preferences

preferences is a command for coding agents from krishagel/geoffrey. It costs 8 tokens per session (914 once invoked), scanned A, original, MIT.

A command for viewing preferences and facts that Geoffrey has learned about you, grouped by category and accompanied by confidence and source information.

In plain words
What is it for?
Use it to inspect all saved preferences or view a category such as travel, work, or communication.
Why use it?
It makes stored personal context visible, so you can check what the assistant remembers and review where each item came from.

Command

Part of the geoffrey plugin — 33 skills, 2 commands, 7 agents, 4 hooks 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/krishagel/geoffrey/preferences
Clone the repo
git clone --depth 1 https://github.com/krishagel/geoffrey

Or install geoffrey, the plugin that ships this one along with the rest of its 33 skills, 2 commands, 7 agents, 4 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 preferences

README.md
[![agentmods](https://agentmods.dev/badge/commands/krishagel/geoffrey/preferences.svg)](https://agentmods.dev/commands/krishagel/geoffrey/preferences)
Your own site
<a href="https://agentmods.dev/commands/krishagel/geoffrey/preferences"><img src="https://agentmods.dev/badge/commands/krishagel/geoffrey/preferences.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 914 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 $0.00008 $0.00914
Opus 5 $0.00004 $0.00457
Sonnet 5 $0.00002 $0.00183
Haiku 4.5 $0.00001 $0.00091

Measured 3d ago against content hash a4d0e3094d81, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

preferences 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/preferences.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Preferences Command

Read and display all stored preferences from Geoffrey's knowledge base.

What This Command Does

The /preferences command shows you everything Geoffrey has learned about you, including:

  • All stored preferences organized by category
  • Confidence scores for each preference
  • When each preference was learned
  • How each preference was learned (explicit, pattern, conversation)

Location

Preferences are stored in:

~/Library/Mobile Documents/com~apple~CloudDocs/Geoffrey/knowledge/preferences.json

How to Use

View all preferences:

/preferences

Shows all preferences across all categories with confidence scores.

View by category:

/preferences travel
/preferences work
/preferences communication

Shows only preferences in the specified category.

What You'll See

Geoffrey's Knowledge Base
Last updated: 2025-11-17 10:30 AM

Travel Preferences:
  Hotels:
    - Primary chain: Marriott
    - Loyalty tier: Platinum Elite
    - Room preferences: High floor, away from elevator
    - Confidence: 1.0 (explicitly stated)
    - Learned from: explicit:2025-11-17

  Airlines:
    - Primary: Alaska Airlines
    - Seat preference: Aisle
    - Time preference: Morning flights
    - Confidence: 0.8 (strong pattern)
    - Learned from: booking:2025-10-15, booking:2025-09-20

Work Preferences:
  Communication:
    - Email tone: Professional but friendly
    - Confidence: 0.6 (moderate pattern)
    - Learned from: conversation:2025-11-10

Total preferences: 8
High confidence (>0.8): 5
Moderate confidence (0.6-0.8): 2
Low confidence (<0.6): 1

Actions You Can Take

After viewing preferences, you can:

  1. Teach Geoffrey something new:

    "I prefer window seats on flights, not aisle"
    
  2. Update existing preferences:

    "Actually, I prefer Hilton over Marriott now"
    
  3. Delete preferences:

    "Forget my airline preferences"
    
  4. Ask questions:

    "Why do you think I prefer morning flights?"
    "How confident are you about my hotel preferences?"
    

Read the full file on GitHub · 154 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 · 154 lines · 8 tokens per session scan A a4d0e3094d81

Subscribe to this mod's changes

preferences is a command published in the GitHub repository krishagel/geoffrey (5 stars, last pushed 5mo ago), licensed MIT. It adds 8 tokens to every session and 914 once invoked, about $0.0000 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.