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 skills add SpillwaveSolutions/automating-mac-apps-plugin --skill automating-voice-memosgit clone --depth 1 https://github.com/SpillwaveSolutions/automating-mac-apps-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/skills/spillwavesolutions/automating-mac-apps-plugin/automating-voice-memos)<a href="https://agentmods.dev/skills/spillwavesolutions/automating-mac-apps-plugin/automating-voice-memos"><img src="https://agentmods.dev/badge/skills/spillwavesolutions/automating-mac-apps-plugin/automating-voice-memos/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/skills/spillwavesolutions/automating-mac-apps-plugin/automating-voice-memos"><img src="https://agentmods.dev/badge/skills/spillwavesolutions/automating-mac-apps-plugin/automating-voice-memos.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00065 | $0.00946 |
| Opus 5 | $0.00032 | $0.00473 |
| Sonnet 5 | $0.00013 | $0.00189 |
| Haiku 4.5 | $0.00006 | $0.00095 |
Grade A, and why
automating-voice-memos 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 9d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Automating Voice Memos (no dictionary, data+UI hybrid)
Relationship to the macOS automation skill
- This is a standalone skill for Voice Memos automation.
- For setup help, see the
automating-mac-appsskill for permissions (Full Disk Access, Accessibility) and the ObjC bridge basics. - Prerequisites: Basic JXA (JavaScript for Automation) knowledge; install via macOS System Preferences > Security & Privacy.
Core Framing
- Catalyst App: Voice Memos is an iOS app adapted for macOS without full macOS APIs, hence no AppleScript dictionary for automation.
- UI-first: Prefer UI scripting/keyboard shortcuts for exports to avoid touching the database/container.
- Data (optional): Use data-layer control only if needed (ObjC + sqlite3). This requires broader permissions.
- Permissions: Accessibility for UI automation; Full Disk Access only if you read/write the container/DB.
Workflow (default)
- UI-first (no FDA): export via menu/shortcut to a folder you control.
- Optional data path: resolve storage paths; query CloudRecordings.db (Apple epoch +978307200) only if required.
- For UI actions (recording/export), drive the app with System Events (shortcuts preferred over clicks).
- For editing, prefer external tools (ffmpeg) after export; avoid writing directly into the container unless you accept FDA.
Quickstart (UI-only export; no Full Disk Access)
- Open Voice Memos and select a recording.
- Export/share UI: the Share sheet can send audio to Notes/other apps (no direct File > Export).
- Transcript copy (UI-only, no FDA):
- Run:
osascript skills/automating-voice-memos/scripts/copy_transcript_to_file.applescript "/path/to/output.txt" - Defaults: Desktop/voice-memo-transcript.txt if no arg.
- Shows transcript (if available), selects all, copies, and writes to the target file via clipboard.
- Run:
Permissions
- Accessibility: System Settings > Privacy & Security > Accessibility > Enable for System Events and your automation app (Terminal/Python/Script Editor).
- Full Disk Access: Only if you read/write the Voice Memos container/DB directly. UI-only exports do not require FDA.
- Verify: For UI-only, confirm you can open the Export menu and interact with the save dialog. For data access, verify
${home}/Library/Group Containers/group.com.apple.VoiceMemos.shared/.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/voice-memos-basics.md 863 B
- references/voice-memos-data.md 1.5 KB
- references/voice-memos-recipes.md 2.5 KB
- references/voice-memos-ui.md 1.6 KB
- scripts/copy_transcript_to_file.applescript 2.3 KB
- scripts/export_selected_recording_via_ui.applescript 3.6 KB
- scripts/set_up_voice_memos_automation.sh 2.0 KB runs code
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.
- 9d ago First seen · 67 lines · 65 tokens per session scan A 9085c9307769
automating-voice-memos is a skill published in the GitHub repository SpillwaveSolutions/automating-mac-apps-plugin (40 stars, last pushed 18d ago), licensed MIT. It adds 65 tokens to every session and 946 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
lyric-refiner
Autonomous multi-pass lyric refinement for tightening, cohesion, and album unity. Use after lyrics are written to polish a track or entire album through iterative passes.
mastering-engineer
Guides audio mastering for streaming platforms including loudness optimization and tonal balance. Use when the user has approved tracks and wants to master audio files.
album-art-director
Creates visual concepts for album artwork and generates AI art prompts. Use during planning for concept discussion, or after all tracks are Final for actual artwork generation.
promo-writer
Generates platform-specific social media copy from album themes, track concepts, and lyrics. Use when promo/ templates need to be populated before release.
voice-checker
Reviews lyrics and prose for AI-written patterns (abstract noun stacking, over-explained metaphors, cliche escalation, missing idiosyncrasy, prose AI tells). Advisory Warning/Info severity — flags issues, does not block or rewrite. Use when reviewing lyrics for authenticity or before generation to catch AI-sounding…
album-ideas
Tracks and manages album ideas including brainstorming, planning, and status updates. Use when the user wants to add, review, or organize their album idea backlog.