learn

learn is a command for Claude Code from Cristhianzl/claude-skills-czl. It costs 26 tokens per session (349 once invoked), scanned A, original, MIT.

A command for recording one reusable lesson from a coding session in a project knowledge base. It checks whether the lesson is new, belongs elsewhere, or is too specific to keep.

In plain words
What is it for?
Use it to save a new development rule, add insight to an existing note, or discard a one-off lesson.
Why use it?
It prevents useful knowledge from being lost and stops the knowledge base filling with duplicate or trivial notes.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

Good fit Use it to save a new development rule, add insight to an existing note, or discard a one-off lesson.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/cristhianzl/claude-skills-czl/learn
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.

Clone the repo
git clone --depth 1 https://github.com/Cristhianzl/claude-skills-czl

Made for: Claude Code.

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/commands/cristhianzl/claude-skills-czl/learn/github.svg)](https://agentmods.dev/commands/cristhianzl/claude-skills-czl/learn)
Your own site
<a href="https://agentmods.dev/commands/cristhianzl/claude-skills-czl/learn"><img src="https://agentmods.dev/badge/commands/cristhianzl/claude-skills-czl/learn/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for learn

Your own site · 80×15
<a href="https://agentmods.dev/commands/cristhianzl/claude-skills-czl/learn"><img src="https://agentmods.dev/badge/commands/cristhianzl/claude-skills-czl/learn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 349 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00026 $0.00349
Opus 5 $0.00013 $0.00175
Sonnet 5 $0.00005 $0.00070
Haiku 4.5 $0.00003 $0.00035

Measured 12d ago against content hash caf0520bfc24, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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 12d 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.

configs/agnostic/commands/learn.md · 22 lines

What it actually says

Capture a durable learning from what just happened — but only if it's worth keeping, and place it where it belongs. This upgrades the plain "append a learning" step with a quality gate so learnings/ doesn't fill with duplicates.

  1. Identify the single most reusable insight from this session — a convention, constraint, trap, or fix pattern. Skip trivial or one-off fixes.

  2. Check for overlap first (don't append blindly):

    • Grep the relevant skill's learnings/ and any project learnings/ / MEMORY.md for the same topic and keywords.
    • Consider whether appending to an existing learning would suffice.
  3. State a verdict, then act:

    • Save — unique and reusable → write skills/<skill>/learnings/YYYY-MM-DD-slug.md (frontmatter description:; body = the rule + Why + How to apply).
    • Improve then Save — tighten the scope/wording, then save.
    • Absorb into [X] — append to the existing learning instead; show the diff.
    • Drop — trivial or already covered → say so and stop.
  4. Put it in the most specific skill it belongs to (a DB trap → developing-features/learnings/; a review heuristic → reviewing-code/learnings/). One pattern per file; body ≤ ~30 lines.

Confirm with the user before writing the file. Never run git.

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. 12d ago First seen · 22 lines · 26 tokens per session scan A caf0520bfc24

Subscribe to this mod's changes

learn is a command published in the GitHub repository Cristhianzl/claude-skills-czl (5 stars, last pushed yesterday), licensed MIT. It adds 26 tokens to every session and 349 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 2026-08-31.