learner

learner is a skill for Claude Code, Codex from XeldarAlz/everything-claude-unity. It costs 34 tokens per session (1,227 once invoked), scanned A, original, MIT.

A post-debugging skill that records unusual, project-specific lessons after a difficult bug or unexpected system interaction has been understood.

In plain words
What is it for?
Use it after lengthy debugging or when a fix depends on an undocumented convention or interaction in the codebase.
Why use it?
It prevents the same hard-won discovery from being lost or repeated, while filtering out general programming advice that is easy to find elsewhere.

Skill for Claude CodeCodex

Part of the everything-claude-unity plugin — 42 skills, 27 commands, 20 agents, 5 hooks shipped together

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/xeldaralz/everything-claude-unity/learner
Any agent
npx skills add XeldarAlz/everything-claude-unity --skill learner
Clone the repo
git clone --depth 1 https://github.com/XeldarAlz/everything-claude-unity

Made for: Claude Code, Codex.

Or install everything-claude-unity, the plugin that ships this one along with the rest of its 42 skills, 27 commands, 20 agents, 5 hooks.

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 learner

README.md
[![agentmods](https://agentmods.dev/badge/skills/xeldaralz/everything-claude-unity/learner.svg)](https://agentmods.dev/skills/xeldaralz/everything-claude-unity/learner)
Your own site
<a href="https://agentmods.dev/skills/xeldaralz/everything-claude-unity/learner"><img src="https://agentmods.dev/badge/skills/xeldaralz/everything-claude-unity/learner.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,227 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 $0.00034 $0.01227
Opus 5 $0.00017 $0.00613
Sonnet 5 $0.00007 $0.00245
Haiku 4.5 $0.00003 $0.00123

Measured 4d ago against content hash e06d3789b97d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

learner 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/core/learner/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Learner — Knowledge Extraction

After resolving a non-trivial bug or discovering surprising behavior, use this skill to extract and preserve the learning. Not every fix is worth saving — apply the quality gates strictly.

When to Invoke

Consider extraction when:

  • A debugging session took more than 3 back-and-forth exchanges
  • The root cause was surprising or counterintuitive
  • The fix required understanding a project-specific convention or quirk
  • You discovered an undocumented interaction between systems

Quality Gates

ALL three gates must pass. If any fails, do not save the learning.

Gate 1: Not Googleable

Could someone find this answer with a 5-minute web search?

  • Fails: "Use CompareTag instead of == for tag comparison" (standard Unity knowledge)
  • Fails: "Cache GetComponent in Awake for performance" (well-documented best practice)
  • Passes: "Our EventChannel ScriptableObjects must be in a Resources/ folder or they get stripped in IL2CPP builds because nothing in code holds a direct reference"
  • Passes: "The CombatSystem processes damage in LateUpdate, not Update, so any health modification in Update will be overwritten"

Gate 2: Codebase-Specific

Is this specific to THIS project's architecture, conventions, or quirks?

  • Fails: "UniTask is better than coroutines" (generic advice)
  • Fails: "VContainer uses constructor injection" (library documentation)
  • Passes: "The InventorySystem expects item IDs to be registered in ItemRegistry before any InventoryModel is created — initialization order matters"
  • Passes: "Scene transitions must go through SceneSystem.LoadAsync, not SceneManager directly, because SceneSystem handles LifetimeScope cleanup"

Gate 3: Required Real Effort

Did this take actual debugging effort to discover?

  • Fails: Missing semicolon, typo in field name, wrong import
  • Fails: Obvious null reference from unassigned SerializeField
  • Passes: Subtle race condition between async scene load and VContainer injection
  • Passes: Serialization depth limit causing data truncation in nested inventory structure

Read the full file on GitHub · 106 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 · 106 lines · 34 tokens per session scan A e06d3789b97d

Subscribe to this mod's changes

learner is a skill published in the GitHub repository XeldarAlz/everything-claude-unity (21 stars, last pushed 4mo ago), licensed MIT. It adds 34 tokens to every session and 1,227 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 2026-08-30.

Related

Other skills, from other repositories

api-design

REST/GraphQL/gRPC API design best practices. Use when designing APIs, defining contracts, handling versioning. Covers OpenAPI 3.2, GraphQL Federation, gRPC streaming.

majiayu000/spellbook · 42 tokens

general-video

The fallback workflow for authoring custom HyperFrames video compositions at any length or format — longer or multi-scene pieces, brand / sizzle reels, montages, title cards, static loops, and freeform compositions. Input- and length-agnostic. If a specialized workflow clearly fits the input — a marketed product, a…

Sma1lboy/rove · 114 tokens

session-scan

Compute metrics for Claude Code sessions. Discovers via ccrider, filters trivial, computes friction/opportunity/fingerprint scores. Use for broad session triage.

oliver-kriska/claude-elixir-phoenix · 36 tokens

vc-autopilot

Emit and validate the provisional goal block for Autopilot Mode. Owns the 9-field format and resume detection from a pasted goal block.

withkynam/vibecode-pro-max-kit · 34 tokens

manage-schemas

Creates, views, edits, deletes, and validates note schemas for the MCP Task Orchestrator in .taskorchestrator/config.yaml — the templates that define which notes agents must fill at each workflow phase. Also recommends schema designs from a library of workflow patterns (autonomous coding loops, spec-driven teams…

jpicklyk/task-orchestrator · 212 tokens

vc-audit-vc

Audit agent harness health: Claude/Codex agent parity, skill registry consistency, README.md sync, and protocol file wiring. Use when agents, skills, README.md, or development-protocol files move, split, or drift.

withkynam/vibecode-pro-max-kit · 52 tokens