A project setup workflow that studies a codebase and writes guidance about its structure, coding conventions, and working rules.

Use it after installation to create architecture notes, style guidance, and project instruction files.

It gives the coding assistant and its delegated agents a shared understanding of an unfamiliar project.

onboard — Skill for Claude Code by Maximumsoft-Co-LTD

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/Maximumsoft-Co-LTD/claude-flightdeck

agentmods

npx agentmods add skills/maximumsoft-co-ltd/claude-flightdeck/onboard

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/maximumsoft-co-ltd/claude-flightdeck/onboard/github.svg)](https://agentmods.dev/skills/maximumsoft-co-ltd/claude-flightdeck/onboard)

Your own site

<a href="https://agentmods.dev/skills/maximumsoft-co-ltd/claude-flightdeck/onboard"><img src="https://agentmods.dev/badge/skills/maximumsoft-co-ltd/claude-flightdeck/onboard/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/maximumsoft-co-ltd/claude-flightdeck/onboard"><img src="https://agentmods.dev/badge/skills/maximumsoft-co-ltd/claude-flightdeck/onboard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 152 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,424 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	$0.00152	$0.02424
Opus 5.5	$0.00061	$0.00970
Sonnet 5.5	$0.00030	$0.00485
Haiku 4.5	$0.00015	$0.00242

Measured 2mo ago against content hash 9e1c61fa3c07, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/detect-topology.sh, scripts/extract-pr-comments.sh, scripts/mine-git-history.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

core/.claude/skills/onboard/SKILL.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/onboard — Generate the project-understanding docs

Announce: Using /onboard to generate the architecture + conventions docs.

Purpose. Bring the orchestrator and every dispatched agent from "template installed" to "understands THIS project" — by auto-generating, from the codebase, the three things the agents actually read:

Output	What it is	Who reads it
`docs/setup/codebase-orientation.md`	the architecture map (structure, areas, stack, integrations, build/test)	orchestrator + agents (pre-task ritual)
`.claude/rules/code-style.md`	the conventions reference (layout, naming, error handling, test + framework idioms)	`backend-engineer` / `frontend-engineer`
`CLAUDE.md` (root) + area `CLAUDE.md`	routing + non-negotiables, drafted from the two above	orchestrator + agents

Mostly automated (read-only Explore agents + one drafting agent) — minutes, not hours. The deep human interview is opt-in (/onboard interview), not required.

Token budget

Stages 0-2 are Bash (topology) + read-only Explore dispatches — no full file Reads in the main session; miners stage their output to _onboard-staging/.
Stage 3 drafting is delegated to onboarding-engineer — trust its summary, don't re-Read the drafts. Hard cap: ~30k main-session tokens for the automated path (the old interview path cost far more).

Modes

/onboard — auto-generate the understanding docs (Stage 0→3 below). Default.
/onboard refresh — re-run the generation; present DELTA only (skip stages whose inputs are unchanged).
/onboard interview — OPTIONAL deep human enrichment for context only humans have (system purpose, what's fragile, exemplary files, sprint state). See §Interview.
/onboard rules — re-mine git history for A-rule candidates + ratify them (operator-gated). See §Ratify.
/onboard retro — after the first sprint closes, reflect on the wizard itself.

Stage 0 — Pre-flight (auto)

Read the full file on GitHub · 177 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

2mo ago First seen · 177 lines · 152 tokens per session scan A 9e1c61fa3c07

Subscribe to this mod's changes

onboard is a skill published in the GitHub repository Maximumsoft-Co-LTD/claude-flightdeck (2 stars, last pushed 5mo ago), licensed MIT. It adds 152 tokens to every session and 2,424 once invoked, about $0.0006 per session on Opus 5.5. 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.

Claude Code Planning agentic ai-workflow control-plane developer-tools llm-agents

onboard next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
onboardMaximumsoft-Co-LTD/claude-flightdeck	Skill	2	5mo ago	MIT	A	152	Claude Code
experience-creatorxingchengxu/OpenExpertise	Skill	5	5mo ago	MIT	A	166	Claude Code, Codex
runtmruntm-ai/runtm	Skill	303	yesterday	none	C	160	Claude Code, Codex
runtmruntm-ai/runtm	Skill	303	yesterday	none	C	160	Claude Code, Codex
skywardsteffenpharai/skyward	Skill	2	4mo ago	none	A	58	Claude Code, Codex
ppt-reviewOrkas-AI/Orkas	Skill	9.0k	yesterday	MIT	A	2	Claude Code, Codex
package-installerOrkas-AI/Orkas	Skill	9.0k	yesterday	MIT	A	35	Claude Code, Codex