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 xuiltul/animaworks --skill zoom-meeting-scribegit clone --depth 1 https://github.com/xuiltul/animaworksWrote 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/xuiltul/animaworks/zoom-meeting-scribe)<a href="https://agentmods.dev/skills/xuiltul/animaworks/zoom-meeting-scribe"><img src="https://agentmods.dev/badge/skills/xuiltul/animaworks/zoom-meeting-scribe/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/xuiltul/animaworks/zoom-meeting-scribe"><img src="https://agentmods.dev/badge/skills/xuiltul/animaworks/zoom-meeting-scribe.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 74 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00085 | $0.01247 |
| Opus 5 | $0.00043 | $0.00624 |
| Sonnet 5 | $0.00017 | $0.00249 |
| Haiku 4.5 | $0.00009 | $0.00125 |
Grade A, and why
zoom-meeting-scribe 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 11d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Zoom Meeting Scribe (Listen, Summarize, Report with Approval)
The Zoom RTMS gateway injects meeting transcripts into your inbox as chunks every few minutes. Your role is to act as a listen-only participant — understand and organize the content, compile a report once the meeting ends, and post it only after obtaining human approval.
Format of Incoming Messages
The header strings below are emitted in Japanese by the gateway implementation (server/zoom_gateway.py); the English meaning is shown in parentheses. Match against the Japanese text as-is.
| Type | Header | Meaning |
|---|---|---|
| Live chunk | [Zoom会議実況 チャンク#N | 会議: {title} ({meeting ID}) | {start time}〜] (Zoom live chunk) |
Utterances during the meeting (followed by lines of speaker: utterance) |
| End notice | [Zoom会議終了 | 会議: {title} ({meeting ID}) | 全Nチャンク配信済み] (Zoom meeting ended, all N chunks delivered) |
Meeting is over. Cue to write the report |
- Chunks for the same meeting arrive in the same thread (
zoom-{meeting UUID}). - If a chunk begins with
[接続断により一部欠落](some content lost due to a dropped connection), the utterances immediately before it may have been lost. Note the possibility of a gap in the report. - Speaker names are the Zoom display names.
不明(unknown) marks utterances whose speaker could not be identified.
Workflow
1. On receiving a live chunk — stay silent and take it in
- Read the content and progressively organize the following into your own notes (working memory / notes):
- Decisions (who decided what)
- Action items (owner, deadline)
- Open questions / carried-over items
- Key points of how the meeting is flowing
- Do not reply, post to any channel, or intervene in the meeting in any way. You are a listener.
- If you notice a missing chunk number, treat it as a gap.
2. Immediate escalation of urgent matters (exception)
Even during the meeting, if you detect content matching any of the following, report the key points at that moment to your supervisor (the supervisor shown in your org context) via send_message:
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.
- 11d ago First seen · 116 lines · 85 tokens per session scan A 3a011d6e53d2
zoom-meeting-scribe is a skill published in the GitHub repository xuiltul/animaworks (254 stars, last pushed today), licensed Apache-2.0. It adds 85 tokens to every session and 1,247 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
email-triage
Classify incoming emails into triage categories using content analysis, sender profile memory, and thread detection. Produces a category (URGENT, REPLYNEEDED, FYI, NEWSLETTER, NOTIFICATION, SPAM) with confidence and reasoning.
efficient-execution
Reduce token waste and task completion time by choosing the simplest tool for each job.
customer-email-assist
Review Gmail customer-support threads with a minimal-token, connector-first workflow. Use when Codex needs to read Gmail through the Codex Gmail connector, import cleaned messages into a local SQLite issue queue, apply deterministic cleanup and classification first, reserve model usage for JSON-only message…
local-document-organizer
Preview-first local file organizer. Scan a user-named folder, classify files with readable rules, show a plan, execute approved moves and undo them. Use for sorting Downloads, renaming into category folders, or reviewing organization history, including scoped metadata-only course persistence. Do not use for knowledge…
Loop
Run the same task on a recurring cron schedule. Parses interval syntax (5m, 2h, 1d, "/15 "), records the schedule, and acknowledges back to the user.
Batch Run
Apply the same prompt or operation to a list of items in turn, collecting results. Useful for "do X to each of these files / PRs / records" tasks.