vision

vision is a command for coding agents from Pitchlab/founder-support-system. It costs 16 tokens per session (1,519 once invoked), scanned A, original, MIT.

An interactive guide for creating or updating a clear personal or company vision and manifesto, meaning a statement of beliefs and direction.

In plain words
What is it for?
Use it to explore what you believe, what should remain human-led, what environment you need, and what you want your work to represent, then save the result to Notion.
Why use it?
It helps turn vague ambitions into specific principles and positions that can guide decisions.

Command

Part of the founder-support-system plugin — 6 skills, 10 commands shipped together

Install

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.

agentmods
npx agentmods add commands/pitchlab/founder-support-system/vision
Clone the repo
git clone --depth 1 https://github.com/Pitchlab/founder-support-system

Or install founder-support-system, the plugin that ships this one along with the rest of its 6 skills, 10 commands.

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 vision

README.md
[![agentmods](https://agentmods.dev/badge/commands/pitchlab/founder-support-system/vision.svg)](https://agentmods.dev/commands/pitchlab/founder-support-system/vision)
Your own site
<a href="https://agentmods.dev/commands/pitchlab/founder-support-system/vision"><img src="https://agentmods.dev/badge/commands/pitchlab/founder-support-system/vision.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,519 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 $0.00016 $0.01519
Opus 5 $0.00008 $0.00759
Sonnet 5 $0.00003 $0.00304
Haiku 4.5 $0.00002 $0.00152

Measured 3d ago against content hash 77f45e3114a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vision 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 3d 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.

commands/vision.md · 218 lines

How it starts

The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vision Command

Create a bold, philosophically grounded vision and manifesto that articulates what you stand for.

Push for substance. Reject bland business speak. Build a vision worth defending.

Purpose

This command invokes an interactive vision creation process that:

  • Forces clarity on what you actually believe
  • Pushes back on generic business speak
  • Helps craft a manifesto from the future
  • Saves to Notion Vision page

NOT generic corporate mission statements. NOT ChatGPT business speak. Clarity. Conviction. Edge.

Usage

# Create or update vision
/planning-strategy:vision

How It Works

This command invokes the vision skill, which guides you through:

  1. Provocative Questions (5 foundational questions):

    • Where do humans still matter most when agents become competent?
    • What kind of environment do you need to become dangerously good?
    • What must never be outsourced to machines, even if it could be?
    • What signal do you want people to associate with your name?
    • If you look back in 15 years, what would make this phase feel inevitable?
  2. Challenge the Answers:

    • Push back on generic/vague responses
    • Force specificity and edge
    • Reject business jargon
  3. Extract Core Beliefs & Themes:

    • Distill into 3-5 core beliefs
    • Identify how beliefs manifest daily (mission themes)
    • Define lines in the sand (what you refuse)
  4. Draft the Manifesto:

    • Write from the future ("From here, I can see...")
    • Use "I" not "we" (personal vision)
    • Channel Kevin Kelly / Steve Jobs clarity
    • 600-1000 words of substance
  5. Style Check (5 tests):

    • Competitor test: Could they say this too?
    • Conviction test: Would you defend this?
    • ChatGPT test: Does it sound AI-generated?
    • Bold formatting test: Do words stand alone?
    • One-line test: Can you summarize it?
  6. Refine & Polish:

    • Cut ruthlessly
    • Strengthen claims
    • Check rhythm
    • Make every word count

Read the full file on GitHub · 218 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. 3d ago First seen · 218 lines · 16 tokens per session scan A 77f45e3114a5

Subscribe to this mod's changes

vision is a command published in the GitHub repository Pitchlab/founder-support-system (2 stars, last pushed 8mo ago), licensed MIT. It adds 16 tokens to every session and 1,519 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 2026-08-31.