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 seameet-ai/seameet-mcp --skill seameetgit clone --depth 1 https://github.com/seameet-ai/seameet-mcpWrote 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/seameet-ai/seameet-mcp/seameet)<a href="https://agentmods.dev/skills/seameet-ai/seameet-mcp/seameet"><img src="https://agentmods.dev/badge/skills/seameet-ai/seameet-mcp/seameet/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/seameet-ai/seameet-mcp/seameet"><img src="https://agentmods.dev/badge/skills/seameet-ai/seameet-mcp/seameet.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 | $0.00061 | $0.01252 |
| Opus 5.5 | $0.00024 | $0.00501 |
| Sonnet 5.5 | $0.00012 | $0.00250 |
| Haiku 4.5 | $0.00006 | $0.00125 |
Grade A, and why
seameet 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 2mo 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SeaMeet workflows
SeaMeet is a desktop meeting recorder + AI note taker. This plugin's MCP
server (seameet, from @seameet/mcp) exposes its tools; the SeaMeet
desktop app must be installed and running on this machine
(download: https://seameet.ai/download/).
0. Check app status first
If any tool returns {"success": false, "error": {"code": "app_not_running"}},
ask the user to launch the SeaMeet desktop app, then retry. When the app is
closed, tools/list exposes only seameet_desktop_app_status — call it for
an actionable status. app_not_ready means the app is still starting: retry
in a few seconds. All tool errors are structured JSON — branch on
error.code (timeout → check seameet_recording_status(), retry once;
not_found → discover files with seameet_list_recordings).
1. Record and transcribe anything
- Pick the source (ask the user or infer):
microphone— voice only (dictation, voice notes)screen— screen video + microphone (demos, walkthroughs)both— screen + mic + system/speaker audio (meetings, webinars)
- Start:
seameet_start_recording(source=...). If it returnsneedsClarification, present the choices to the user. - Monitor:
seameet_recording_status()for elapsed time;seameet_get_live_transcript(lastN=20)to follow along mid-recording. - Stop:
seameet_stop_recording()→ returns the savedfilePath. - Retrieve artifacts (they generate shortly after stop; retry briefly):
seameet_get_artifact(filePath, key="transcription")andseameet_get_artifact(filePath, key="summary"). - Optionally persist your own work:
seameet_save_artifact(filePath, artifactKey="notes", content=..., mimeType="text/markdown", generatedBy="claude").
Notes: only audio-only recordings can be paused
(seameet_pause_recording). Recordings save to
seameet_get_settings().defaultSaveDirectory.
2. Capture a bug report
When the user reports a bug you cannot reproduce, capture ground truth instead of guessing from a text description:
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.
- 2mo ago First seen · 101 lines · 61 tokens per session scan A 0c500a004bfd
seameet is a skill published in the GitHub repository seameet-ai/seameet-mcp (1 stars, last pushed 25d ago), licensed MIT. It adds 61 tokens to every session and 1,252 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.
seameet compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| seameetseameet-ai/seameet-mcp | Skill | 1 | 25d ago | MIT | A | 61 | Claude Code |
| orbit-notionnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 117 | Claude Code, Codex |
| gogopenclaw/openclaw | Skill | 394k | today | MIT | A | 20 | Claude Code, Codex |
| boxNousResearch/hermes-agent | Skill | 262k | today | MIT | A | 14 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | today | MIT | A | 33 | Claude Code, Codex |
| material-organizerOrkas-AI/Orkas | Skill | 9.1k | yesterday | MIT | A | 3 | Claude Code, Codex |
| recipe-save-email-attachmentsgoogleworkspace/cli | Skill | 32k | 5d ago | Apache-2.0 | A | 20 | Claude Code, Codex |