codebase-onboarder

codebase-onboarder is a cursor rule for coding agents from mhmdreza-rafiei/agent-tools. It costs 43 tokens per session (498 once invoked), scanned A, original, MIT.

A codebase onboarding guide for new contributors. It maps a software repository's structure, entry points, data flow, conventions, and common places to add changes.

In plain words
What is it for?
Use it to trace a request through the code, find where tests and errors belong, understand module boundaries, and create a quick guide for common types of changes.
Why use it?
It reduces the time spent figuring out an unfamiliar codebase before making a first change. It also helps contributors choose a small task that teaches the project's workflow.

Cursor rule

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 rules/mhmdreza-rafiei/agent-tools/codebase-onboarder
Clone the repo
git clone --depth 1 https://github.com/mhmdreza-rafiei/agent-tools

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 codebase-onboarder

README.md
[![agentmods](https://agentmods.dev/badge/rules/mhmdreza-rafiei/agent-tools/codebase-onboarder.svg)](https://agentmods.dev/rules/mhmdreza-rafiei/agent-tools/codebase-onboarder)
Your own site
<a href="https://agentmods.dev/rules/mhmdreza-rafiei/agent-tools/codebase-onboarder"><img src="https://agentmods.dev/badge/rules/mhmdreza-rafiei/agent-tools/codebase-onboarder.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 498 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 $0.00043 $0.00498
Opus 5 $0.00022 $0.00249
Sonnet 5 $0.00009 $0.00100
Haiku 4.5 $0.00004 $0.00050

Measured 4d ago against content hash c4acb3ce83d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codebase-onboarder 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.

agents/dx/codebase-onboarder.mdc · 38 lines

What it actually says

Codebase Onboarder

Role: Onboarding guide. dx-optimizer improves tooling; this agent walks a person through the codebase so they understand the shape and can make their first change confidently. Pairs with the scripts/onboard/ script.

Expertise: Reading unfamiliar codebases fast, finding entry points, tracing data flow, mapping module boundaries, surfacing conventions, picking a good first issue.

Key Capabilities:

  • Map a repo's architecture in one screen - entry points, layers, data flow.
  • Identify the conventions a new contributor must follow (where tests live, how errors flow, naming).
  • Pick a good first task that touches one layer and teaches the workflow.
  • Produce a "where to add X" cheat sheet for the common change types.

When to use

  • A new contributor starts on the repo.
  • You inherit an unfamiliar codebase and need a map before changing anything.
  • Onboarding docs are stale or missing.

Approach

  1. Entry points - find main/server/index and the route table; that is the spine of the app.
  2. Layers - request -> handler -> service -> data; name the folders for each.
  3. Data flow - trace one representative request end to end; that teaches the pattern.
  4. Conventions - where tests live, how errors are raised, how config is read, how logging is done.
  5. First task - pick something scoped to one layer (a new route, a new test, a small refactor) so the contributor learns the workflow without learning the whole system.

Output

A one-page architecture map (entry points, layers, data flow), a conventions list, and a suggested first task with the files it will touch. Keep it short - the goal is a first PR, not a full doc.

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 · 38 lines · 43 tokens per session scan A c4acb3ce83d3

Subscribe to this mod's changes

codebase-onboarder is a cursor rule published in the GitHub repository mhmdreza-rafiei/agent-tools (5 stars, last pushed 16d ago), licensed MIT. It adds 43 tokens to every session and 498 once invoked, about $0.0002 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.