onboard

A session-start guide that loads project context and reports the current state, with a deeper mode for major work.

In plain words
What is it for?
Use it when beginning focused work or a larger task. It can identify relevant files, inspect project notes and structure, check Git changes, and report tests or linting when configured.
Why use it?
It reduces the time spent manually finding important project files, pending changes, test status, and known decisions.

Command for Claude Code

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 commands/codeverbojan/claude-code-kickstart/onboard
Clone the repo
git clone --depth 1 https://github.com/codeverbojan/claude-code-kickstart

Made for: Claude Code.

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 402 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 $0.00018 $0.00402
Opus 5 $0.00009 $0.00201
Sonnet 5 $0.00004 $0.00080
Haiku 4.5 $0.00002 $0.00040

Measured 2d ago against content hash 98154110d762, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

onboard 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.

.claude/commands/onboard.md · 49 lines

What it actually says

Session Onboard

primer.md is auto-loaded by the SessionStart hook, so skip anything that just re-reads it. Mode is determined by $ARGUMENTS.

DEEP MODE — if $ARGUMENTS contains "deep"

Full context load for major work. Read in this order, skipping any file that contains a placeholder stub (No gotchas yet, No patterns extracted yet, No decisions logged yet) — those have no signal:

  1. gotchas.md, patterns.md, decisions.md (non-stub only)
  2. Project structure: key directories, entry points, top-level config
  3. Architecture docs if present (docs/, ARCHITECTURE.md, README.md)
  4. git status for uncommitted state
  5. Typecheck/lint if configured — otherwise skip silently

Report in under 15 lines:

  • Current state (from primer.md)
  • Project structure (one line)
  • Uncommitted changes
  • Test/lint health or "not configured"
  • Next steps from primer.md
  • Blockers or clarifications needed

If a task was given alongside "deep", also name the 1–3 files you'll need and how the task fits the current state.

LIGHT MODE — if a task is given (no "deep")

Fast onboard for focused work.

  1. Identify the 1–3 files most relevant to $ARGUMENTS
  2. Report in 3–5 lines: current state, what you'll work on, files you'll touch, any blocker
  3. Start working immediately.

STATUS MODE — no arguments

Just report git status + next steps from primer.md in 3 lines. Don't re-read primer.md — it's already in context. Wait for instructions.

$ARGUMENTS

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 · 49 lines · 18 tokens per session scan A 98154110d762

Subscribe to this mod's changes

onboard is a command published in the GitHub repository codeverbojan/claude-code-kickstart (2 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 402 once invoked, about $0.0001 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.