learner

A workflow for extracting reusable coding patterns and project conventions from a session and saving them as rule files.

In plain words
What is it for?
Use it after discovering a project convention, solving a recurring problem, or deciding that a coding or debugging pattern should be reused.
Why use it?
It turns lessons learned during development into written guidance that can prevent the same mistakes later.

Cursor rule

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 rules/dasomel/oh-my-cursor/learner
Clone the repo
git clone --depth 1 https://github.com/dasomel/oh-my-cursor
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 642 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 $0.00013 $0.00642
Opus 5 $0.00006 $0.00321
Sonnet 5 $0.00003 $0.00128
Haiku 4.5 $0.00001 $0.00064

Measured yesterday against content hash 6c5fc5e7cb16, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

learner 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 yesterday.

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.

rules/workflows/learner.mdc · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Learner Workflow

The Learner extracts reusable patterns, conventions, and lessons from the current session and saves them as .mdc rule files or updates existing ones.

Triggers

  • "learn this", "save this pattern", "remember this", "extract rule"

When to Use

  • After discovering a project convention
  • After solving a recurring problem
  • After the user corrects a pattern multiple times
  • When a debugging technique proves effective
  • When a coding pattern should be consistently applied

Protocol

Step 1: Identify the Pattern

Ask yourself:
1. What did I learn that applies beyond this specific task?
2. Is this a project convention, a general practice, or a debugging technique?
3. Would this prevent future mistakes if codified?
4. Is it specific enough to be actionable?

Step 2: Classify the Pattern

Type Directory Example
Coding convention rules/practices/ "Always use named exports"
Agent behavior rules/agents/ "Always check for null before accessing nested properties"
Workflow improvement rules/workflows/ "Run lint before commit"
Project-specific .cursor/rules/ "Use camelCase for API endpoints in this project"

Step 3: Create or Update Rule

For new rules:

Create a .mdc file with proper frontmatter:

---
description: "Concise description of what this rule enforces"
alwaysApply: false  # or true for universal rules
globs:              # optional: auto-attach for matching files
  - "**/*.ts"
---
For existing rules:

Read the existing rule, then append the new pattern to the appropriate section.

Step 4: Validate

1. Read the created/updated rule file
2. Verify it's well-formed YAML frontmatter + Markdown
3. Check it doesn't conflict with existing rules
4. Confirm with user: "Saved pattern: {description}. Applied to: {scope}"

Output Format

## Learned Pattern

**Pattern**: {what was learned}
**Source**: {what triggered the learning — user correction, repeated issue, etc.}
**Saved to**: {file path}
**Scope**: {when this rule activates}
**Conflicts**: {none | list of potential conflicts with existing rules}

Read the full file on GitHub · 83 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. yesterday First seen · 83 lines · 13 tokens per session scan A 6c5fc5e7cb16

Subscribe to this mod's changes

learner is a cursor rule published in the GitHub repository dasomel/oh-my-cursor (2 stars, last pushed 5mo ago), licensed MIT. It adds 13 tokens to every session and 642 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 2026-08-31.