README

A directory of specialized Claude Code agent configurations for AudioBash, a voice-controlled terminal application built with Electron.

In plain words
What is it for?
Use its security agent to review vulnerabilities, its UI agent to build React and Tailwind interface changes, and its performance agent to investigate Electron, rendering, memory, or bundle-size issues.
Why use it?
It gives focused development roles instead of asking one general agent to handle security, interface design, or performance work.

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

Made for: Claude Code.

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 1,295 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 $0.01295
Opus 5 $0.00000 $0.00647
Sonnet 5 $0.00000 $0.00259
Haiku 4.5 $0.00000 $0.00129

Measured 2d ago against content hash 5148680f6392, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

README 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.

.claude/agents/README.md · 233 lines

How it starts

The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AudioBash Specialized Agents

This directory contains specialized Claude Code agent configurations for different AudioBash development workflows.

Available Agents

1. audiobash-security (Opus 4.5)

Security-focused code reviewer for Electron and Node.js security.

Usage:

claude --agent audiobash-security

Focus:

  • Electron security (context isolation, IPC, CSP)
  • Dependency vulnerabilities
  • Shell injection risks
  • Credential exposure
  • File system security

Tools: Read-only (Read, Grep, Glob, npm audit, git diff)


2. audiobash-ui (Sonnet 4.5)

UI developer specialized in void/brutalist aesthetic.

Usage:

claude --agent audiobash-ui

Focus:

  • Void/brutalist design language
  • React 19 + TypeScript components
  • Tailwind CSS styling
  • xterm.js integration
  • CRT effects and retrotechnofuturism

Tools: Full editing (Read, Edit, Write, Grep, Glob, npm commands)


3. audiobash-perf (Sonnet 4.5)

Performance engineer for Electron optimization.

Usage:

claude --agent audiobash-perf

Focus:

  • Electron process optimization
  • xterm.js rendering performance
  • React rendering optimization
  • Bundle size analysis
  • Memory management
  • IPC efficiency

Tools: Analysis + editing (Read, Edit, Grep, Glob, npm build, file size analysis)


4. audiobash-test (Sonnet 4.5)

Test engineer for Vitest-based testing.

Usage:

claude --agent audiobash-test

Focus:

  • Vitest test patterns
  • React Testing Library
  • Electron IPC testing
  • Cross-platform compatibility
  • 70+ test suite maintenance

Tools: Full testing (Read, Edit, Write, Grep, Glob, npm test, vitest)


How to Use

Start a Session with an Agent

# From the audiobash directory
claude --agent audiobash-security    # Security review
claude --agent audiobash-ui          # UI development
claude --agent audiobash-perf        # Performance optimization
claude --agent audiobash-test        # Test writing

Read the full file on GitHub · 233 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 · 233 lines · 0 tokens per session scan A 5148680f6392

Subscribe to this mod's changes

README is an agent published in the GitHub repository jamditis/audiobash (5 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,295 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

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

reviewer

../../.claude/agents/reviewer.md.

fredrikaverpil/dotfiles · 0 tokens

vet

Perceptual-quality analyst for orkid output artifacts — images, movies, meshes (OBJ), heightmaps. Use for open-ended quality work (why does this look wrong, review N renders, compare silhouettes across seeds, corpus sweeps, triage) AND for improving the vet instruments themselves. Instruments-first discipline; never…

tweakoz/orkid · 90 tokens

gate-runner

Verification agent for orkid engine work. Use after an implementation slice to run a named battery — builds (with lying-rc defense), pyext tests, canaries, bounded scene runs, fleet jobs via obtnet, artifact byte-identity/idiff/histogram comparisons — and return a verdict-first report. Give it an explicit list of…

tweakoz/orkid · 101 tokens

laravel-feature-builder

Use this agent when you need to implement new features in a Laravel application, including creating models, controllers, migrations, routes, views, and associated business logic. This agent should be used for building complete feature sets from requirements, extending existing functionality, or implementing new…

freekmurze/dotfiles · 0 tokens

ROUTING

Is this a workflow phase (spec, plan, tasks, optimize, ship)? ├── Yes → Use PHASE AGENT (spec-agent, plan-agent, etc.) └── No → Continue...

marcusgoll/Spec-Flow · 0 tokens