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 pattern-ai-labs/built-with-agentcall --skill meeting-presentergit clone --depth 1 https://github.com/pattern-ai-labs/built-with-agentcallWrote 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/pattern-ai-labs/built-with-agentcall/meeting-presenter)<a href="https://agentmods.dev/skills/pattern-ai-labs/built-with-agentcall/meeting-presenter"><img src="https://agentmods.dev/badge/skills/pattern-ai-labs/built-with-agentcall/meeting-presenter/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/pattern-ai-labs/built-with-agentcall/meeting-presenter"><img src="https://agentmods.dev/badge/skills/pattern-ai-labs/built-with-agentcall/meeting-presenter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00113 | $0.06949 |
| Opus 5 | $0.00056 | $0.03474 |
| Sonnet 5 | $0.00023 | $0.01390 |
| Haiku 4.5 | $0.00011 | $0.00695 |
Grade A, and why
meeting-presenter 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 — 372 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Presenter — present a document (or a topic) in a meeting
An AI bot joins a meeting and presents: by default the deck goes big on the meeting's main stage
as a screenshare, narrated in the bot's voice and advancing by itself, with the bot's face in a small
camera tile. (Pass --avatar-mode — or if the user says "join in avatar mode" — to instead show the
deck on the camera tile, the original single-tile look.) No clicker either way.
Display modes: screenshare is the default (readable full-stage slides + a presenter face);
avatar mode (--avatar-mode) puts the deck on the camera tile only. Everything else — voice control,
the companion remote, narration, Q&A — works identically in both.
The headline use: the user gives a meeting link and a document — PDF, PowerPoint, or Word — and the bot presents it. You can also start from just a topic.
Do this in order (the whole flow — same every time, no detours)
Before anything — you need something to present. Never join a meeting empty. If the user named
no document, no topic, and no existing deck, do NOT launch. First offer what's already in decks/
(list those decks by title), or ask what topic to build one from (you can author a deck from just a
topic — see B). Only move on once you have material in hand. A quick "what should I present?" beats a
bot that joins with nothing to say. (Suggesting the user's existing decks/ and offering to build from
a topic is the standard no-material flow — do it for every user, not just when you happen to know their
decks.)
0 · Preflight (once).
- API key — check in this order, and DON'T ask if it's already there (one config, the SAME file
AgentCall uses; this is the exact order
load_api_keyuses):~/.agentcall/config.jsonexists with anapi_key? → ready.AGENTCALL_API_KEYenv var set? → ready.- Neither? → ask the user for their key (free at agentcall.dev/api-keys) and write it to
~/.agentcall/config.json(see Setup) — creating that file exactly like AgentCall would — then continue.
- Dependencies —
pip install -r requirements.txt(fast; pure-Python wheels, no system tools).
What ships with it
15 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.
- .gitignore 173 B
- assets/agentcall-audio.js 16 KB runs code
- assets/avatar.html 11 KB
- assets/control.html 15 KB
- assets/in-meeting.png 53 KB
- assets/presenter-bot.gif 1489 KB
- assets/remote.png 110 KB
- assets/slides.html 15 KB
- decks/sample.json 2.0 KB
- engine/bridge-visual.py 78 KB runs code
- LICENSE 1.0 KB
- README.md 10 KB
- requirements.txt 1.0 KB
- scripts/doc_to_deck.py 26 KB runs code
- scripts/present.py 69 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 · 372 lines · 113 tokens per session scan A 49aa53add2a6
meeting-presenter is a skill published in the GitHub repository pattern-ai-labs/built-with-agentcall (12 stars, last pushed 1mo ago), licensed MIT. It adds 113 tokens to every session and 6,949 once invoked, about $0.0006 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
seedance-examples-ja
This skill should be used when the user asks for Japanese Seedance 2.0 examples, Japanese prompt patterns, example rewrites, or safe versions of working Japanese video-generation prompts.
seedance-examples-ko
This skill should be used when the user asks for Korean Seedance 2.0 examples, Korean prompt patterns, example rewrites, or safe versions of working Korean video-generation prompts.
seedance-examples-zh
This skill should be used when the user asks for Chinese Seedance 2.0 examples, Chinese prompt patterns, example rewrites, or safe versions of working Chinese video-generation prompts.
seedance-examples-ja
This skill should be used when the user asks for Japanese Seedance 2.0 examples, Japanese prompt patterns, example rewrites, or safe versions of working Japanese video-generation prompts.
image-gen-skill
An AI image-generation skill for creating new pictures from written descriptions, including product images, illustrations, and different art styles.
image-edit-skill
An AI image-editing skill for changing an existing picture, such as replacing its background, changing its style, adding content, or extending the scene.