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.
npx agentmods add commands/krishagel/geoffrey/preferencesgit clone --depth 1 https://github.com/krishagel/geoffreyWrote 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/krishagel/geoffrey/preferences)<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>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 | $0.00008 | $0.00914 |
| Opus 5 | $0.00004 | $0.00457 |
| Sonnet 5 | $0.00002 | $0.00183 |
| Haiku 4.5 | $0.00001 | $0.00091 |
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.
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:
-
Teach Geoffrey something new:
"I prefer window seats on flights, not aisle" -
Update existing preferences:
"Actually, I prefer Hilton over Marriott now" -
Delete preferences:
"Forget my airline preferences" -
Ask questions:
"Why do you think I prefer morning flights?" "How confident are you about my hotel preferences?"
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.
- 3d ago First seen · 154 lines · 8 tokens per session scan A a4d0e3094d81
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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.