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 commands/railly/agent-brain/meetinggit clone --depth 1 https://github.com/Railly/agent-brainWhat 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 | $0.00011 | $0.00753 |
| Opus 5 | $0.00005 | $0.00377 |
| Sonnet 5 | $0.00002 | $0.00151 |
| Haiku 4.5 | $0.00001 | $0.00075 |
Grade A, and why
meeting 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 2d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Process meeting notes: $ARGUMENTS
IMPORTANT: Be direct
- Don't check if folders exist
- Don't search existing notes
- Just create and append
Step 0: Transcribe (if audio/video input)
If the user provides an audio or video file (.mp3, .mp4, .wav, .m4a, .webm, .ogg) or a URL (YouTube, Google Meet recording, etc.), transcribe it first using trx:
trx "$ARGUMENTS" --output json --fields text
This outputs the full transcript as text. Use that as the meeting content for the steps below.
If the user provides text directly, skip this step.
Flow
-
Create meeting note in
03_Garden/meetings/{YYYY-MM-DD}/{slug}.md:--- type: meeting created: {{date}} attendees: - "[[Person 1]]" - "[[Person 2]]" project: --- # {Meeting Title} ## Key Decisions - ## Insights - ## Action Items - [ ] @{person}: {task} ## Notes {summary of discussion} -
Create corrected transcript in
03_Garden/meetings/{YYYY-MM-DD}/{slug}-transcript.md:- Fix common transcription errors (tool names, product names, technical terms)
- Format as dialogue:
**{Person 1}:** .../**{Person 2}:** ... - Keep the natural spoken language as-is
- Add
[Pause],[Screen share],[Laughter]annotations where evident - Frontmatter:
--- type: transcript created: {{date}} meeting: "[[{slug}]]" language: {detected language} coverage: {full (~Xmin) | partial (~Xmin of Ymin)} --- # Transcript: {Title} - {duration} -
Create summary in
03_Garden/meetings/{YYYY-MM-DD}/{slug}-summary.md:- Written in first person reflecting on the conversation
- Structured sections: Context, Key Topics, Learnings, Takeaways
- Frontmatter:
--- type: summary created: {{date}} meeting: "[[{slug}]]" --- -
Create person notes for attendees not yet in
03_Garden/people/
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.
- 2d ago First seen · 103 lines · 11 tokens per session scan A 2be6a48ceda3
meeting is a command published in the GitHub repository Railly/agent-brain (22 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 753 once invoked, about $0.0001 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 commands, from other repositories
stt
Transcribe a local audio file or remote audio URL into text.
audition-voices
Generate voice audition samples for a character using Venice TTS.
status
Show 3d-design team status and recent activity.
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.
develop-image-prompt.eval
Generates a detailed image generation prompt from a document or content description. Good output: a prompt that is specific, visual, non-abstract, includes style/composition/lighting guidance, and is calibrated to the specified dimensions and style options.
frontend-3d
You are an expert in 3D web development using Three.js, React Three Fiber, WebGL, and WebGPU. You create immersive 3D experiences for the web.