What is project-onboard?

A command that examines an existing code repository in depth and creates an onboarding report and project notes. It can use a fast or deep review and a full or minimal scenario.

Use it when joining a repository, taking over maintenance, or checking how well its structure and documentation are understood. It can review the project from its current directory or from a path you provide.

It reduces the time needed to understand an unfamiliar, mature codebase and shows what was inspected, what is missing, and whether the project notes are useful.

project-onboard — Command for Claude Code by VKirill

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/VKirill/claude-lane-stack

Made for: Claude Code.

Or install lane-stack, the plugin that ships this one along with the rest of its 53 skills, 4 commands, 17 agents, 1 hook.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/vkirill/claude-lane-stack/project-onboard.svg)](https://agentmods.dev/commands/vkirill/claude-lane-stack/project-onboard)

Your own site

<a href="https://agentmods.dev/commands/vkirill/claude-lane-stack/project-onboard"><img src="https://agentmods.dev/badge/commands/vkirill/claude-lane-stack/project-onboard.svg" alt="Measured on agentmods" height="20"></a>

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 431 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.

Model	Per session	Once invoked
Fable 5.1	$0.00018	$0.00431
Opus 5	$0.00009	$0.00216
Sonnet 5	$0.00004	$0.00086
Haiku 4.5	$0.00002	$0.00043

Measured 7d ago against content hash a155ec9c5e4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

project-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 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.

plugins/lane-stack/commands/project-onboard.md · 48 lines

What it actually says

Онбординг репозитория делает project-onboarder (не Grok). Fable не пишет CLAUDE.md руками.

Args

$ARGUMENTS may include path and flags:

path to repo (default: cwd)
deep / fast — depth override
full / minimal — scenario override

Examples: /project-onboard · /project-onboard deep · /project-onboard /path/to/repo fast

Steps

PROJECT_CWD = path from args or cwd (absolute).
Parse depth/scenario from $ARGUMENTS → ONBOARD_DEPTH, ONBOARD_SCENARIO if present.
Spawn Agent → project-onboarder:

PROJECT_CWD: <abs>
ARTIFACT_DIR: <abs>/.agents/runs/_onboard/artifacts/001
FORCE: 0
ONBOARD_DEPTH: deep|fast # if user asked; else omit (auto: full→deep, minimal→fast)
ONBOARD_SCENARIO: full|minimal # only if user asked

Wait for finish. Read:
- .agents/onboard.scenario.yaml
- ARTIFACT_DIR/report.md
- skim CLAUDE.md (must not be “Edit me”)
Reply in Russian:
- scenario + depth + score
- files created/updated
- verify result (if deep)
- wiki mismatches
- gaps / next step
If depth was deep but report is thin (no MODULES_READ / still stub CLAUDE) → say partial and offer re-run --deep.

Do not implement product features in this command.

If codex CLI missing: run project-onboard shell seed only, warn that deep fill needs Codex/agent write path.

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.

7d ago First seen · 48 lines · 18 tokens per session scan A a155ec9c5e4f

Subscribe to this mod's changes

project-onboard is a command published in the GitHub repository VKirill/claude-lane-stack (115 stars, last pushed 6d ago), licensed MIT. It adds 18 tokens to every session and 431 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 2026-08-30.

Claude Code Planning agentic-coding ai-agents ai-coding automation claude

project-onboard

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Args

Steps

What this file has done since we first saw it

Other commands, from other repositories

audit-agents-skills

security-audit

pull-repos

init-docs

analizar-sesiones

minar-referencias