FounderOS: Command for Claude Code

.claude/commands/pre-meeting.md

pre-meeting is a command for Claude Code from ARCASSystems/FounderOS. It costs 39 tokens per session (811 once invoked), scanned A, original, MIT.

A meeting preparation command that requires you to name a tangible meeting outcome and a specific request before the meeting starts.

In plain words
What is it for?
Use it before calls to decide what should come out of the meeting, such as a transcript, signed agreement, recorded decision, or proposal, and what you will ask the other person to do.
Why use it?
It prevents meetings from beginning without a clear purpose or a defined result. Vague goals such as “stay in touch” are rejected.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

This is ARCASSystems/FounderOS's own configuration. It tells Claude Code how to work on FounderOS itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything FounderOS configures →

Part of the founder-os plugin — 95 skills, 45 commands, 6 hooks shipped together

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/ARCASSystems/FounderOS/main/.claude/commands/pre-meeting.md
Clone the repo
git clone --depth 1 https://github.com/ARCASSystems/FounderOS

Made for: Claude Code.

Or install founder-os, the plugin that ships this one along with the rest of its 95 skills, 45 commands, 6 hooks.

Wrote 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.

agentmods badge for pre-meeting

README.md
[![agentmods](https://agentmods.dev/badge/commands/arcassystems/founderos/pre-meeting.svg)](https://agentmods.dev/commands/arcassystems/founderos/pre-meeting)
Your own site
<a href="https://agentmods.dev/commands/arcassystems/founderos/pre-meeting"><img src="https://agentmods.dev/badge/commands/arcassystems/founderos/pre-meeting.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 811 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00039 $0.00811
Opus 5 $0.00019 $0.00405
Sonnet 5 $0.00008 $0.00162
Haiku 4.5 $0.00004 $0.00081

Measured 6d ago against content hash 5e54ad514746, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

pre-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.

.claude/commands/pre-meeting.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pre-meeting gate

You are enforcing a hard gate. Meetings leak value when no capture artifact and no ask are declared up front. This command blocks the meeting from starting until both are named.

The argument passed is the person or meeting name: $ARGUMENTS.

Procedure (mandatory, in order)

  1. If $ARGUMENTS is empty, reply exactly: Who is the meeting with? Re-run as /pre-meeting <person>. and stop.

  2. Ask the founder these two questions as a single message, numbered, nothing else:

    Gate before this meeting. Two answers required.
    
    1. Capture artifact - what tangible thing leaves this meeting? (transcript, signed NDA, logged row in clients.md, proposal sent, scoped brief, specific decision recorded)
    2. Ask - what are you asking them for? (intro, signature, commitment, referral, paid engagement, answer to a specific question)
    
    No vague answers. "Stay in touch" and "see where it goes" are not artifacts or asks.
    
  3. Wait for the reply. Parse the two answers.

  4. If either answer is missing, empty, or falls into the vague-answer list ("stay in touch", "see where it goes", "build rapport", "catch up", "keep warm", "get to know them"), refuse. Reply:

    Rejected. That is not an artifact / that is not an ask. Re-answer both questions. Binary: answer or cancel the meeting.
    

    Then re-present the two questions. Loop until both answers are concrete. Do not proceed otherwise.

  5. Once both answers are concrete, apply the private-tag filter then write: scan the answers for <private>...</private> blocks (case-insensitive). Remove every matched block (including the tags) from the text before writing. If the entire input is wrapped in <private>, write nothing and report "skipped - content was tagged private." Then append this exact block to brain/log.md (use the Edit or Write tool - read the file first, then append at the end). Use the current real date and time. If brain/log.md does not exist, create it.

Read the full file on GitHub · 63 lines

Changes

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.

  1. 6d ago First seen · 63 lines · 39 tokens per session scan A 5e54ad514746

Subscribe to this mod's changes

pre-meeting is a command published in the GitHub repository ARCASSystems/FounderOS (5 stars, last pushed 22d ago), licensed MIT. It adds 39 tokens to every session and 811 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 2026-08-31.