learn

learn is a command for coding agents from datacore-one/datacore. It costs 4 tokens per session (1,276 once invoked), scanned A, original, MIT.

A command for saving corrections, preferences, decisions, and other reusable knowledge in persistent AI memory. An engram is a stored memory intended to remain available in later sessions.

In plain words
What is it for?
Use it to record coding conventions, user preferences, architectural decisions, corrections, competitive findings, or contact details for future work.
Why use it?
It prevents important context from being lost when a conversation ends or work moves to another project.

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/datacore-one/datacore/learn
Clone the repo
git clone --depth 1 https://github.com/datacore-one/datacore

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/datacore-one/datacore/learn.svg)](https://agentmods.dev/commands/datacore-one/datacore/learn)
Your own site
<a href="https://agentmods.dev/commands/datacore-one/datacore/learn"><img src="https://agentmods.dev/badge/commands/datacore-one/datacore/learn.svg" alt="Measured on agentmods" height="20"></a>
Per session 4 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,276 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 $0.00004 $0.01276
Opus 5 $0.00002 $0.00638
Sonnet 5 $0.00001 $0.00255
Haiku 4.5 $0.00000 $0.00128

Measured today against content hash 4b0032ef7883, 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 today.

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.

.datacore/commands/learn.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/learn

Capture an engram into PLUR memory.

Purpose

/learn is the front door to your persistent AI memory. Use it to record corrections, preferences, decisions, conventions, or any reusable knowledge that should survive across sessions and projects.

This command wraps mcp__plur__plur_learn with sensible defaults so you can capture in one line without thinking about engram metadata.

Note: this is the Datacore /learn command (PLUR-backed). It explicitly supersedes the gstack learn skill. Do not invoke gstack:learn — engrams are the canonical learning artifact in this Datacore installation.

When to use

  • User corrects you ("no, use X not Y") → capture the correction immediately
  • User states a preference ("always do X", "never do Y") → capture
  • You discover a codebase convention or pattern that future sessions should know
  • You make a decision worth preserving (architectural, naming, branding)
  • You want to remember a competitive insight, market datum, or contact detail
  • You realize you got something wrong in this session and want it recorded so you don't repeat it

If unsure whether something is worth saving: it probably is. Engrams are cheap; re-deriving lost context is expensive.

Usage

Quick capture

/learn The current price of X is €Y as of 2026-05-07

The command will:

  1. Call mcp__plur__plur_learn with the statement
  2. Auto-classify type (terminological/behavioral/procedural/architectural) from content
  3. Default scope to global
  4. Return the engram ID

Structured capture

When the user provides additional metadata in natural language, parse it:

/learn [decided] [domain: cos.pricing] €19 entry tier is correct, €200 floor was wrong

Recognized inline modifiers:

  • [exploring] / [leaning] / [decided] / [locked] → commitment level
  • [domain: x.y] → domain tag
  • [scope: project:name] → custom scope
  • [type: behavioral|terminological|procedural|architectural] → explicit type
  • [tags: a,b,c] → searchable tags
  • [derived_from: ENG-id] → link to source engram
  • [pinned] → always-load flag (use sparingly — meta-rules only)

Read the full file on GitHub · 122 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. today First seen · 122 lines · 4 tokens per session scan A 4b0032ef7883

Subscribe to this mod's changes

learn is a command published in the GitHub repository datacore-one/datacore (4 stars, last pushed today), licensed MIT. It adds 4 tokens to every session and 1,276 once invoked, about $0.0000 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 2026-09-03.