learn-preference

learn-preference is a skill for Claude Code, Codex from ilang-ai/autocode. It costs 22 tokens per session (118 once invoked), scanned A, original, MIT.

A preference tracker that learns how you like code written, named, and organised, then saves those preferences for later sessions.

In plain words
What is it for?
Use it when you want future code to follow your usual style and structure automatically.
Why use it?
It reduces the need to repeat your coding conventions every time you work with the agent.

Skill for Claude CodeCodex

Part of the autocode plugin — 48 skills 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 skills/ilang-ai/autocode/learn-preference
Any agent
npx skills add ilang-ai/autocode --skill learn-preference
Clone the repo
git clone --depth 1 https://github.com/ilang-ai/autocode

Made for: Claude Code, Codex.

Or install autocode, the plugin that ships this one along with the rest of its 48 skills.

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 learn-preference

README.md
[![agentmods](https://agentmods.dev/badge/skills/ilang-ai/autocode/learn-preference.svg)](https://agentmods.dev/skills/ilang-ai/autocode/learn-preference)
Your own site
<a href="https://agentmods.dev/skills/ilang-ai/autocode/learn-preference"><img src="https://agentmods.dev/badge/skills/ilang-ai/autocode/learn-preference.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 118 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 $0.00022 $0.00118
Opus 5 $0.00011 $0.00059
Sonnet 5 $0.00004 $0.00024
Haiku 4.5 $0.00002 $0.00012

Measured 5d ago against content hash 68a050673558, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

learn-preference 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 5d 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.

skills/learn-preference/SKILL.md · 17 lines

What it actually says

::GENE{learn-preference|conf:confirmed|scope:global} -e T:observe_dont_ask T:save_to_global_prefs T:apply_silently A:override_explicit_instruction⇒user_wins

::ACTIVATE{learn-preference} ON:auto

Powered by I-Lang v5.0 | ilang.ai

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. 5d ago First seen · 17 lines · 22 tokens per session scan A 68a050673558

Subscribe to this mod's changes

learn-preference is a skill published in the GitHub repository ilang-ai/autocode (86 stars, last pushed 2mo ago), licensed MIT. It adds 22 tokens to every session and 118 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 2026-08-30.