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 skills add X-School-Academy/skill-pilot --skill user-preferencesgit clone --depth 1 https://github.com/X-School-Academy/skill-pilotWrote 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/skills/x-school-academy/skill-pilot/user-preferences)<a href="https://agentmods.dev/skills/x-school-academy/skill-pilot/user-preferences"><img src="https://agentmods.dev/badge/skills/x-school-academy/skill-pilot/user-preferences/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/x-school-academy/skill-pilot/user-preferences"><img src="https://agentmods.dev/badge/skills/x-school-academy/skill-pilot/user-preferences.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00058 | $0.00854 |
| Opus 5.5 | $0.00023 | $0.00342 |
| Sonnet 5.5 | $0.00012 | $0.00171 |
| Haiku 4.5 | $0.00006 | $0.00085 |
Grade A, and why
user-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 16d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Builder - User Preferences
Capture user corrections and turn them into persistent working rules for future tasks.
When to Use This Skill
- The user corrects a previous action
- The user says "please use X", "do not use Y", or "next time do Z"
- The user says to do something this way in the future
- The user rejects a tool choice and specifies the preferred one
- The user adds a standing workflow rule that should be remembered
Your Roles in This Skill
- Project Manager: Identify whether the user statement is a durable preference or a one-off request
- Backend Developer: Update the persistent preference record accurately and minimally
- Technical Writer: Rewrite the preference into a short, reusable rule without losing meaning
Role Communication
As an expert in your assigned roles, you must announce your actions before performing them using the following format:
As a {Role} [and {Role}, ...], I will {action description}
This communication pattern ensures transparency and allows for human-in-the-loop oversight at key decision points.
Instructions
Follow these steps in order.
Step 1: Detect a corrective preference
- Look for user phrases that correct your prior behavior or specify a preferred future behavior
- Treat direct corrections as high priority, including:
- "please use ..."
- "do not use ..."
- "next time ..."
- "in the future, please ..."
- "please do this in the future ..."
- "you should ..."
- "No, use ..."
- If the user is only making a one-time request for the current task and does not imply future reuse, do not record it unless they ask
Step 2: Apply the correction immediately
- Change your current action to follow the user correction in the same turn whenever feasible
- Do not defend the prior choice if the new instruction is valid and lower risk
- If the correction conflicts with safety, sandbox, or project constraints, explain the constraint and record the preference with that limitation
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.
- 16d ago First seen · 101 lines · 58 tokens per session scan A 31bba40df83b
user-preferences is a skill published in the GitHub repository X-School-Academy/skill-pilot (20 stars, last pushed 4mo ago), licensed MIT. It adds 58 tokens to every session and 854 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-02.
Other skills, from other repositories
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.