learn

learn is a command for Claude Code from tomdwipo/claude-soul. It costs 0 tokens per session (252 once invoked), scanned A, original, MIT.

A command that turns recent corrections into reusable development guidance. It checks whether a correction reflects a general rule and places it in the project’s principles or common-issues documentation.

In plain words
What is it for?
Use it after a correction to identify the root cause, check for an existing related rule, and prepare a documented principle or rule for review.
Why use it?
It prevents the same mistake from being corrected repeatedly without recording what caused it and how to avoid it.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

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 commands/tomdwipo/claude-soul/learn
Clone the repo
git clone --depth 1 https://github.com/tomdwipo/claude-soul

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/tomdwipo/claude-soul/learn.svg)](https://agentmods.dev/commands/tomdwipo/claude-soul/learn)
Your own site
<a href="https://agentmods.dev/commands/tomdwipo/claude-soul/learn"><img src="https://agentmods.dev/badge/commands/tomdwipo/claude-soul/learn.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 252 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 $0.00000 $0.00252
Opus 5 $0.00000 $0.00126
Sonnet 5 $0.00000 $0.00050
Haiku 4.5 $0.00000 $0.00025

Measured 6d ago against content hash 59c5ab6104b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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/commands/learn.md · 18 lines

What it actually says

/learn — Distil a correction into a principle (or rule)

Run the engine in .docs/principles/how-to-learn.md on the most recent correction(s) in this session (or on $ARGUMENTS if given).

Steps:

  1. Identify the concrete correction (quote it).
  2. Find the root cause (why), not the symptom.
  3. Confirm it generalises (applies 3+ times) — else stop and say so.
  4. Scan .docs/principles/README.md + .docs/common-issues/ for an existing entry to sharpen/merge instead of adding a sibling.
  5. FORK (principle-default): a compile/test/lint/build result settles it → RULE (.docs/common-issues/ + catalog row); judgment/taste → PRINCIPLE (.docs/principles/ + index row); unsure → principle.
  6. Write the file in the canonical shape; keep it tight.
  7. Show the exact diff (new/edited files + index/catalog rows) and STOP for review. Do not commit unless the user says so.
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. 6d ago First seen · 18 lines · 0 tokens per session scan A 59c5ab6104b8

Subscribe to this mod's changes

learn is a command published in the GitHub repository tomdwipo/claude-soul (24 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 252 tokens. 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.