learn-new-things

learn-new-things is a skill for Claude Code, Codex from Abilityai/cornelius. It costs 20 tokens per session (4,933 once invoked), scanned A, original, MIT.

A recurring learning workflow that researches new topics, extracts insights, connects them to an existing knowledge base, and saves each session in its own Git branch. Git branches are separate lines of work that keep changes isolated.

In plain words
What is it for?
Use it for ongoing research sessions, storing findings in Document Insights, discovering connections to older notes, and committing each session to a dated learning branch.
Why use it?
It provides a repeatable way to expand a knowledge base while keeping the main version clean. Each learning cycle preserves its work for later review or merging.

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/abilityai/cornelius/learn-new-things
Any agent
npx skills add Abilityai/cornelius --skill learn-new-things
Clone the repo
git clone --depth 1 https://github.com/Abilityai/cornelius

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-new-things

README.md
[![agentmods](https://agentmods.dev/badge/skills/abilityai/cornelius/learn-new-things.svg)](https://agentmods.dev/skills/abilityai/cornelius/learn-new-things)
Your own site
<a href="https://agentmods.dev/skills/abilityai/cornelius/learn-new-things"><img src="https://agentmods.dev/badge/skills/abilityai/cornelius/learn-new-things.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,933 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 $0.00020 $0.04933
Opus 5 $0.00010 $0.02466
Sonnet 5 $0.00004 $0.00987
Haiku 4.5 $0.00002 $0.00493

Measured 4d ago against content hash b5c8e5a8761f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

learn-new-things 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.

.claude/skills/learn-new-things/SKILL.md · 799 lines

How it starts

The opening of the file, as written. The whole thing — 799 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Learn New Things - Continuous Learning Heartbeat

Autonomous learning loop that periodically expands the knowledge base through research, extraction, and connection discovery. Runs locally using existing skills and sub-agents.

Overview

This heartbeat skill implements a continuous learning cycle:

  1. Research - Discover cutting-edge papers and developments
  2. Extract - Pull unique insights into Document Insights
  3. Connect - Map discoveries to existing knowledge base
  4. Commit - Save results to dedicated git branch, return to main
  5. Rest - Wait for next cycle

Each cycle is a complete learning session. The heartbeat never "completes" - it continuously learns.

Git Workflow: Each learning session commits to its own branch (learning/YYYY-MM-DD-topic-slug), then returns to main. This keeps main clean while preserving all learning for selective merging.

Dependencies

  • Skills: /deep-research, /auto-discovery, /integrate-recent-notes, /refresh-index
  • Sub-agents: research-specialist, document-insight-extractor, connection-finder
  • Local Brain Search: For semantic search and connection discovery

Usage

/learn-new-things                    # Default: 8-hour interval, auto-select topic
/learn-new-things 4                  # 4-hour interval
/learn-new-things 8 "multi-agent systems"  # Specific topic
/learn-new-things stop               # Stop the learning loop

State Tracking

Track learning progress in resources/learn-new-things-log.md:

session_id: YYYY-MM-DD-HHMMSS
last_cycle: 2026-02-18T13:15:00
cycles_completed: 0
topics_researched: []
insights_extracted: 0
connections_discovered: 0
consecutive_errors: 0
phase: "running"  # running | paused | error
branches_created: []  # e.g., ["learning/2026-02-18-embodied-cognition"]

STEP 1: Initialize State

Read or create state file:

cat resources/learn-new-things-log.md 2>/dev/null || echo "No existing state"

Parse arguments:

  • $ARGUMENTS[0] - Interval in hours (default: 8)
  • $ARGUMENTS[1] - Optional topic (default: auto-select)

Read the full file on GitHub · 799 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 · 799 lines · 20 tokens per session scan A b5c8e5a8761f

Subscribe to this mod's changes

learn-new-things is a skill published in the GitHub repository Abilityai/cornelius (105 stars, last pushed 11d ago), licensed MIT. It adds 20 tokens to every session and 4,933 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.

Related

Other skills, from other repositories

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

auditing-subgroup-fairness

Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…

maziyarpanahi/openmed · 148 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