onboard

onboard is a command for Claude Code from hautc-it/cil. It costs 25 tokens per session (561 once invoked), scanned A, original, MIT.

A guided command for learning an unfamiliar software project before changing it. It maps the project's purpose, main code paths, configuration, tests, coding rules, and common pitfalls.

In plain words
What is it for?
Use `/onboard` when entering a new codebase or returning to one after a long gap. It helps identify entry points, core modules, configuration, test commands, formatting and type-checking rules, and continuous-integration setup.
Why use it?
It reduces the risk of making changes without understanding where the application starts, how its parts fit together, or which project rules apply.

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/hautc-it/cil/onboard
Clone the repo
git clone --depth 1 https://github.com/hautc-it/cil

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 onboard

README.md
[![agentmods](https://agentmods.dev/badge/commands/hautc-it/cil/onboard.svg)](https://agentmods.dev/commands/hautc-it/cil/onboard)
Your own site
<a href="https://agentmods.dev/commands/hautc-it/cil/onboard"><img src="https://agentmods.dev/badge/commands/hautc-it/cil/onboard.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 561 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 $0.00025 $0.00561
Opus 5 $0.00013 $0.00280
Sonnet 5 $0.00005 $0.00112
Haiku 4.5 $0.00003 $0.00056

Measured 3d ago against content hash 5f502bc4a573, 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 3d 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 · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/onboard

Structured orientation for an unfamiliar codebase. Run this before making changes to any project you haven't worked in before (or haven't touched in a while).


Step 1 — Project identity

Read:

  • package.json / pyproject.toml / Cargo.toml / go.mod — name, version, scripts
  • README.md — stated purpose, install, quick-start
  • CLAUDE.md — project-specific AI instructions (highest priority)

Answer: What does this project do? Who is the primary user?


Step 2 — Codebase map

find . -maxdepth 3 -type f \( -name "*.ts" -o -name "*.py" -o -name "*.go" -o -name "*.rs" \) \
  | grep -v node_modules | grep -v dist | grep -v .git | head -60

Identify:

  • Entry point(s) — where execution starts
  • Core modules — what the main packages/directories do
  • Config surface — env vars, config files, feature flags
  • Test layout — where tests live, how to run them

Step 3 — Conventions audit

Check for:

  • Linting / formatting config (.eslintrc, ruff.toml, .prettierrc)
  • Type checking (tsconfig.json, mypy.ini, pyright)
  • Git hooks (.husky/, .pre-commit-config.yaml)
  • CI pipeline (.github/workflows/, .gitlab-ci.yml)

Note any rules that will affect your work (strict null checks, import order, etc.)


Step 4 — Recent changes

git log --oneline -20
git diff HEAD~5..HEAD --stat

What has changed recently? Any migrations in progress? Flags being ramped?


Step 5 — Search memory for prior context

memory_search("[project name or key technology]")

Have you worked in this project before? Retrieve prior decisions and constraints.


Step 6 — Store orientation summary

memory_store("architecture", "[project name]: [1–2 sentence architecture summary]", ["onboarding", "architecture"])
memory_store("constraint", "[any hard constraint discovered]", ["constraint", "project"])

Step 7 — State assumptions explicitly

List 3–5 assumptions you are making about this codebase before writing any code. These become checkpoints — verify them during implementation.

Read the full file on GitHub · 84 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. 3d ago First seen · 84 lines · 25 tokens per session scan A 5f502bc4a573

Subscribe to this mod's changes

onboard is a command published in the GitHub repository hautc-it/cil (1 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 561 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.