Borrowing it
Nothing to install: this file belongs to ARCASSystems/FounderOS. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ARCASSystems/FounderOS/main/.claude/commands/capture-meeting.mdgit clone --depth 1 https://github.com/ARCASSystems/FounderOSWrote 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/commands/arcassystems/founderos/capture-meeting)<a href="https://agentmods.dev/commands/arcassystems/founderos/capture-meeting"><img src="https://agentmods.dev/badge/commands/arcassystems/founderos/capture-meeting.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 5.1 | $0.00000 | $0.01360 |
| Opus 5 | $0.00000 | $0.00680 |
| Sonnet 5 | $0.00000 | $0.00272 |
| Haiku 4.5 | $0.00000 | $0.00136 |
Grade A, and why
capture-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 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Capture meeting
You just finished a meeting. This command routes the raw input (transcript, file path, or brain dump) into the right Founder OS files so nothing leaks.
Argument: $ARGUMENTS (the person or meeting name).
Procedure (in order)
-
If
$ARGUMENTSis empty, reply:Which meeting? Re-run as /capture-meeting <name>.and stop. -
Ask the founder, as a single message, nothing else:
Capture mode for <name>. Paste one of: - Full transcript text - A file path to a transcript - A brain dump of what happened (voice-to-text is fine) Also tell me: is this person already in context/clients.md? (yes / no / unsure) -
Wait for the reply. Accept any of the three input forms.
-
Read
context/clients.md. If the person exists, note their current row. If not, you will create one.
4.5. Name pass (mandatory on transcript input). Dictation and meeting recorders mangle proper nouns. Before extracting meaning, read context/names.md (the names glossary) if it exists and check every person, company, and product name in the input:
- A name matching a glossary entry or a listed mishearing: use the canonical spelling.
- A name matching nothing: keep it as heard, marked
(sp?), and ask about all unknowns in one batch before writing to any file. Never guess a fuller identity for an unmatched name, and never overwrite an existing person's record on a near-match - a heard name that is close to two known people is a question, not a pick. - Append every correction the founder makes to the glossary's mishearings column. Numbers, prices, and dates you are unsure of stay as captured, marked - never silently "fixed".
- Parse the input for:
- Key decisions made (things settled or ruled out)
- Commitments the founder made (things they owe, verbs like "I'll send / share / do / book")
- Commitments the other party made (things they owe)
- Next step (what happens after this meeting)
- Pain surfaced (what they named as broken)
- Signal quality (did something ICP-worthy surface)
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 · 94 lines · 0 tokens per session scan A b442a3616f72
capture-meeting is a command published in the GitHub repository ARCASSystems/FounderOS (5 stars, last pushed 22d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,360 tokens. 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.
Other commands, from other repositories
voice-sessions
List all voice elicitation interview sessions.
batch
This page documents how the livewiki batch command is registered with the Commander CLI framework and how it formats batch run reports for human consumption.
update_brain
Migra a ESTRUTURA do vault da v1 para a v2 (skills→commands, CLAUDE.md→AGENTS.md) sem perder dados.
handover_chat
Salva o progresso da sessão atual em 07 - HANDOVERS/ ou em uma tarefa T0XX ativa.
handon_chat
Retoma uma tarefa T0XX ou lista handovers ativos.
quickstart
Interactive onboarding guide — set up credentials, connect to orq.ai, and learn every command and skill.