Starlight-Intelligence-System: Command for Claude Code

.claude/commands/define-vision.md

define-vision is a command for Claude Code from frankxai/Starlight-Intelligence-System. It costs 51 tokens per session (1,821 once invoked), scanned A, original, MIT.

A long-range map of a person's direction across 30-year, 10-year, 3-year, annual, and quarterly horizons. It creates a named record for each horizon and tests whether current choices stay aligned.

In plain words
What is it for?
Use it to clarify a person's long-term vision and turn it into practical planning checkpoints. It requires an existing Genius Profile and is intended for people, not software agents.
Why use it?
It helps connect short-term decisions with a larger direction instead of planning each period in isolation. It also identifies when day-to-day work has started to drift.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is frankxai/Starlight-Intelligence-System's own configuration. It tells Claude Code how to work on Starlight-Intelligence-System 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 Starlight-Intelligence-System configures →

Part of the starlight-intelligence-system plugin — 5 skills, 121 commands, 7 agents shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to frankxai/Starlight-Intelligence-System. 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/frankxai/Starlight-Intelligence-System/main/.claude/commands/define-vision.md
Clone the repo
git clone --depth 1 https://github.com/frankxai/Starlight-Intelligence-System

Made for: Claude Code.

Or install starlight-intelligence-system, the plugin that ships this one along with the rest of its 5 skills, 121 commands, 7 agents.

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 define-vision

README.md
[![agentmods](https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/define-vision.svg)](https://agentmods.dev/commands/frankxai/starlight-intelligence-system/define-vision)
Your own site
<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/define-vision"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/define-vision.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,821 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00051 $0.01821
Opus 5 $0.00026 $0.00911
Sonnet 5 $0.00010 $0.00364
Haiku 4.5 $0.00005 $0.00182

Measured 6d ago against content hash acc681cbffaf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

define-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 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/define-vision.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/define-vision

Load SIP.md, VOICES.md, agents/starlight-visionary.md, skills/vision/fundamentals-excavation.md. Excavate the person's vision across five horizons. Produce the Vision Architecture. Hand off to exactly one downstream command.

Input

$ARGUMENTS

When this command fires

  • A Genius Profile exists for the person at genius/profile-<slug>.md
  • The person is ready to name the axis their decisions rotate around
  • Brand work is needed downstream, but brand without vision is fantasy — vision is the gate

When this command does NOT fire

  • No Genius Profile → halt and route to /discover-genius
  • Single-decision support → use /navigate instead
  • The person explicitly wants quarterly-only planning → honor sovereignty, skip the upper horizons, note that future brand work will need the upper horizons later

Process

  1. Ground in genius.

    • Resolve <person-slug> from <person-name> (lowercase, hyphenated).
    • Load genius/profile-<slug>.md and genius/freedom-path-<slug>.md.
    • If not present, halt:

    "Before we name where you're going, we name what only you uniquely see. Run /discover-genius first — vision without genius is fantasy."

  2. 30-year horizon excavation. Ask once, precisely:

    "In 30 years — you're 60, 70, 80, whatever age that is for you — what world do you want to exist because you lived? Not your company's world. Not the market's world. The world."

    Wait. Do not fabricate. If the person cannot answer, note the blank and continue. Do not return a Vision Architecture with a fabricated 30-year.

  3. 10-year horizon. Ask:

    "Ten years from now — if that 30-year world is becoming real — what does your life look like? Where do you live, what are you working on, who's around you, what's the weekly shape of your time?"

    Capture: location, primary work, team shape, audience shape, revenue shape, personal-life shape. Produce a one-page "life snapshot."

  4. 3-year horizon. Ask:

    "Three years from now — what must be true for you to still be on that 10-year arc? What's shipped, what's running, what's behind you?"

Read the full file on GitHub · 151 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 · 151 lines · 51 tokens per session scan A acc681cbffaf

Subscribe to this mod's changes

define-vision is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 1,821 once invoked, about $0.0003 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.