A memory tool for saving coding preferences and project rules in files that different coding assistants can use. It supports project, project-local, and personal settings.

Use it when someone asks the assistant to remember a convention, preference, or project rule, and when deciding where that rule should be stored.

It prevents users from repeating the same instructions and keeps shared rules separate from personal or machine-specific preferences.

learn — Skill for Claude Code and Codex by gullitmiranda: A memory tool for saving coding preferences and project…

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/gullitmiranda/.cursor/learn

Any agent

npx skills add gullitmiranda/.cursor --skill learn

Clone the repo

git clone --depth 1 https://github.com/gullitmiranda/.cursor

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/gullitmiranda/.cursor/learn.svg)](https://agentmods.dev/skills/gullitmiranda/.cursor/learn)

Your own site

<a href="https://agentmods.dev/skills/gullitmiranda/.cursor/learn"><img src="https://agentmods.dev/badge/skills/gullitmiranda/.cursor/learn.svg" alt="Measured on agentmods" height="20"></a>

Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 952 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.

Model	Per session	Once invoked
Fable 5.1	$0.00039	$0.00952
Opus 5	$0.00019	$0.00476
Sonnet 5	$0.00008	$0.00190
Haiku 4.5	$0.00004	$0.00095

Measured 5d ago against content hash b15207bb3e07, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 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/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Learn (Tool-Agnostic Memory)

Persist "learned" instructions so they work across agentic coding tools, not just Cursor.

Principles:

Default scope is PROJECT (shared, version-controlled) for repo conventions.
Use USER when the instruction is clearly a personal preference about the assistant's behavior (even if the user did not explicitly write scope=user:).
Keep everything ASCII; avoid invisible Unicode.
Never update git config.

Explicit syntax (preferred when you care about scope)

Support these optional prefixes in the user's /learn text:

scope=user: <rule>
scope=project: <rule>
scope=project-local: <rule>
applies-to=<path-or-glob>: <rule> (can be combined, e.g. scope=project applies-to=backend/: ...)

Targets by scope

scope = project:

./AGENTS.md (create if missing)
Ensure Claude compatibility shim: ./.claude/CLAUDE.md (create if missing)

scope = project-local:

./AGENTS.local.md (create if missing)
Must not be committed:
- Add AGENTS.local.md to the user's global gitignore (core.excludesfile or default file)
- Optionally add to repo .gitignore if appropriate

scope = user (until ~/.claude is configured):

Persist in user-level Cursor config:
- ~/.cursor/skills/user-preferences/SKILL.md under ## Learned preferences

File templates (when creating new files)

AGENTS.md:

# AGENTS

## Always apply (project)

## Contextual (project)

AGENTS.local.md:

# AGENTS (local)

## Always apply (project-local)

## Contextual (project-local)

.claude/CLAUDE.md (shim):

# Claude instructions

Read and follow `AGENTS.md` as the canonical project rules.

If `AGENTS.local.md` exists, treat it as personal (project-local) preferences.

Workflow

Parse the instruction into:

rule: one bullet, imperative, concise
appliesTo (optional): repo path or glob pattern (only when explicitly specified)
scope: default to project

Decide scope:

Read the full file on GitHub · 123 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.

5d ago First seen · 123 lines · 39 tokens per session scan A b15207bb3e07

Subscribe to this mod's changes

learn is a skill published in the GitHub repository gullitmiranda/.cursor (2 stars, last pushed 6mo ago), licensed MIT. It adds 39 tokens to every session and 952 once invoked, about $0.0002 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.

Memory and context

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

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…

danielmiessler/LifeOS · 196 tokens

agent-memory

../../../engineering/agent-memory/skills/agent-memory/SKILL.md.

alirezarezvani/claude-skills · 0 tokens

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.

opensquilla/opensquilla · 44 tokens

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…

shiwenwen/hope-agent · 115 tokens