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 agentmods add skills/mathematic-inc/earl/recall_ainpx skills add mathematic-inc/earl --skill recall_aigit clone --depth 1 https://github.com/mathematic-inc/earlWrote 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/mathematic-inc/earl/recall_ai)<a href="https://agentmods.dev/skills/mathematic-inc/earl/recall_ai"><img src="https://agentmods.dev/badge/skills/mathematic-inc/earl/recall_ai.svg" alt="Measured on agentmods" 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 | $0.00043 | $0.01613 |
| Opus 5 | $0.00022 | $0.00807 |
| Sonnet 5 | $0.00009 | $0.00323 |
| Haiku 4.5 | $0.00004 | $0.00161 |
Grade A, and why
recall_ai 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 5d 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recall.ai
Records video meetings (Zoom, Google Meet, Teams, Webex, GoToMeeting), generates speaker-attributed transcripts, and produces downloadable audio/video files.
Status Reference
Bot lifecycle status (from get_bot):
| Status | Meaning |
|---|---|
pending |
Bot created, not yet attempting to join |
joining |
Bot is connecting to the meeting |
joined |
Bot is in the meeting, recording NOT started |
recording |
Bot is actively recording |
stopped |
Recording stopped, processing in progress |
done |
Bot left and all processing complete |
Artifact status (media_shortcuts.*.status.code):
| Status | Meaning |
|---|---|
waiting |
Not started |
processing |
Being generated |
done |
Ready to retrieve |
failed |
Generation failed — retry or contact support |
deleted |
Artifact was removed |
CRITICAL: Async Lifecycle
Creating a bot does NOT start recording. The full sequence is async:
create_bot → [wait: pending→joining→joined] → start_recording → [meeting runs] → leave_call/stop_recording → [wait: processing] → get_transcript → download_transcript
Do NOT call get_transcript immediately after create_bot. You will get an error or empty data. Always poll first.
Polling intervals:
- While status is
pendingorjoining: every 10–15 seconds (max 2 minutes — if longer, the meeting URL may be invalid or the meeting hasn't started) - While status is
recording: every 30 seconds - After
stop_recordingorleave_call, while transcript isprocessing: every 15 seconds
Recipe A: Record a meeting and get the transcript
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.
- 5d ago First seen · 174 lines · 43 tokens per session scan A 284f6cebd224
recall_ai is a skill published in the GitHub repository mathematic-inc/earl (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 43 tokens to every session and 1,613 once invoked, about $0.0002 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
box
Box manages cloud files, sharing, search, and metadata.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
gog-drive
Google Drive operations through gog.
gog-save-attachments
Gmail attachment download and Google Drive archival with gog.
recipe-save-email-attachments
Find Gmail messages with attachments and save them to a Google Drive folder.