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.
npx agentmods add agents/nxtg-ai/forge-plugin/performancegit clone --depth 1 https://github.com/nxtg-ai/forge-pluginWhat 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 | $0.00000 | $0.01925 |
| Opus 5 | $0.00000 | $0.00962 |
| Sonnet 5 | $0.00000 | $0.00385 |
| Haiku 4.5 | $0.00000 | $0.00193 |
Grade A, and why
performance 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.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance
Finds and eliminates bottlenecks -- profiles bundle size, React render cycles, memory leaks, API latency, and enforces performance budgets.
| Level | L1 Vibe Coder |
| Category | Domain Specialist |
| Model | Sonnet |
What It Does
The Performance agent measures first and optimizes second. When your dashboard takes forever to load or your bundle exceeds 2MB, it does not guess at the cause -- it profiles, identifies the specific bottleneck, and applies targeted fixes. It understands the full performance stack: JavaScript bundle size and tree-shaking, React component render cycles, memory allocation and leak detection, API response times and query efficiency, and WebSocket message throughput.
The agent enforces performance budgets -- concrete thresholds that separate "fast enough" from "needs work." JS bundle under 200KB gzipped. First Contentful Paint under 1.5 seconds. API p95 latency under 500ms. Heap memory under 100MB. These are not aspirational targets; they are enforced constraints. When a budget is exceeded, the agent identifies the specific cause and recommends a fix: code split this route, memoize this component, debounce this state update, paginate this query.
What makes this agent particularly useful for React applications is its understanding of render performance. It identifies unnecessary re-renders caused by missing React.memo, inline object/function creation in JSX, state stored too high in the component tree, and components that could benefit from lazy loading. These are the performance issues that do not show up in network profiling but dominate real-world user experience.
When to Use It
- When the UI feels slow: When page loads take too long, interactions feel laggy, or scrolling stutters. The Performance agent profiles to identify whether the bottleneck is bundle size, render cycles, data fetching, or memory.
- When bundle size is too large: When your production build exceeds budget and you need specific recommendations on what to code-split, tree-shake, or lazy-load.
- When memory usage grows over time: When long-running sessions (dashboards, terminals) accumulate memory. The agent identifies leak patterns: unclosed WebSockets, cleared intervals, removed event listeners, and unbounded arrays.
- After adding new dependencies: When a new library increases bundle size and you need to assess the cost vs. alternatives.
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.
- yesterday First seen · 138 lines · 0 tokens per session scan A 69b3c7841e1e
performance is an agent published in the GitHub repository nxtg-ai/forge-plugin (5 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,925 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 2026-08-31.
Other agents, from other repositories
code-reviewer
Reviews code for project guideline compliance, bugs, and quality issues. Use after writing code, before commits, or before PRs. Specify files to review or defaults to unstaged git changes. High-confidence issues only (80+) to minimize noise.
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
data-pipeline-engineer
Data pipeline specialist: embeddings, chunking strategies, vector indexes, data transformation for AI consumption.
demo-producer
Universal demo video producer that creates polished marketing videos for any content - skills, agents, plugins, tutorials, CLI tools, or code walkthroughs. Uses VHS terminal recording and Remotion composition.
emulate-engineer
Stateful API emulation via Vercel emulate. Seeds GitHub/Vercel/Google/Slack/Apple/Entra/AWS/MongoDB/Okta/Resend/Stripe/Clerk/Linear, webhooks, port isolation, Next.js adapter. Use to replace flaky API mocks.
TESTING
This document provides comprehensive guidance for testing the Multi-Agent Networks feature in NeuroLink.