learn

learn is a command for coding agents from raja21068/AutoResearch. It costs 8 tokens per session (330 once invoked), scanned A, a copy of learn, MIT.

A command that extracts recurring solutions, useful practices, mistakes, and reusable code examples from the current coding session.

In plain words
What is it for?
Use it to capture patterns for future work and suggest updates to coding skills or rules.
Why use it?
It turns session experience into documented guidance so useful lessons are less likely to be lost.

Command

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/raja21068/autoresearch/learn
Clone the repo
git clone --depth 1 https://github.com/raja21068/AutoResearch

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/raja21068/autoresearch/learn.svg)](https://agentmods.dev/commands/raja21068/autoresearch/learn)
Your own site
<a href="https://agentmods.dev/commands/raja21068/autoresearch/learn"><img src="https://agentmods.dev/badge/commands/raja21068/autoresearch/learn.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 330 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 95% copy Near-identical to another mod 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 $0.00008 $0.00330
Opus 5 $0.00004 $0.00165
Sonnet 5 $0.00002 $0.00066
Haiku 4.5 $0.00001 $0.00033

Measured today against content hash 78e4f7ab06e3, 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 today.

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.

Origin

This is a copy

95% identical to learn — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/commands/learn.md · 62 lines

What it actually says

Learn Command

Extract patterns, learnings, and reusable insights from the current session: $ARGUMENTS

Your Task

Analyze the conversation and code changes to extract:

  1. Patterns discovered - Recurring solutions or approaches
  2. Best practices applied - Techniques that worked well
  3. Mistakes to avoid - Issues encountered and solutions
  4. Reusable snippets - Code patterns worth saving

Output Format

Patterns Discovered

Pattern: [Name]

  • Context: When to use this pattern
  • Implementation: How to apply it
  • Example: Code snippet

Best Practices Applied

  1. [Practice name]
    • Why it works
    • When to apply

Mistakes to Avoid

  1. [Mistake description]
    • What went wrong
    • How to prevent it

Suggested Skill Updates

If patterns are significant, suggest updates to:

  • skills/coding-standards/SKILL.md
  • skills/[domain]/SKILL.md
  • rules/[category].md

Instinct Format (for continuous-learning-v2)

{
  "trigger": "[situation that triggers this learning]",
  "action": "[what to do]",
  "confidence": 0.7,
  "source": "session-extraction",
  "timestamp": "[ISO timestamp]"
}

TIP: Run /learn periodically during long sessions to capture insights before context compaction.

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. today First seen · 62 lines · 8 tokens per session scan A 78e4f7ab06e3

Subscribe to this mod's changes

learn is a command published in the GitHub repository raja21068/AutoResearch (2 stars, last pushed 3mo ago), licensed MIT. It adds 8 tokens to every session and 330 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to learn, differing in 2 lines, and is treated as a copy.