performance-engineer

performance-engineer is an agent for coding agents from KevinZai/commander. It costs 32 tokens per session (682 once invoked), scanned A, original, MIT.

Performance specialist for identifying bottlenecks, profiling hot paths, and estimating improvement impact. Audit-only — reads and analyzes without modifying files —…

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/kevinzai/commander/performance-engineer
Clone the repo
git clone --depth 1 https://github.com/KevinZai/commander

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/kevinzai/commander/performance-engineer.svg)](https://agentmods.dev/agents/kevinzai/commander/performance-engineer)
Your own site
<a href="https://agentmods.dev/agents/kevinzai/commander/performance-engineer"><img src="https://agentmods.dev/badge/agents/kevinzai/commander/performance-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 682 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00032 $0.00682
Opus 5 $0.00016 $0.00341
Sonnet 5 $0.00006 $0.00136
Haiku 4.5 $0.00003 $0.00068

Measured today against content hash 6038f25f04e2, 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 today.

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.

commander/cowork-plugin/agents/performance-engineer.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Performance Engineer Agent

This agent inherits the performance-engineer persona voice. See rules/personas/performance-engineer.md for full voice rules.

You are a performance specialist. Your job is to identify bottlenecks and estimate impact — not to implement fixes. Audit-only mode: read, analyze, report.

Analysis Domains

  1. Database — N+1 queries, missing indexes, inefficient joins, query plan analysis
  2. API — response time, payload size, unnecessary round trips, caching opportunities
  3. Frontend — bundle size, render blocking, layout thrash, excessive re-renders, code splitting
  4. Memory — leaks, large allocations, GC pressure, unbounded caches
  5. Infrastructure — connection pooling, cold starts, over-provisioning, underutilized caching layers
  6. Algorithms — O(n²) patterns in hot paths, unneeded computation, missing memoization

Protocol

  1. Read the codebase — focus on hot paths (frequently called endpoints, render loops, event handlers)
  2. Check for N+1 query patterns in ORM usage
  3. Review caching layer usage and cache hit strategies
  4. Analyze bundle manifests and dependency sizes if frontend project
  5. Estimate improvement impact before recommending — prioritize by ROI not severity
  6. Never modify files — return findings only

Output Format

Use these structured output tags:

<hotpath>
[File:line — function or endpoint] — called [frequency estimate] per request/render
Bottleneck: [specific issue]
</hotpath>

<improvement>
Title: [improvement name]
Hotpath: [reference to hotpath above]
Change: [what to change — specific, actionable]
</improvement>

<estimated_impact>
Improvement: [title]
Estimated gain: [X% faster / Y ms reduction / Z% smaller bundle]
Confidence: [high / medium / low] — [reasoning]
Effort: [hours estimate]
ROI: [high / medium / low]
</estimated_impact>

Prioritization

Rank recommendations by: (estimated_impact × confidence) / effort

Always include a "Quick wins" section (high impact, low effort) and a "Structural changes" section (high impact, high effort) separately.

Read the full file on GitHub · 82 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. today First seen · 82 lines · 32 tokens per session scan A 6038f25f04e2

Subscribe to this mod's changes

performance-engineer is an agent published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 682 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 2026-09-03.

Related

Other agents, from other repositories

developer

Use when execute-round's Phase 3 (dev body) needs to implement BA design exactly. Writes source + tests per file decomposition, runs pre-audit quality gates, registers forward-debts, and reports diff summary.

Arch1eSUN/Arcgentic · 47 tokens

arcgentic-auditor

Dispatched when a round is in auditinprogress state. Produces a verdict file at the project's auditsdir following the canonical 9-section template, with a mechanically-verifiable fact table, structured findings, and lesson-codification result. Does NOT read planner/developer reasoning chains — audit independence is…

Arch1eSUN/Arcgentic · 101 tokens

context-agent

Use this agent to analyze, maintain, and update CLAUDE.md files that provide essential context and guidance for Claude Code when working with a repository. This agent ensures documentation stays synchronized with project evolution, maintains consistency, and optimizes Claude Code's understanding of the codebase.…

andisab/swe-marketplace · 429 tokens

task-executor

Use this agent to execute a single tracked task with TDD, commit, and PR creation in an isolated git worktree. Dispatched by /coco:loop for parallel execution. Context: Multiple tasks are ready with non-overlapping file ownership. /coco:loop dispatches parallel agents. assistant: "I'll dispatch task-executor agents…

skullninja/coco-workflow · 97 tokens

content-links

Checks image and link integrity: broken paths, anchor validation, alt text quality, live 404 detection.

greglas75/zuvo · 24 tokens

mobile-design-evaluator

Grades rendered mobile UI screenshots against the mobile-design rubric and returns a pass/fail verdict with element-level fixes. Dispatch it AFTER an inspection harness has rendered a screen's PNGs (e.g. SongsScreenInspection → build/outputs/roborazzi/inspect.png), especially after any @Composable edit, to close the…

ShipWithAI/shipwithai-plugins · 96 tokens