learn

learn is a skill for Claude Code, Codex from automagik-dev/genie. It costs 23 tokens per session (669 once invoked), scanned A, original, MIT.

An interactive procedure for recording a user’s correction to an agent’s behavior. It identifies whether the rule belongs in project instructions, memory, or another configuration surface, then proposes one small change.

In plain words
What is it for?
It is for diagnosing repeated or important agent mistakes, updating the appropriate project guidance after approval, and recording the lesson for later sessions.
Why use it?
It helps prevent the same mistake from happening again by turning a correction into a persistent, targeted rule.

Skill for Claude CodeCodex

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/automagik-dev/genie/learn
Any agent
npx skills add automagik-dev/genie --skill learn
Clone the repo
git clone --depth 1 https://github.com/automagik-dev/genie

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.

agentmods badge for learn

README.md
[![agentmods](https://agentmods.dev/badge/skills/automagik-dev/genie/learn.svg)](https://agentmods.dev/skills/automagik-dev/genie/learn)
Your own site
<a href="https://agentmods.dev/skills/automagik-dev/genie/learn"><img src="https://agentmods.dev/badge/skills/automagik-dev/genie/learn.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 669 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 $0.00023 $0.00669
Opus 5 $0.00012 $0.00334
Sonnet 5 $0.00005 $0.00134
Haiku 4.5 $0.00002 $0.00067

Measured 4d ago against content hash 09c159e27b92, 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 4d 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.

.genie/attic/skills/learn/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/learn — Behavioral Correction

When the user corrects a mistake, diagnose which behavioral surface caused it and apply one minimal, targeted fix. Interactive — runs in the foreground with the user.

When to Use

  • User corrects behavior ("no, don't do that", "you should always...") or a mistake must never recur
  • A pattern of repeated errors suggests a missing rule

Flow

  1. Diagnose before changing anything. Read the conversation, recent changes, and relevant config to establish what went wrong and why — missing rule, stale convention, or wrong default. Name the responsible surface. If the diagnosis is ambiguous, report what you verified and ask — never guess a surface.
  2. Propose the minimal fix in plan mode: exactly which file changes, the content, and the rationale. One learning = one surface = one change; never batch.
  3. Apply after approval, then confirm what was learned.
  4. Persist to memory: write a feedback memory (format below) and add it to the .claude/memory/MEMORY.md index so the learning survives across sessions.

Writable Surfaces

Surface Path Controls
Project conventions CLAUDE.md Commands, gotchas, coding rules
Agent identity AGENTS.md Role, preferences, team behavior
Personality SOUL.md / IDENTITY.md Tone, communication style
Global rules ~/.claude/rules/*.md Cross-project behavior
Native memory .claude/memory/ Feedback, user prefs, project context
Project memory memory/ Project-scoped knowledge
Hooks .claude/settings.json Event-driven automation, gates

Never Touch

  • Framework files — the installed genie plugin's skills/ and agents/
  • Other projects' files — scope is the current project only
  • Source code — learn changes behavior configuration, never implementation

Memory Format

.claude/memory/<name>.md:

---
name: <concise-name>
description: <one line for relevance matching>
type: feedback
---

<The rule itself>
**Why:** <the incident or reason the user gave>
**How to apply:** <when/where this guidance kicks in>

Read the full file on GitHub · 62 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. 4d ago First seen · 62 lines · 23 tokens per session scan A 09c159e27b92

Subscribe to this mod's changes

learn is a skill published in the GitHub repository automagik-dev/genie (334 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 669 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 2026-08-30.