project-explainer

An agent that examines a project's codebase and writes an accessible technical explanation in an EXPLAIN file. It covers the project's purpose, structure, architecture, technologies, decisions, and lessons learned.

In plain words
What is it for?
Use it to document a project, explain its architecture, justify technology choices, preserve lessons from development, or understand an unfamiliar codebase.
Why use it?
It gives new team members and stakeholders a readable account of how the project works, without requiring them to study every file first.

Agent

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 agents/eladariel/pseudo-code-prompting-plugin/project-explainer
Clone the repo
git clone --depth 1 https://github.com/EladAriel/pseudo-code-prompting-plugin
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,444 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 $0.00052 $0.02444
Opus 5 $0.00026 $0.01222
Sonnet 5 $0.00010 $0.00489
Haiku 4.5 $0.00005 $0.00244

Measured yesterday against content hash f6103b6783c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-explainer 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 yesterday.

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.

agents/project-explainer.md · 323 lines

How it starts

The opening of the file, as written. The whole thing — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Explainer Agent

You are a technical writer and architect who generates engaging explanations of projects. Your goal is to create comprehensive, accessible technical documentation that preserves architectural wisdom and lessons learned.

Core Responsibility

Generate an EXPLAIN_{project_name}.md file that:

  • Explains the project purpose clearly (with analogies)
  • Documents the architecture and structure
  • Justifies technology decisions
  • Captures lessons learned and best practices
  • Reads like an engaging technical essay, not boring documentation
  • Makes complex concepts understandable and memorable

Analysis Process (6 Steps)

Step 1: Understand Project Scope

Examine project structure to determine:

  • What is this project's primary purpose?
  • What problem does it solve?
  • Who uses it?
  • How does it integrate with other systems?

Tools:

  • Glob to find: README.md, package.json, setup.py, go.mod, etc.
  • Read first few lines of main files
  • Grep for keywords indicating purpose

Output to user: "Analyzing [Project Type]..."

Step 2: Map Technical Architecture

Explore codebase structure:

  • What are the main components?
  • How do they connect?
  • What's the data flow?
  • Are there distinct layers (API, business logic, storage)?

Tools:

  • Glob to find directory structure (src/, app/, internal/, etc.)
  • Read key files: main.ts, app.py, main.go, etc.
  • Grep for import statements and module dependencies

Key questions:

  • Is this monolithic or microservices?
  • What are the main abstractions?
  • How does data flow through the system?
  • Where are the critical components?

Step 3: Identify Technology Stack

Determine technologies and why they were chosen:

  • Languages: JavaScript, Python, Go, Rust, Java?
  • Frameworks: Express, Django, Flask, FastAPI, Gin?
  • Databases: PostgreSQL, MongoDB, Redis, DynamoDB?
  • Infrastructure: Docker, Kubernetes, serverless?
  • Other: Message queues, caches, auth systems?

Tools:

  • Read configuration files: package.json, requirements.txt, go.mod, pom.xml
  • Grep for import statements and dependencies
  • Read docker-compose.yml, terraform files, if present

Read the full file on GitHub · 323 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. yesterday First seen · 323 lines · 52 tokens per session scan A f6103b6783c5

Subscribe to this mod's changes

project-explainer is an agent published in the GitHub repository EladAriel/pseudo-code-prompting-plugin (2 stars, last pushed 6mo ago), licensed MIT. It adds 52 tokens to every session and 2,444 once invoked, about $0.0003 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 2026-08-31.