learn

learn is a command for coding agents from gullitmiranda/.cursor. It costs 15 tokens per session (276 once invoked), scanned A, original, MIT.

A command for saving rules learned from the user in project files or user preferences.

In plain words
What is it for?
Use it to record conventions such as which package manager to use, when to run tests, or whether to ask before committing.
Why use it?
It prevents useful instructions from being forgotten and lets them apply to the project or to the user's other work, as appropriate.

Command

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 commands/gullitmiranda/.cursor/learn
Clone the repo
git clone --depth 1 https://github.com/gullitmiranda/.cursor

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/gullitmiranda/.cursor/learn.svg)](https://agentmods.dev/commands/gullitmiranda/.cursor/learn)
Your own site
<a href="https://agentmods.dev/commands/gullitmiranda/.cursor/learn"><img src="https://agentmods.dev/badge/commands/gullitmiranda/.cursor/learn.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 276 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 $0.00015 $0.00276
Opus 5 $0.00008 $0.00138
Sonnet 5 $0.00003 $0.00055
Haiku 4.5 $0.00002 $0.00028

Measured 3d ago against content hash 4ca4283d3872, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

learn 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.

commands/learn.md · 30 lines

What it actually says

/learn

Persist "learned" instructions in a tool-agnostic way.

Canonical behavior lives in the learn skill:

  • skills/learn/SKILL.md

Usage examples:

  • /learn "In this repo, we use pnpm."
  • /learn "Only for me in this repo: run tests first" (project-local)
  • /learn "For all my projects: ask before commits" (user)
  • /learn "scope=user: only push when explicitly requested" (explicit scope)
  • /learn "Applies to backend/: prefer pytest fixtures" (contextual)

When this command is used:

  • Apply the learn skill workflow.
  • Default scope to project for repo conventions, but prefer scope=user when the text is clearly a personal preference about the assistant's behavior (not a project convention).
    • Examples that should infer scope=user (even without an explicit prefix):
      • "Always respect when I'm told to use a git worktree."
      • "Only push when explicitly requested."
      • "Ask before committing."
      • PT-BR equivalents: "sempre ...", "nunca ...", "nao faça ...", when addressed to the assistant's behavior.
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. 3d ago First seen · 30 lines · 15 tokens per session scan A 4ca4283d3872

Subscribe to this mod's changes

learn is a command published in the GitHub repository gullitmiranda/.cursor (2 stars, last pushed 6mo ago), licensed MIT. It adds 15 tokens to every session and 276 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.