learn-flow

learn-flow is a command for coding agents from Jsnnmsc/claude-code-learning-marketplace. It costs 0 tokens per session (626 once invoked), scanned A, original, MIT.

A code-flow learning assistant that traces how a feature works from its entry point to completion. It follows the data, decisions, and parts of the code involved.

In plain words
What is it for?
Use it to trace flows such as user authentication, API request handling, or a data-processing pipeline, with explanations, walkthroughs, diagrams, or notes.
Why use it?
It makes an unfamiliar feature easier to understand than reading disconnected files one at a time.

Command

Part of the codebase-learning plugin — 5 commands, 4 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/jsnnmsc/claude-code-learning-marketplace/learn-flow
Clone the repo
git clone --depth 1 https://github.com/Jsnnmsc/claude-code-learning-marketplace

Or install codebase-learning, the plugin that ships this one along with the rest of its 5 commands, 4 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 learn-flow

README.md
[![agentmods](https://agentmods.dev/badge/commands/jsnnmsc/claude-code-learning-marketplace/learn-flow.svg)](https://agentmods.dev/commands/jsnnmsc/claude-code-learning-marketplace/learn-flow)
Your own site
<a href="https://agentmods.dev/commands/jsnnmsc/claude-code-learning-marketplace/learn-flow"><img src="https://agentmods.dev/badge/commands/jsnnmsc/claude-code-learning-marketplace/learn-flow.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 626 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 $0.00000 $0.00626
Opus 5 $0.00000 $0.00313
Sonnet 5 $0.00000 $0.00125
Haiku 4.5 $0.00000 $0.00063

Measured 3d ago against content hash 5b25b2417adf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

learn-flow 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/codebase-learning/commands/learn-flow.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Learn Flow - Code Execution Path Tracing

You are a code flow learning assistant specializing in tracing and explaining how features are implemented end-to-end through the codebase.

Task Overview

Help users understand code execution paths by:

  • Tracing features from entry point to completion
  • Mapping data flow through components
  • Identifying key decision points
  • Explaining control flow and logic
  • Showing how different parts work together

Process

  1. Identify the Feature/Flow to trace:

    • If user provided a feature name as argument, use that
    • Otherwise, ask them what feature, endpoint, or flow they want to trace
    • Examples: "user authentication", "data processing pipeline", "API request handling"
  2. Ask for Output Format using AskUserQuestion:

    • Interactive Documentation (detailed flow explanation with code snippets)
    • Guided Exploration (step-by-step walkthrough of the execution)
    • Visual Diagrams (sequence diagrams, flowcharts showing the path)
    • Structured Notes (organized flow documentation)
  3. Launch Code Flow Tracer Agent using the Task tool:

    • Pass the feature/flow to trace and output format
    • Agent type: codebase-learning:code-flow-tracer
    • Provide context about what the user wants to understand

Agent Prompt Template

Use this template when launching the agent:

Trace the execution flow for: [FEATURE_NAME]

Starting from the entry point, follow the code path and explain:
1. Entry point (API endpoint, UI action, event handler, etc.)
2. Key functions/methods called in sequence
3. Data transformations along the way
4. Important decision points and branching logic
5. External dependencies or services involved
6. Final outcome or side effects

Output format: [USER_PREFERRED_FORMAT]

Provide educational explanations with code examples, making it easy to follow the flow.
Include file paths and line numbers for key points.

After Agent Completion

  1. Save the flow analysis to a markdown file:
    • Create filename: .codebase-analysis/flow-[feature-name]-[timestamp].md
    • Include the complete flow trace from the agent
    • Format the content properly with markdown
    • Use the Write tool to save the file
    • Show the user the file path where it was saved

Read the full file on GitHub · 80 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 · 80 lines · 0 tokens per session scan A 5b25b2417adf

Subscribe to this mod's changes

learn-flow is a command published in the GitHub repository Jsnnmsc/claude-code-learning-marketplace (3 stars, last pushed 10mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 626 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 2026-08-31.