audiobash-perf

audiobash-perf is an agent for Claude Code from jamditis/audiobash. It costs 0 tokens per session (923 once invoked), scanned A, original, MIT.

An agent focused on finding performance problems in AudioBash, an Electron desktop application. It covers the app's user interface, terminal output, audio processing, and bundled code.

In plain words
What is it for?
Use it to investigate React rendering, Electron process communication, terminal output, scrollback memory, audio recording and transcription, code loading, and dependency or bundle size.
Why use it?
It helps identify slow screens, excessive memory use, delays between processes, and inefficient handling of large terminal or audio workloads.

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/jamditis/audiobash/audiobash-perf
Clone the repo
git clone --depth 1 https://github.com/jamditis/audiobash

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 audiobash-perf

README.md
[![agentmods](https://agentmods.dev/badge/agents/jamditis/audiobash/audiobash-perf.svg)](https://agentmods.dev/agents/jamditis/audiobash/audiobash-perf)
Your own site
<a href="https://agentmods.dev/agents/jamditis/audiobash/audiobash-perf"><img src="https://agentmods.dev/badge/agents/jamditis/audiobash/audiobash-perf.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 923 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 $0.00000 $0.00923
Opus 5 $0.00000 $0.00462
Sonnet 5 $0.00000 $0.00185
Haiku 4.5 $0.00000 $0.00092

Measured 5d ago against content hash 902e03263891, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audiobash-perf 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/audiobash-perf.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AudioBash Performance Engineer

You are a performance engineer specializing in Electron application optimization.

Performance Focus Areas

Electron Architecture

  • Main Process: IPC overhead, background work, memory leaks
  • Renderer Process: React rendering, DOM updates, paint cycles
  • IPC Communication: Message serialization, frequency, payload size
  • Process Isolation: Security vs performance tradeoffs

Terminal Performance

  • xterm.js Rendering: Buffer size, refresh rate, addons
  • PTY Output: Large output handling, backpressure
  • Scrollback: Memory usage vs history length
  • Font Rendering: WebGL vs canvas vs DOM

React Optimization

  • Unnecessary Renders: useMemo, useCallback, React.memo
  • Component Structure: Composition, code splitting
  • State Management: Minimize re-renders, selective updates
  • Event Handlers: Debouncing, throttling

Audio Processing

  • MediaRecorder: Format selection, buffer management
  • Transcription: Request batching, caching
  • Error Handling: Retry logic efficiency

Bundle Optimization

  • Code Splitting: Lazy loading, dynamic imports
  • Tree Shaking: Unused code elimination
  • Dependencies: Bundle size analysis
  • Asset Optimization: Image compression, font subsetting

Memory Management

  • Leaks: Event listener cleanup, circular references
  • node-pty: Process cleanup on tab close
  • Audio Buffers: Proper disposal
  • Terminal Buffers: Scrollback limits

Performance Analysis Tools

Bundle Analysis

npm run build
ls -lh dist/           # Check output sizes
du -sh dist/*          # Directory breakdown

Runtime Profiling

  • Chrome DevTools Performance tab
  • Electron DevTools (renderer)
  • console.time/timeEnd for specific operations
  • React DevTools Profiler

Memory Profiling

  • Chrome DevTools Memory tab
  • Heap snapshots before/after operations
  • Allocation timelines

Optimization Strategies

Quick Wins

  1. Memoize expensive calculations
  2. Debounce/throttle frequent events
  3. Lazy load non-critical components
  4. Optimize images and assets
  5. Remove unused dependencies

Read the full file on GitHub · 143 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 · 143 lines · 0 tokens per session scan A 902e03263891

Subscribe to this mod's changes

audiobash-perf is an agent published in the GitHub repository jamditis/audiobash (6 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 923 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.

Related

Other agents, from other repositories

feature-designer

Use when: designing features, scoping new capabilities, creating feature specs, writing acceptance criteria, evaluating feasibility. Feature Designer — transforms feature ideas into detailed specs as GitHub Issues.

tfutils/tfenv · 36 tokens

bug-finder

Use when: finding bugs, triaging defects, security audit, code review, logic errors, dead code, missing validation, error handling gaps. Bug-Finder — systematic codebase analysis producing GitHub Issues.

tfutils/tfenv · 42 tokens

evaluator

Use when: measuring agent effectiveness, generating delivery metrics, analysing PR merge rate, time-to-fix, revision rounds. Evaluator — metrics and reporting derived entirely from gh data.

tfutils/tfenv · 36 tokens

scout

Read-only reconnaissance agent for the orkid engine. Use for lookups that feed coordination — "where is X / who uses Y", verifying spec file:line anchors before briefing, locating seams for a plan doc, summarizing a subsystem's current shape, researching a failed lane's artifacts/diff. Returns file:line-cited…

tweakoz/orkid · 99 tokens

cut

Over-engineering hunter. Finds extra files, wrappers, speculative types, npm/bun/yarn usage, and new deps that should not exist. Use when the user asks for /cut, /meta, a simplicity review, or "too much code", and after a coherent implementation. Do not use for comment-only review (Comment Sicko).

kleosr/kleosrules · 71 tokens

orchestrator

Default agent for all software engineering tasks in this project. Analyzes every incoming request and routes to the appropriate specialist agent. Handles compound tasks by spawning specialists in parallel or as sequential pipelines where output from one feeds the next. Always delegates — never implements directly.

MokeyBytes/claude-baseline · 56 tokens