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/silverstein/minutes/minutes-verifynpx skills add silverstein/minutes --skill minutes-verifygit clone --depth 1 https://github.com/silverstein/minutesWhat 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 | $0.00071 | $0.00747 |
| Opus 5 | $0.00036 | $0.00374 |
| Sonnet 5 | $0.00014 | $0.00149 |
| Haiku 4.5 | $0.00007 | $0.00075 |
Grade A, and why
minutes-verify scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Path
Before running helper scripts or opening bundled references, set:
export MINUTES_SKILLS_ROOT="$(git rev-parse --show-toplevel)/.agents/skills/minutes"
export MINUTES_SKILL_ROOT="$MINUTES_SKILLS_ROOT/minutes-verify"
/minutes-verify
Run a health check on the Minutes installation to confirm everything is working.
How to verify
Run the verification script included with this skill:
bash "$MINUTES_SKILL_ROOT/scripts/verify-setup.sh"
The script checks each component and outputs a pass/fail status for each. Read the output and report results to the user.
What gets checked
| Check | What it verifies |
|---|---|
| Binary | minutes command exists on PATH |
| Model | At least one whisper model downloaded in ~/.minutes/models/ or ~/.cache/whisper/ |
| Meetings dir | ~/meetings/ directory exists |
| Memos dir | ~/meetings/memos/ directory exists |
| PID state | No stale PID file in ~/.minutes/recording.pid |
| Audio input | CLI-context audio input visibility (macOS only; desktop readiness is authoritative for the signed app) |
| Config | ~/.config/minutes/config.toml exists (optional — defaults work fine) |
| Spotlight privacy | macOS .metadata_never_index markers exist for ~/.minutes and ~/meetings when those directories exist |
After verification
If any checks fail, tell the user exactly what to do:
- Binary missing →
cargo build --releasein the minutes repo, then add to PATH - No model →
minutes setup --model small(recommended) or--model tiny(faster, lower quality) - No meetings dir →
mkdir -p ~/meetings/memos— will also be created on first recording - Stale PID →
rm ~/.minutes/recording.pid— previous recording crashed without cleanup - Audio input warning → Treat as CLI-context-only. If the signed desktop app's Readiness Center shows Audio input/Microphone as ready, trust the desktop app identity.
- Spotlight privacy warning → Open the desktop app or run
minutes setupso Minutes can recreate the.metadata_never_indexmarkers.
What ships with it
2 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.
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.
- yesterday First seen · 60 lines · 71 tokens per session scan A 477f4341d813
minutes-verify is a skill published in the GitHub repository silverstein/minutes (1,457 stars, last pushed 3d ago), licensed MIT. It adds 71 tokens to every session and 747 once invoked, about $0.0004 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
ondevice-model-perf
Deep on-device model-performance context for Murmur on Apple Silicon Metal — the bandwidth-bound mental model, the quant/KV-cache ladder, whisper flash-attn/audioctx/profile discipline, the four crash/leak war stories, residency/RAM math, and the measurement bar. Use whenever a task is about MODEL-level performance /…
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
vox-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage"…
model-compatibility
Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models.