onboard-codebase

A codebase onboarding skill that creates a guide to a new software project. It maps files and important symbols, shows how modules depend on one another, finds code owners, and identifies complex areas.

In plain words
What is it for?
Use it when joining a project, onboarding teammates, or preparing documentation. It requires the Omen command-line tool to inspect structure, dependencies, ownership, and complexity.
Why use it?
It replaces a slow first pass through an unfamiliar repository with a structured overview of its architecture and key people.

Skill for Claude CodeCodex

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 skills/panbanda/omen/onboard-codebase
Any agent
npx skills add panbanda/omen --skill onboard-codebase
Clone the repo
git clone --depth 1 https://github.com/panbanda/omen

Made for: Claude Code, Codex.

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 813 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 $0.00035 $0.00813
Opus 5 $0.00017 $0.00407
Sonnet 5 $0.00007 $0.00163
Haiku 4.5 $0.00003 $0.00081

Measured 2d ago against content hash eb310555e721, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

onboard-codebase 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 2d 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/development/skills/onboard-codebase/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Onboard Codebase

Generate a comprehensive onboarding guide for a new developer joining the project, identifying key code, architecture, and people to talk to.

Prerequisites

Omen CLI must be installed and available in PATH.

Workflow

Step 1: Get a Quick Code Map

Run the outline command for a token-cheap overview of every file's structure:

omen -f json outline --compact --top 50

This returns imports, classes with methods, and top-level functions — much cheaper than reading full source files.

Step 2: Identify Key Symbols

Run the repomap analysis to find the most important code:

omen -f json repomap --compact --top 25

PageRank-ranked symbols show what's central to the codebase.

Step 3: Map the Architecture

Run the dependency graph analysis to understand structure:

omen -f json graph

This reveals how the codebase is organized and how modules relate.

Step 4: Identify Subject Matter Experts

Run the ownership analysis to find who knows what:

omen -f json ownership

This shows who has expertise in each area of the code.

Step 5: Find Complexity Hotspots

Run the complexity analysis to identify tricky areas:

omen -f json complexity

New developers should be warned about complex areas.

Output Format

Generate an onboarding guide:

# Onboarding Guide: <Project Name>

## Quick Start
1. Clone the repo: `git clone ...`
2. Install dependencies: `...`
3. Run tests: `...`
4. Start dev server: `...`

## Architecture Overview

### Module Structure

src/ ├── core/ # Core business logic ├── api/ # HTTP handlers ├── storage/ # Database layer └── utils/ # Shared utilities


### Key Dependencies
- `core/` depends on `storage/`
- `api/` depends on `core/`
- `utils/` is shared by all

## Important Code to Understand

### Core Symbols (by importance)
1. `core.Engine` - Main processing engine, heart of the system
2. `api.Router` - HTTP routing and middleware
3. `storage.Repository` - Database abstraction
4. ...

### Entry Points
- `cmd/server/main.go` - Main server entry point
- `cmd/worker/main.go` - Background job processor

## Subject Matter Experts

| Area | Expert | Notes |
|------|--------|-------|
| Core engine | [email protected] | Original author |
| API layer | [email protected] | Recent maintainer |
| Storage | [email protected] | Database specialist |

## Areas to Be Careful With

### High Complexity
- `core/processor.go` - Cognitive complexity: 45
  - Talk to alice before modifying
  - Has many edge cases

- `api/middleware.go` - Cyclomatic complexity: 28
  - Authentication logic is tricky
  - Well-tested but fragile

### Knowledge Silos
- `legacy/importer.go` - Only one contributor
  - Documentation is sparse
  - Ask alice for context

## First Tasks Suggestions

Good starter tasks to learn the codebase:
1. Add a new API endpoint (learn api/ patterns)
2. Write tests for an untested function (learn testing patterns)
3. Fix a documentation issue (explore while reading)
4. Address a simple TODO/FIXME (learn code style)

## Resources

- Design docs: `docs/design/`
- API docs: `docs/api/`
- Team wiki: <link>

Read the full file on GitHub · 145 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. 2d ago First seen · 145 lines · 35 tokens per session scan A eb310555e721

Subscribe to this mod's changes

onboard-codebase is a skill published in the GitHub repository panbanda/omen (18 stars, last pushed 9d ago), licensed Apache-2.0. It adds 35 tokens to every session and 813 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 2026-08-30.

Related

Other skills, from other repositories

commit-push-pr

Commit selected local changes, push the branch, and create or update a GitHub pull request with BitFun attribution. Use when the user asks to 提交 PR、提代码、commit and push、开 PR、create a pull request, or wants a Claude Code-like one-command PR publishing flow from BitFun.

GCWing/BitFun · 68 tokens

watch

File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…

SethGammon/Citadel · 70 tokens

issue-reporter

只在用户明确要求提交 GitHub Issue、GitHub Bug Report 或 GitHub Feature Request 时使用。用户只说“提交问题”“提交反馈”“上报 bug”“这是个 bug”或描述功能建议但未点名 GitHub 时不得触发,必须改用 cherry-studio-feedback 并默认提交飞书。.

CherryHQ/cherry-studio · 73 tokens

code-mate-antigravity

Runs Antigravity CLI headlessly for repository analysis and coding tasks. Use when the user asks to delegate work to Antigravity CLI or compare its result with another coding agent.

CherryHQ/cherry-studio · 43 tokens

code-mate-openclaw

Runs a local OpenClaw agent non-interactively and returns its structured response. Use when the user asks to delegate a bounded task to the OpenClaw main agent.

CherryHQ/cherry-studio · 41 tokens

live-preview

Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.

SethGammon/Citadel · 40 tokens