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 team-telnyx/ai --skill telnyx-meeting-botgit clone --depth 1 https://github.com/team-telnyx/aiWrote 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/team-telnyx/ai/telnyx-meeting-bot)<a href="https://agentmods.dev/skills/team-telnyx/ai/telnyx-meeting-bot"><img src="https://agentmods.dev/badge/skills/team-telnyx/ai/telnyx-meeting-bot/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/team-telnyx/ai/telnyx-meeting-bot"><img src="https://agentmods.dev/badge/skills/team-telnyx/ai/telnyx-meeting-bot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
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 →
- high Tool Misuse · line 63 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 400 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Data Exfiltration · line 49 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 60 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00080 | $0.06848 |
| Opus 5 | $0.00040 | $0.03424 |
| Sonnet 5 | $0.00016 | $0.01370 |
| Haiku 4.5 | $0.00008 | $0.00685 |
Grade A, and why
telnyx-meeting-bot 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 6d 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 — 462 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Telnyx Meeting Bot
Use this skill to attend a meeting visibly, monitor its finalized transcript, alert the requester, execute explicitly authorized live rules such as speaking one response, and produce evidence-based meeting results. The bot is observe-only by default: it must not speak, send chat, or make other in-meeting changes unless the requester explicitly asks for that.
Quick Workflow
- Resolve only missing essentials: meeting URL, join now versus a scheduled time, desired live/final outputs, and trigger/action rules. Reuse authorized details; do not ask again.
- Persist an operation record before creating the session and choose its transport. Ordinary sessions use MCP
join_meeting. Any Portal Assistant or Anam avatar session uses RESTPOST /v2/meeting_sessionswith the requested object(s). Persist one stableidempotency_key, the transport, and the exact logical create request; store only a secret reference for a write-only Anam key. REST-only sessions are immediate, so omitjoin_at; Assistant sessions also omitbarge_in. For an ordinary session with an authorized later speech rule, setbarge_in: trueso human speech can stop bot output. - Poll
get_session,get_transcript, and, when available,get_events. Selectwait_secondsfrom the request—about2for “as soon as,” reactive speech, or urgent mentions—and persist cursors, seen segments, outboxes, claims, and IDs for recovery. - On each new final segment, evaluate requested literal or semantic rules; deliver mention notifications through the durable outbox, and atomically claim and execute each authorized
speak/send_chataction at most once. - On a terminal session, drain transcript pages, wait a bounded time for
transcript.completed, obtain requested implemented artifact types without duplicate creation, then deliver a Markdown report.
Preconditions and Safe Defaults
- Require
TELNYX_API_KEYin a backend secret store. Never include it in a URL, transcript, event, artifact, chat message, or user-facing report. - Before joining, ensure the runtime can keep monitoring or can resume from durable background state. Do not promise end-to-end monitoring from a process that disappears without preserving and resuming the operation record.
- Verify authorization for a visible bot. A host may need to admit it; never bypass a waiting room, password, platform policy, or consent requirement.
- Default notification target: this current conversation. Do not configure a
webhook_urlmerely to send requester notifications. - Default behavior is immediate join,
summarize_on_end: true, observe-only, and no recording-media deletion.speak,send_chat,speak_on_enter, andchat_on_enterare opt-in. - An explicit conditional request such as “when someone asks about lunch, say ‘I want pizza’” authorizes exactly that action. Before join, persist trigger, exact payload, one-shot/repeat policy, and latency target; do not interrupt the workflow to ask again.
- Select monitoring cadence from the request: default immediate reactions and urgent mentions to
wait_seconds: 2, never silently substituting a 15-second cadence for “as soon as.” - If the link is missing, ask for it. If timing is ambiguous, ask only now versus specified time. If “my name” is not resolvable from authorized request/context/profile data, ask for name/phrases and optional variants.
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.
- 6d ago First seen · 462 lines · 80 tokens per session scan A d4bf038e4302
telnyx-meeting-bot is a skill published in the GitHub repository team-telnyx/ai (213 stars, last pushed yesterday), licensed MIT. It adds 80 tokens to every session and 6,848 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 2026-09-05.
Other skills, from other repositories
peek
Use when the user mentions a recent browser session, an error they just reproduced, "what was the user doing before X", DOM state at some past moment, or wants to turn a manual repro into a Playwright test. Peek exposes 18 MCP tools backed by a local SQLite store of rrweb-captured browser sessions.
playwright-recording
Record browser interactions as video using Playwright. Use for capturing demo videos, app walkthroughs, and UI flows for Remotion videos. Triggers include recording a demo, capturing browser video, screen recording a website, or creating walkthrough footage.
dev-browser
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website"…
tavily-usage
This skill should be used when user asks to "search the web", "fetch content from URL", "extract page content", "use Tavily search", "scrape this website", "get information from this link", or "web search for X".
Dead Link Detector
Automated detection and reporting of broken links, missing resources, and orphaned pages across web applications using crawl-based and DOM-based strategies.
Karma Testing
Comprehensive Karma test runner skill for browser-based JavaScript unit testing with Jasmine, Mocha, or QUnit frameworks, real browser execution, coverage reporting, and CI/CD pipeline integration.