learn-preferences

learn-preferences is a skill for Claude Code from mocraimer/mo-cc-plugins. It costs 58 tokens per session (1,428 once invoked), scanned A, original, MIT.

A preference-tracking agent that reviews task-planning files and discovery logs to find recurring patterns in how you work.

In plain words
What is it for?
Use it during recurring runs to identify repeated preferences and suggest updates to CLAUDE.md after they appear across multiple sessions.
Why use it?
It reduces the need to restate stable workflow preferences while keeping changes to CLAUDE.md under your control.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; mentions CLAUDE.md; names the AskUserQuestion tool.

Part of the loop-recipes plugin — 11 skills shipped together

Good fit Use it during recurring runs to identify repeated preferences and suggest updates to CLAUDE.md after they appear across multiple sessions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mocraimer/mo-cc-plugins/learn-preferences
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.

Any agent
npx skills add mocraimer/mo-cc-plugins --skill learn-preferences
Clone the repo
git clone --depth 1 https://github.com/mocraimer/mo-cc-plugins

Made for: Claude Code.

Or install loop-recipes, the plugin that ships this one along with the rest of its 11 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-preferences

README.md
[![agentmods](https://agentmods.dev/badge/skills/mocraimer/mo-cc-plugins/learn-preferences/github.svg)](https://agentmods.dev/skills/mocraimer/mo-cc-plugins/learn-preferences)
Your own site
<a href="https://agentmods.dev/skills/mocraimer/mo-cc-plugins/learn-preferences"><img src="https://agentmods.dev/badge/skills/mocraimer/mo-cc-plugins/learn-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.

agentmods 80×15 button for learn-preferences

Your own site · 80×15
<a href="https://agentmods.dev/skills/mocraimer/mo-cc-plugins/learn-preferences"><img src="https://agentmods.dev/badge/skills/mocraimer/mo-cc-plugins/learn-preferences.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,428 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 $0.00058 $0.01428
Opus 5.5 $0.00023 $0.00571
Sonnet 5.5 $0.00012 $0.00286
Haiku 4.5 $0.00006 $0.00143

Measured 2mo ago against content hash c73aea1b1a9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

learn-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 2mo 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.

plugins/loop-recipes/skills/learn-preferences/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Manifest Preference Learner

You are a preference learning agent running as a recurring /loop iteration. Your job: read recent /define manifests and discovery logs, extract patterns in user preferences, track candidates across sessions, and suggest CLAUDE.md updates for confirmed patterns. You NEVER modify CLAUDE.md without explicit user approval.

State Management

State file: ~/.claude/loop-recipes/preference-candidates.md (persistent across sessions)

On Start — Read State

  1. Read ~/.claude/loop-recipes/preference-candidates.md. If it does not exist, initialize:

    ---
    status: idle
    last_scan: "1970-01-01T00:00:00Z"
    total_patterns_found: 0
    total_patterns_promoted: 0
    ---
    # Candidate Patterns
    
    ## Candidates (seen once — need confirmation)
    
    ## Confirmed (seen 2+ sessions — eligible for CLAUDE.md)
    
    ## Applied (already written to CLAUDE.md)
    
  2. If status: in-progress with a locked_by field set:

    • If locked_by timestamp is less than 2 hours old: a previous iteration is still running. Output "Previous iteration still running — skipping." and stop.
    • If locked_by is older than 2 hours: treat as stale lock (previous iteration likely crashed), clear it, and proceed.
  3. Set locked_by: <current_timestamp> and status: in-progress.

  4. Ensure ~/.claude/loop-recipes/ directory exists (mkdir -p).

On End — Write State

After every iteration:

  • Clear locked_by, set status: idle
  • Update last_scan to current timestamp
  • Update pattern counts
  • Preserve all existing candidates, confirmed, and applied entries

Iteration Logic

Step 1: Find Recent Manifests and Logs

Search for manifests and discovery logs. Note: these files live in /tmp and are ephemeral (lost on reboot).

find /tmp -name "manifest-*.md" -mtime -1 2>/dev/null
find /tmp -name "define-discovery-*.md" -mtime -1 2>/dev/null

If no files found: output "No recent manifests or discovery logs." Stop.

Read each file found.

Read the full file on GitHub · 139 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. 2mo ago First seen · 139 lines · 58 tokens per session scan A c73aea1b1a9f

Subscribe to this mod's changes

learn-preferences is a skill published in the GitHub repository mocraimer/mo-cc-plugins (2 stars, last pushed 7mo ago), licensed MIT. It adds 58 tokens to every session and 1,428 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 2026-08-31.

Related

learn-preferences compared with skills from other repositories

learn-preferences next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
learn-preferencesmocraimer/mo-cc-pluginsSkill27mo agoMITA58Claude Code
knowledge-ingestopenclaw/openclawSkill394ktodayMITA80Claude Code, Codex
mem0-oss-to-platformmem0ai/mem0Skill69ktodayApache-2.0A217Claude Code, Codex
forgetasgeirtj/system_prompts_leaksSkill71ktodayCC0-1.0A0Claude Code, Codex
Cortexdanielmiessler/LifeOSSkill20kyesterdayMITA184Claude Code
memoryopensquilla/opensquillaSkill7.1k6d agoApache-2.0A44Claude Code, Codex
ha-data-storesshiwenwen/hope-agentSkill1.9ktodayMITA115Claude Code, Codex