f5-learn

f5-learn is a command for coding agents from Fujigo-Software/f5-framework-claude. It costs 8 tokens per session (3,005 once invoked), scanned A, original, MIT.

A command for learning project-specific coding patterns and managing reusable code examples. It can collect, categorize, display, add, remove, and apply examples from areas such as services, tests, components, and hooks.

In plain words
What is it for?
Use it to learn conventions from the codebase or to collect, browse, inspect, add, remove, and apply approved code examples.
Why use it?
It helps an agent follow the project's existing naming, style, and implementation patterns instead of generating unrelated code.

Command

Part of the f5-core plugin — 46 commands, 10 agents 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 commands/fujigo-software/f5-framework-claude/f5-learn
Clone the repo
git clone --depth 1 https://github.com/Fujigo-Software/f5-framework-claude

Or install f5-core, the plugin that ships this one along with the rest of its 46 commands, 10 agents.

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 f5-learn

README.md
[![agentmods](https://agentmods.dev/badge/commands/fujigo-software/f5-framework-claude/f5-learn.svg)](https://agentmods.dev/commands/fujigo-software/f5-framework-claude/f5-learn)
Your own site
<a href="https://agentmods.dev/commands/fujigo-software/f5-framework-claude/f5-learn"><img src="https://agentmods.dev/badge/commands/fujigo-software/f5-framework-claude/f5-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 3,005 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 $0.00008 $0.03005
Opus 5 $0.00004 $0.01503
Sonnet 5 $0.00002 $0.00601
Haiku 4.5 $0.00001 $0.00300

Measured 4d ago against content hash 8d613391f2d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

f5-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 4d 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/f5-core/commands/f5-learn.md · 492 lines

How it starts

The opening of the file, as written. The whole thing — 492 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/f5-learn - Unified Learning & Examples Command

Consolidated command that replaces:

  • /f5-examples/f5-learn examples

Learn and apply project-specific coding patterns, naming conventions, and style preferences.

ARGUMENTS

$ARGUMENTS

MODE DETECTION

Pattern Mode Description
examples <action> EXAMPLES Code example management
<other> (default) LEARN Pattern learning

MODE: EXAMPLES (from /f5-examples)

/f5-learn examples <action>

Collect, manage, and reference high-quality code examples.

Action Description
collect Find and score example code
list [category] List examples by category
show <id> Display specific example
add <file> Manually add example
remove <id> Remove example
apply <id> Apply example to current context

Categories: services, controllers, repositories, entities, utils, tests, components, hooks

Examples:

/f5-learn examples collect --category services
/f5-learn examples list tests
/f5-learn examples show svc_001
/f5-learn examples apply svc_001

MODE: LEARN (Default)

Learn project-specific coding patterns.

Usage

/f5-learn <action> [options]

Actions

scan

Analyze codebase to detect patterns.

/f5-learn scan [--full] [--path <dir>]

Options:

  • --full - Deep scan including all file types
  • --path - Specific directory to scan (default: project root)
  • --force - Overwrite existing profile

show

Display current learning profile.

/f5-learn show [section]

Sections:

  • naming - Naming conventions
  • style - Code style preferences
  • architecture - Architecture patterns
  • all - Full profile (default)

apply

Apply learned patterns to current session.

/f5-learn apply [--strict]

Options:

  • --strict - Enforce all patterns as errors

correct

Record a correction to learn from.

Read the full file on GitHub · 492 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. 4d ago First seen · 492 lines · 8 tokens per session scan A 8d613391f2d9

Subscribe to this mod's changes

f5-learn is a command published in the GitHub repository Fujigo-Software/f5-framework-claude (24 stars, last pushed 7mo ago), licensed MIT. It adds 8 tokens to every session and 3,005 once invoked, about $0.0000 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 2026-08-30.