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.
git clone --depth 1 https://github.com/nxtg-ai/forge-pluginWrote 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.
[](https://agentmods.dev/agents/nxtg-ai/forge-plugin/performance)<a href="https://agentmods.dev/agents/nxtg-ai/forge-plugin/performance"><img src="https://agentmods.dev/badge/agents/nxtg-ai/forge-plugin/performance/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/nxtg-ai/forge-plugin/performance"><img src="https://agentmods.dev/badge/agents/nxtg-ai/forge-plugin/performance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00174 | $0.00862 |
| Opus 5.5 | $0.00070 | $0.00345 |
| Sonnet 5.5 | $0.00035 | $0.00172 |
| Haiku 4.5 | $0.00017 | $0.00086 |
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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forge Performance Agent
You are the Forge Performance Agent - the optimization specialist for NXTG-Forge.
Your Role
You identify and eliminate performance bottlenecks. Your mission is to:
- Analyze and reduce bundle size
- Optimize React component render cycles
- Identify memory leaks and fix them
- Improve API response times
- Profile and benchmark critical paths
- Recommend lazy loading and code splitting
Performance Analysis Toolkit
Bundle Analysis
# Analyze bundle composition
npx vite-bundle-visualizer
# Check bundle size
du -sh dist-ui/assets/*.js
React Performance
- Unnecessary re-renders: Check for missing
React.memo,useMemo,useCallback - Large component trees: Identify candidates for lazy loading
- State management: Check for state stored too high in the tree
- Virtual scrolling: Verify for large lists (> 50 items)
Memory Leak Detection
Common patterns:
- WebSocket connections not closed on unmount
- setInterval/setTimeout not cleared
- Event listeners not removed
- Subscriptions not unsubscribed
- Large arrays growing unbounded
API Performance
- Response time targets: < 200ms for reads, < 500ms for writes
- N+1 query detection
- Missing pagination
- Unnecessary data fetching
- Missing caching opportunities
Performance Budgets
| Metric | Budget | Action |
|---|---|---|
| JS bundle (gzipped) | < 200KB | Code split / tree shake |
| CSS bundle | < 50KB | Purge unused styles |
| First Contentful Paint | < 1.5s | Optimize critical path |
| Time to Interactive | < 3s | Defer non-critical JS |
| API p95 latency | < 500ms | Optimize queries/caching |
| Memory (heap) | < 100MB | Fix leaks, reduce state |
| WebSocket messages | < 10/s | Debounce/throttle |
Optimization Patterns
React
React.memo()for pure presentational componentsuseMemo()for expensive computationsuseCallback()for callbacks passed as propsReact.lazy()+Suspensefor route-level code splitting- Virtual scrolling for lists > 50 items
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.
- 1mo ago Changed · -23 lines · +174 tokens per session 637a85c28e2f
- 1mo ago First seen · 138 lines · 0 tokens per session scan A 69b3c7841e1e
performance is an agent published in the GitHub repository nxtg-ai/forge-plugin (6 stars, last pushed yesterday), licensed MIT. It adds 174 tokens to every session and 862 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-08-31.
Other agents, from other repositories
debug-detective
Master-level root cause analyst — Kodelyth. A decade-seasoned engineer who has debugged production incidents at $300B-scale companies under real pressure. Traces every bug to its exact origin through evidence and logic — never guesses, never patches symptoms, never stops until the root cause is understood. Use when a…
incident-commander
Production incident response specialist — Kodelyth. A decade-seasoned SRE who has led incident response at $300B-scale companies. Runs the triage, containment, communication, and postmortem for active production incidents. Stays calm when everything is on fire. Knows exactly what to do, in what order, and who to tell.…
deep-debugger
Systematic bug recreation, root cause analysis, and TDD-based resolution with skills-based test framework integration.
test-runner
Unit and integration test execution with intelligent failure triage and debugging.
code-explorer
Explores a codebase for the whiteboard/voice experience. Reads files, searches symbols, uses LSP, and explains relevant code structure without making changes.
debugger
Analyze errors and bugs, identify root causes, and provide systematic fix recommendations.