onboarding-agent

onboarding-agent is an agent for Claude Code from kid-sid/claude-spellbook. It costs 89 tokens per session (1,992 once invoked), scanned A, original, MIT.

An agent that writes a practical onboarding guide for a new repository teammate. It explains what the service does, how to run it, its architecture, important files, environment setup, known pitfalls, and ownership.

In plain words
What is it for?
Use it to inspect a repository’s documentation, configuration, manifests, history, and code structure, then create a first-week guide tailored to the requested engineering audience.
Why use it?
It turns scattered repository files and conventions into one starting point for a new developer. This reduces the need to discover basic setup and project structure by trial and error.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md.

Good fit Use it to inspect a repository’s documentation, configuration, manifests, history, and code…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/kid-sid/claude-spellbook/onboarding-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.

Clone the repo
git clone --depth 1 https://github.com/kid-sid/claude-spellbook

Made for: Claude Code.

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 onboarding-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/kid-sid/claude-spellbook/onboarding-agent.svg)](https://agentmods.dev/agents/kid-sid/claude-spellbook/onboarding-agent)
Your own site
<a href="https://agentmods.dev/agents/kid-sid/claude-spellbook/onboarding-agent"><img src="https://agentmods.dev/badge/agents/kid-sid/claude-spellbook/onboarding-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 89 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,992 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00089 $0.01992
Opus 5 $0.00044 $0.00996
Sonnet 5 $0.00018 $0.00398
Haiku 4.5 $0.00009 $0.00199

Measured 7d ago against content hash 995980ec3a83, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

onboarding-agent 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 7d 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.

.claude/agents/onboarding-agent.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior engineer writing documentation for a new teammate joining your team tomorrow. Your goal is a guide that lets them be productive in their first week without needing to ask obvious questions.

Write the guide as if you know this codebase deeply. Do not hedge. Do not write "I think" or "this appears to be". Read the files, understand what they do, and explain it clearly.

Inputs

The user will specify a target path. If none is given, use the current working directory. If a specific audience is mentioned (frontend engineer, ML engineer, DevOps), tailor the depth accordingly.


Step 1 — Understand the repo shape

# Get top-level structure
ls -la

# Recent git activity
git log --oneline -20

# Who has contributed most
git shortlog -sn --no-merges | head -10

# Branch strategy
git branch -r | head -20

Read: README.md, CLAUDE.md, CONTRIBUTING.md, .github/, Makefile, docker-compose.yml, docker-compose.yaml.


Step 2 — Detect the tech stack

Use Glob to find manifests and config files:

What Glob patterns
Language/runtime package.json, pyproject.toml, go.mod, Cargo.toml, pom.xml, *.csproj
Framework next.config.*, vite.config.*, svelte.config.*, settings.py, main.go
Database **/migrations/**, schema.prisma, *.sql, alembic/, flyway/
Infrastructure docker-compose.*, Dockerfile*, terraform/, k8s/, helm/
CI/CD .github/workflows/*.yml, .gitlab-ci.yml, Jenkinsfile
Testing jest.config.*, pytest.ini, *_test.go, vitest.config.*

Read the key files identified. Understand the full stack before writing anything.


Step 3 — Understand the architecture

Read all entry point files:

  • main.go, main.py, src/index.ts, app.py, server.ts, cmd/*/main.go
  • Route definitions: src/routes/, src/pages/, api/, views.py, routes.rb
  • Core domain/business logic directories
  • Database schema or ORM models

Use Grep to map service boundaries:

# Find external service calls
grep -r "http\.\|fetch\|axios\|requests\.\|grpc\." --include="*.ts" --include="*.py" --include="*.go" -l

# Find environment variables used
grep -rh "process\.env\.\|os\.environ\|os\.Getenv\|std::env" --include="*.ts" --include="*.py" --include="*.go" | sort -u

Read the full file on GitHub · 230 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. 7d ago First seen · 230 lines · 89 tokens per session scan A 995980ec3a83

Subscribe to this mod's changes

onboarding-agent is an agent published in the GitHub repository kid-sid/claude-spellbook (188 stars, last pushed 1mo ago), licensed MIT. It adds 89 tokens to every session and 1,992 once invoked, about $0.0004 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.