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 skills/jamditis/audiobash/user-testingnpx skills add jamditis/audiobash --skill user-testinggit clone --depth 1 https://github.com/jamditis/audiobashWhat 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 | $0.03138 |
| Opus 5 | $0.00000 | $0.01569 |
| Sonnet 5 | $0.00000 | $0.00628 |
| Haiku 4.5 | $0.00000 | $0.00314 |
Grade A, and why
user-testing 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.
How it starts
The opening of the file, as written. The whole thing — 389 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AudioBash End-User Testing Skill
Testing AudioBash from the perspective of non-technical users, with focus on Electron, terminal emulation, and audio recording edge cases.
Quick Test Suite
Run these tests after any significant change:
# 1. Launch fresh build
pkill AudioBash 2>/dev/null
rm -f ~/Library/Application\ Support/audiobash/Singleton*
open "dist/mac-arm64/AudioBash.app"
sleep 4
pgrep AudioBash && echo "✅ Launch OK"
# 2. Multi-instance prevention
open "dist/mac-arm64/AudioBash.app"
open "dist/mac-arm64/AudioBash.app"
sleep 2
[ $(pgrep AudioBash | wc -l) -eq 5 ] && echo "✅ Single instance OK"
# 3. Tab creation
osascript -e 'tell application "AudioBash" to activate'
osascript -e 'tell application "System Events" to keystroke "t" using command down'
sleep 1
[ $(pgrep zsh | wc -l) -ge 2 ] && echo "✅ Tab creation OK"
# 4. Large paste
python3 -c "print('A' * 50000)" | pbcopy
osascript -e 'tell application "System Events" to keystroke "v" using command down'
sleep 2
pgrep AudioBash && echo "✅ Large paste OK"
# 5. Force quit recovery
pkill -9 AudioBash
sleep 1
open "dist/mac-arm64/AudioBash.app"
sleep 4
pgrep AudioBash && echo "✅ Force quit recovery OK"
# Cleanup
pkill AudioBash 2>/dev/null
echo "Tests complete"
Test Categories
1. Installation & Launch
| Test | Command | Expected |
|---|---|---|
| Run from DMG | open "/Volumes/AudioBash*/AudioBash.app" |
App runs from read-only volume |
| Run from dist folder | open "dist/mac-arm64/AudioBash.app" |
App runs normally |
| Gatekeeper bypass | Right-click → Open | Dialog allows opening |
| xattr removal | xattr -cr /Applications/AudioBash.app |
Removes quarantine |
spawn-helper Permission Check:
# This is the #1 cause of launch failures
ls -la dist/mac-arm64/AudioBash.app/Contents/Resources/app.asar.unpacked/node_modules/node-pty/prebuilds/darwin-arm64/spawn-helper
# Must show: -rwxr-xr-x (755)
# Fix if wrong:
chmod +x dist/mac-arm64/AudioBash.app/Contents/Resources/app.asar.unpacked/node_modules/node-pty/prebuilds/darwin-*/spawn-helper
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.
- 2d ago First seen · 389 lines · 0 tokens per session scan A 552cf599e3c3
user-testing is a skill published in the GitHub repository jamditis/audiobash (5 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,138 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 skills, from other repositories
seedance-audio
This skill should be used when the user asks for Seedance 2.0 audio, dialogue, lip-sync, music, sound effects, ambience, beat-sync, audio-reference mapping, desync troubleshooting, or sound-driven visual timing.
record-demo
Record or regenerate the mcpc demo GIFs (the README hero docs/images/mcpc-demo.gif and the focused tapes in docs/vhs/) with VHS. Use whenever asked to create, refresh, restyle, shorten, or fix a terminal demo/animation/GIF of mcpc. The tapes drive real mcpc commands; for the authenticated step this skill ALWAYS…
metasounds
Create and modify MetaSound Source assets — add/connect nodes, wire pins, set input defaults, and play procedurally (MetaSoundService). Use when the user asks to create a MetaSound, build or edit a MetaSound graph, add operator/input/output nodes, or generate procedural audio.
videoagent-audio-studio
Tired of juggling multiple audio APIs? This skill gives you one-command access to TTS, music generation, sound effects, and voice cloning. Use when you want to generate any audio without managing multiple API keys.
transcribe-tool
Audio transcription tool. Converts audio files to text with Whisper and optional LLM post-processing. Use when: transcribing meetings, podcasts, or extracting text from recorded audio files.
audio-transcriber
Transform audio recordings into professional Markdown documentation with intelligent summaries using LLM integration.