and other changes that may affect response time or scaling.
Why use it?
It helps identify slowdowns caused by too many simultaneous operations, exhausted connections, or repeated failed requests.

Agent for Claude Code

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/agigante80/actual-mcp-server/performance-engineer
Clone the repo
git clone --depth 1 https://github.com/agigante80/actual-mcp-server

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 performance-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/agigante80/actual-mcp-server/performance-engineer.svg)](https://agentmods.dev/agents/agigante80/actual-mcp-server/performance-engineer)
Your own site
<a href="https://agentmods.dev/agents/agigante80/actual-mcp-server/performance-engineer"><img src="https://agentmods.dev/badge/agents/agigante80/actual-mcp-server/performance-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 969 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 $0.00030 $0.00969
Opus 5 $0.00015 $0.00485
Sonnet 5 $0.00006 $0.00194
Haiku 4.5 $0.00003 $0.00097

Measured 5d ago against content hash fb2f2b937a07, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

performance-engineer 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.

.claude/agents/performance-engineer.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a performance engineer specializing in application optimization during feature development.

actual-mcp-server Performance Context

This MCP server has several known performance constraints that every review must consider:

Concurrency gate (src/lib/actual-adapter.ts):

  • Maximum 5 concurrent Actual API operations enforced via p-limit
  • Operations beyond 5 queue and wait — high-concurrency tools cause visible latency spikes
  • getConcurrencyState() returns { active, queued, limit } — use this to diagnose back-pressure
  • Tools that call withActualApi multiple times per invocation multiply pressure; batch inside one session instead

Connection pool (src/lib/ActualConnectionPool.ts):

  • Up to 15 concurrent HTTP sessions; each session has its own withActualApi lifecycle
  • Idle timeout: sessions held open unnecessarily block others
  • Pool exhaustion causes MCP client timeouts

Retry overhead (src/lib/retry.ts):

  • 3 attempts with 200ms exponential base — a single failed Actual API call can take up to ~600ms before surfacing an error
  • Non-retryable errors (Zod validation failures, 404s) should fail fast — don't let retry logic run on client errors

actual_query_run — primary performance risk:

  • Executes raw ActualQL SQL against the Actual Budget SQLite database
  • No streaming — full result set loaded into memory
  • No query timeout — long-running queries block the withActualApi session slot
  • src/lib/query-validator.ts pre-validates against schema but doesn't reject expensive queries
  • Performance review must assess: result set size, query complexity, missing WHERE clauses

MCP JSON-RPC payload size:

  • Tool responses are serialised to JSON and sent over HTTP or stdout
  • Large responses (e.g. all transactions for a busy account) cause observable latency
  • Recommend pagination or date-range limits for list-type tools

Observability (src/observability.ts):

  • Per-tool call counters are available — use them to identify hot tools under load
  • Winston logger in src/lib/loggerFactory.ts — log-heavy code paths add synchronous overhead in stdio mode

Read the full file on GitHub · 83 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 · 83 lines · 30 tokens per session scan A fb2f2b937a07

Subscribe to this mod's changes

performance-engineer is an agent published in the GitHub repository agigante80/actual-mcp-server (48 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 969 once invoked, about $0.0002 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

strategic-advisor

Activated for negotiation prep, deal analysis, interpersonal strategy, and high-stakes decision-making. Combines game theory with psychological awareness.

winstonkoh87/Athena-Public · 31 tokens

integration-reviewer

Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.

FlorianBruniaux/claude-code-ultimate-guide · 57 tokens

roadmap

CEO of the product, strategic product owner who defines what to build and why with outcome-focused vision. Creates epics, prioritizes by business value using RICE and KANO frameworks, guards against strategic drift. Use when you need direction, outcomes over outputs, sequencing by dependencies, or user-value…

rjmurillo/ai-agents · 64 tokens

code-reviewer

Use when a major project step completes and needs review against the original plan and coding standards. Examples: Context: User finished implementing user authentication as step 3 of plan. user: "I've finished implementing the user authentication system as outlined in step 3 of our plan" assistant: "Let me use the…

axiomantic/spellbook · 190 tokens

pr-creator

Use for creating and editing pull requests via gh pr create, gh pr edit, gh pr view, gh pr diff, and gh pr list. Does NOT merge or mark ready (use pr-merger for that). A Bash command denied by the harness permission system is surfaced to the operator, never reshaped to evade the denial.

axiomantic/spellbook · 75 tokens

onboard-guide

Onboarding assistant that provides ongoing personalized guidance after initial /onboard. Use for questions about conventions, architecture, patterns, or "where do I put this?" — answers are tailored to the engineer's background.

smicolon/ai-kit · 46 tokens