prompt

explain_code — Claude Code prompt: what it does, how to install

Q: How to install explain_code in Claude Code?

Save the file to `.claude/commands/explain_code.md`. If you use Fabric, run `fabric --pattern explain_code`.

Breaks down source code, security scanner logs, and config files into structured sections without extra conversational filler.

Install into Claude Code · Manually: put the files in place All methods and platforms ↓

.claude/commands/explain_code.md

Open on GitHub

What explain_code does

The prompt organizes analysis into dedicated headings depending on the input. Source code gets analyzed under EXPLANATION:, while configuration settings go into CONFIGURATION EXPLANATION:. Security tool logs fall under SECURITY IMPLICATIONS:. When the prompt includes an inquiry, the output puts the response inside ANSWER:.

The system prompt strictly forbids notes and warnings. You get predictable, factual blocks instead of polite chat filler.

What it helps with

understand unfamiliar source code routines
interpret output from security scanners
clarify directives inside configuration files
answer targeted questions about technical snippets

Example prompts for the agent

Explain the directives in this nginx.conf snippet
Review this security tool output and summarize the implications
What does this token verification function do in auth.py?

How to install explain_code

Manually: put the files in place

.claude/commands/explain_code.md

Command from the source

fabric --pattern explain_code

Questions about explain_code

How to install explain_code in Claude Code?

Save the file to .claude/commands/explain_code.md. If you use Fabric, run fabric --pattern explain_code.

What does explain_code do?

It examines code, security reports, or configuration data and produces explanations grouped by standard section titles.

How does explain_code format its output?

It suppresses preamble, disclaimers, and warnings, returning only the specific named sections relevant to your input.

Source text

explain_code · MIT

# IDENTITY and PURPOSE

You are an expert coder that takes code and documentation as input and do your best to explain it.

Take a deep breath and think step by step about how to best accomplish this goal using the following steps. You have a lot of freedom in how to carry out the task to achieve the best result.

# OUTPUT SECTIONS

- If the content is code, you explain what the code does in a section called EXPLANATION:. 

- If the content is security tool output, you explain the implications of the output in a section called SECURITY IMPLICATIONS:.

- If the content is configuration text, you explain what the settings do in a section called CONFIGURATION EXPLANATION:.

- If there was a question in the input, answer that question about the input specifically in a section called ANSWER:.

# OUTPUT 

- Do not output warnings or notes—just the requested sections.

# INPUT:

INPUT:


<!-- user.md -->

Code Review taste f This prompt sets practical review standards for pull requests, from checking correctness to labeling comments by severity. Use it when you want a consistent review checklist. GP ChatGPT ★ 174,676repo stars Universal LLM Operating Guidelines [email protected] A rule set for LLM-assisted coding: understand the task first, then touch the code. Cuts invented APIs and stray edits. GP ChatGPT ★ 174,676repo stars Web Accessibility taste f Sets frontend accessibility standards for interface development. It guides accessible markup, keyboard navigation, and focus handling. GP ChatGPT ★ 174,676repo stars Web Security taste f A curated set of web security conventions with confidence scores. Helps full-stack developers verify session cookies, auth flows, and injection defenses. GP ChatGPT ★ 174,676repo stars Git Workflow taste f A prompt that gives an AI assistant trunk-based habits: short-lived branches, Conventional Commits, squash-merge and a protected main. GP ChatGPT ★ 174,676repo stars API Design taste f Opinionated REST API design rules with confidence scores. It guides AI models on clean routing, error contracts, and schema validation. GP ChatGPT ★ 174,676repo stars

From the same set26

The whole set →