claude-learn

claude-learn is a skill for Claude Code from Jerry0022/dotclaude. It costs 140 tokens per session (2,698 once invoked), scanned A, original, MIT.

A learning recorder for project-specific coding-agent instructions. It saves corrections in the appropriate project rule file so they can guide later sessions.

In plain words
What is it for?
Recording durable project or plugin rules, routing them to the right instruction location, and pruning duplicate feedback entries.
Why use it?
It prevents the same project mistake from being corrected repeatedly in future conversations. It also removes duplicate saved feedback after confirmation.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; names the AskUserQuestion tool.

Part of the devops plugin — 25 skills, 12 agents, 5 hooks, 3 MCP servers 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/jerry0022/dotclaude/claude-learn
Any agent
npx skills add Jerry0022/dotclaude --skill claude-learn
Clone the repo
git clone --depth 1 https://github.com/Jerry0022/dotclaude

Made for: Claude Code.

Or install devops, the plugin that ships this one along with the rest of its 25 skills, 12 agents, 5 hooks, 3 MCP servers.

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 claude-learn

README.md
[![agentmods](https://agentmods.dev/badge/skills/jerry0022/dotclaude/claude-learn.svg)](https://agentmods.dev/skills/jerry0022/dotclaude/claude-learn)
Your own site
<a href="https://agentmods.dev/skills/jerry0022/dotclaude/claude-learn"><img src="https://agentmods.dev/badge/skills/jerry0022/dotclaude/claude-learn.svg" alt="Measured on agentmods" height="20"></a>
Per session 140 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,698 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 5.1 $0.00140 $0.02698
Opus 5 $0.00070 $0.01349
Sonnet 5 $0.00028 $0.00540
Haiku 4.5 $0.00014 $0.00270

Measured 5d ago against content hash 40da157d7828, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

claude-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.

plugins/devops/skills/claude-learn/SKILL.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Learn — Capture a Project-Persistent Learning

Persist a correction so it survives across sessions. Personal style/tone feedback belongs in auto-memory and is handled elsewhere — this skill writes project- or plugin-specific rules.

Step 0 — Load extensions

Use Glob to verify each path exists before reading; skip missing files silently (no output). Merge project > global > plugin defaults.

  1. Global: ~/.claude/skills/claude-learn/SKILL.md + reference.md
  2. Project: {project}/.claude/skills/claude-learn/SKILL.md + reference.md

The directory name is the skill's own name (claude-learn), per CONVENTIONS.md → Extension Mechanism. Any other spelling silently loads nothing.

Step 1 — Collect the learning

Text passed after /claude-learn is the learning. Otherwise ask once: "Was soll ich langfristig lernen?"

The learning MUST end up a self-contained rule. Vague input ("die Farben waren falsch") → one clarifying question before continuing. Capture the why when the user gives it — without the reason the rule becomes superstition and future Claude cannot judge edge cases.

Step 2 — Route

One decision, exactly one branch. Run the gate, then answer Q1–Q3 in order.

Gate — before Q1: does the rule belong to any project at all? A rule that would land outside every project (~/.claude/CLAUDE.md, ~/.claude/skills/) — typically about how Claude answers, regardless of what is being worked on — cannot answer Q1. Stop here: branch E, ask first, never auto-write.

Judge by where the rule has to live, not by the words in it. "In jedem Projekt" is not the trigger: "in jedem Projekt soll /ship die Issue-Nummer schreiben" changes a plugin default and is a plugin rule (Q1). Nor does naming a plugin part keep the gate shut — "sprich mich per Du an, auch wenn /ship nachfragt" is a tone preference that merely mentions /ship as the venue; its home is auto-memory, so the gate fires. Ask what the rule is about: the plugin's behavior, a project's, or how Claude talks to you.

Read the full file on GitHub · 199 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago First seen · 199 lines · 140 tokens per session scan A 40da157d7828

Subscribe to this mod's changes

claude-learn is a skill published in the GitHub repository Jerry0022/dotclaude (5 stars, last pushed yesterday), licensed MIT. It adds 140 tokens to every session and 2,698 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens