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 markmhendrickson/ateles --skill record_meetinggit clone --depth 1 https://github.com/markmhendrickson/atelesWrote 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/markmhendrickson/ateles/record_meeting)<a href="https://agentmods.dev/skills/markmhendrickson/ateles/record_meeting"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/record_meeting.svg" alt="Measured on agentmods" 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 | $0.00019 | $0.03289 |
| Opus 5 | $0.00010 | $0.01644 |
| Sonnet 5 | $0.00004 | $0.00658 |
| Haiku 4.5 | $0.00002 | $0.00329 |
Grade A, and why
record_meeting 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 4d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Record meeting
Use this skill when the user wants command-style control of meeting recording.
Default (no argument)
When the user invokes /record_meeting with no argument (or "toggle"): run npm run record_meeting. That starts recording if not running, or stops (and transcribes + Neotoma store) if running. If the user asks to stop without transcribing, run RECORD_MEETING_SKIP_TRANSCRIBE=1 npm run record_meeting (or set RECORD_MEETING_SKIP_TRANSCRIBE=1 in .env) so the WAV is saved but transcribe_audio.py is not run.
Guardrail
- Treat plain
start/stopas meeting-recording commands only when the current thread is clearly about meeting transcription/recording.
Recording disclosure & consent (legal guardrail)
The operator is always a party to recordings made via this skill (operator-triggered, operator present). That satisfies US federal one-party consent and Spain's Penal Code Art. 197 (no interception of others' communications). The residual gaps are US all-party-consent states and EU transparency. Apply this disclosure ladder, best to worst:
- Platform-native recording (preferred). If the call is on Zoom/Meet/Teams, prefer the platform's own Record button: it auto-discloses to everyone — on-screen banner + consent splash + an audio announcement to phone/dial-in participants. This is the only method that reaches dial-ins, and it sidesteps the disclosure problem entirely. Route the resulting file through Tyto's
TYTO_NATIVE_RECORDINGS_DIR(stampedcapture_method=platform_native) so the transcribe+analyze pipeline is identical. When the operator is on a supported platform, suggest native recording instead of starting BlackHole capture. - Verbal announcement. "I'm recording this for my notes." Reaches everyone; continuing to talk after it is valid implied consent in every state.
- In-meeting chat message. Valid + creates a written record, BUT misses (a) phone/dial-in participants (they never see chat) and (b) late joiners (most platforms don't show pre-arrival messages). If using chat, repeat for late joiners and announce verbally for any dial-in.
- Booking-page disclaimer only (e.g. markmhendrickson.com/meet): prior notice, not contemporaneous — leaves a residual gap in all-party states (esp. California) for anyone who didn't book through the page (forwarded invite, booked by someone else).
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.
- 4d ago First seen · 145 lines · 19 tokens per session scan A 6a0a39bd914b
record_meeting is a skill published in the GitHub repository markmhendrickson/ateles (6 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 3,289 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
notion
Notion API for creating and managing pages, databases, and blocks.
gog
Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.
google-workspace
Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python.
box
Box manages cloud files, sharing, search, and metadata.
ima-skill
A unified IMA skill for managing personal notes and knowledge bases through the platform's APIs.
notes
A note-management skill for searching, reading, creating, and adding content to personal notes in IMA, a note and knowledge platform.