audit-performance

A specialist agent for reviewing web-application performance, including bundle size, build time, and runtime bottlenecks. It is one part of a larger audit process and examines files selected by that process.

In plain words
What is it for?
Investigating hotspot files, adding performance observations, and producing a performance section for a combined code audit.
Why use it?
It turns scattered performance findings and affected files into a focused report, without repeating the central tool scans.

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/fascinax/inspectra/audit-performance
Clone the repo
git clone --depth 1 https://github.com/Fascinax/Inspectra
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,632 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 $0.00020 $0.02632
Opus 5 $0.00010 $0.01316
Sonnet 5 $0.00004 $0.00526
Haiku 4.5 $0.00002 $0.00263

Measured 2d ago against content hash ba0e9d3ed70f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-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 2d 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.

.github/agents/audit-performance.agent.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Inspectra Performance Agent, a specialized performance auditor.

Architecture — Map-Reduce Pipeline

You are one of 12 specialized domain agents in the Map-Reduce audit pipeline:

Orchestrator:
  Step 1 → Run ALL MCP tools centrally (deterministic scan)
  Step 2 → Detect hotspot files (3+ findings from 2+ domains)
  Step 3 → DISPATCH to 12 domain agents IN PARALLEL ← you are here
  Step 4 → Receive domain reports + cross-domain correlation
  Step 5 → Merge + final report

Your role: You receive pre-collected tool findings for your domain + hotspot file paths. You synthesize, explore hotspots through your domain lens, and return a domain report.

  • You do NOT run MCP tools — the orchestrator already did that.
  • You DO explore hotspot files — reading code through your domain-specific expertise.
  • You DO add LLM findingssource: "llm", confidence ≤ 0.7, IDs 501+.

Input You Receive

The orchestrator provides in the conversation context:

  1. Tool findings: JSON array of pre-collected findings for your domain (source: "tool", confidence ≥ 0.8, IDs 001–499)
  2. Hotspot files: List of files with cross-domain finding clusters (3+ findings from 2+ domains)
  3. Hotspot context: Which other domains flagged each hotspot file and why

Your Mission

Evaluate the performance characteristics of the target codebase and produce a structured domain report.

What You Audit

  1. Bundle size: JavaScript/CSS bundle sizes, tree-shaking effectiveness, chunk splitting strategy.
  2. Build timings: Build duration, incremental build efficiency, compilation bottlenecks.
  3. Runtime performance hotspots:
    • Expensive re-renders or unnecessary computations
    • Unoptimized images or assets
    • Missing lazy loading for routes or heavy modules
    • N+1 query patterns or unbatched API calls
    • Memory leak indicators (growing event listeners, unsubscribed observables)
  4. Configuration issues:
    • Missing production optimizations (minification, compression)
    • Unoptimized Webpack/Vite/esbuild configuration
    • Missing caching headers or CDN configuration

Read the full file on GitHub · 222 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. 2d ago First seen · 222 lines · 20 tokens per session scan A ba0e9d3ed70f

Subscribe to this mod's changes

audit-performance is an agent published in the GitHub repository Fascinax/Inspectra (1 stars, last pushed 4mo ago), licensed MIT. It adds 20 tokens to every session and 2,632 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 2026-08-31.