learn

A tool for finding useful lessons in a coding conversation and saving them for later. These lessons can be stored as rules, skills, or agents for broad or project-specific use.

In plain words
What is it for?
Use it after debugging or problem-solving to discover candidate lessons, choose which ones to keep, and set their type and scope.
Why use it?
It prevents valuable debugging approaches and recurring patterns from being lost when the conversation ends.

Skill for Claude CodeCodex

Part of the claude-evolve plugin — 13 skills, 8 commands, 9 agents, 4 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/hknc/claude-evolve/learn
Any agent
npx skills add hknc/claude-evolve --skill learn
Clone the repo
git clone --depth 1 https://github.com/hknc/claude-evolve

Made for: Claude Code, Codex.

Or install claude-evolve, the plugin that ships this one along with the rest of its 13 skills, 8 commands, 9 agents, 4 hooks.

Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 845 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 $0.00072 $0.00845
Opus 5 $0.00036 $0.00423
Sonnet 5 $0.00014 $0.00169
Haiku 4.5 $0.00007 $0.00085

Measured 3d ago against content hash 4e4de4575fc9, 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 3d 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/claude-evolve/skills/learn/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Learning Extraction

Action

Execute the /learn command flow, which orchestrates the learning-extractor agent in two phases with user selection in between.

Execution

  1. Check prerequisite: Verify $HOME/.claude-evolve/active exists. If not, tell user to run /evolve init first and stop.
  2. Check explicit intent: If the user's request contains explicit type and scope (e.g., "save this as a universal rule"), pre-set those values and skip selection steps.
  3. Phase 1 - Discover: Spawn claude-evolve:evolve-learning-extractor with action="discover" and the user's trigger text as topic hint. Agent analyzes conversation context and session signals, returns at most 4 candidate learnings ranked by value.
  4. Present candidates: Show discovered learnings to user as a numbered list with summary, suggested type, and scope.
  5. User selects: Use AskUserQuestion to let user choose which learnings to capture. Single candidate gets a shortcut (yes/change/skip). Multiple candidates use multiSelect with a "Capture all" option.
  6. Confirm settings: Use AskUserQuestion to ask "Accept suggested types/scopes or customize each?" If customizing, ask type then scope per learning with the recommended option listed first.
  7. Phase 2 - Create: Spawn claude-evolve:evolve-learning-extractor with action="create" and the user's approved selections (id, summary, detail, type, scope, name, consolidates_with per learning).
  8. Report result: Show user what was created or consolidated. If Phase 2 fails, display error and suggest checking toolkit permissions.

See ${CLAUDE_PLUGIN_ROOT}/commands/learn.md for full implementation details.

Learning Types (Learnings become Components)

Found Becomes Location
Problem-solving pattern Skill $HOME/.claude-evolve/toolkits/{name}/skills/{skill-name}/SKILL.md
Investigation method Agent $HOME/.claude-evolve/toolkits/{name}/agents/{name}.md
Code pattern/approach Rule $HOME/.claude-evolve/toolkits/{name}/rules/{name}.md
Improvement to existing Consolidated Merged into existing file

Read the full file on GitHub · 70 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. 3d ago First seen · 70 lines · 72 tokens per session scan A 4e4de4575fc9

Subscribe to this mod's changes

learn is a skill published in the GitHub repository hknc/claude-evolve (8 stars, last pushed 7mo ago), licensed MIT. It adds 72 tokens to every session and 845 once invoked, about $0.0004 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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens