app-onboard

A command for bringing an existing app into a team's development process by detecting its technology stack, describing its current structure, and creating baseline project documents.

In plain words
What is it for?
Use it to inspect an app's platforms, libraries, modules, project instructions, continuous-integration setup, and Firebase usage, then prepare it for further work.
Why use it?
It gives the team an understanding of an existing codebase before auditing or changing it, instead of relying on guesses about how it was built.

Command

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/vmobifystudio/app-dev-team/app-onboard
Clone the repo
git clone --depth 1 https://github.com/vmobifystudio/app-dev-team
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,329 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 $0.00041 $0.01329
Opus 5 $0.00020 $0.00665
Sonnet 5 $0.00008 $0.00266
Haiku 4.5 $0.00004 $0.00133

Measured 2d ago against content hash 98cbf8b2cdad, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

app-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.

commands/app-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.

/app-onboard — Bring an existing app into the team

Target app path (optional, default = current directory): $ARGUMENTS

Use this when the project already has code. It produces the same baseline the greenfield flow assumes, but reverse-engineered from what's actually there — so /app-audit and /app-build have something to work against.

Steps

  1. Invoke the brownfield-onboarding skill and follow it. Run its Step 1 detection first: scan the target for iOS/Android markers, versions, libraries, and module layout. Print a short "what I found" block (platforms, stack, module count, whether CLAUDE.md / CI / Firebase exist). If the directory has no app in it, stop and suggest /app-init (greenfield) instead.

  2. Invoke house-conventions so the reverse-engineering is framed against the studio's standards (and the right Flagship/Utility tier).

2a. Activate the roster. Invoke the role-activation skill. Both axes come from step 1's detection, not from a guess: the product type from its detection table (a tree that is neither iOS nor Android is a normal answer — read the package manifests), the tier from the app's size and shape, naming the signal that decided it. Ambiguous → ask one question.

Write docs/02-team-roster.md (copy ${CLAUDE_PLUGIN_ROOT}/docs/02-team-roster.md and fill it in) — every role in the activation matrix, active / conditional / off with trigger or reason — before spawning anyone below. If detection lands on an unstaffed product type (cli), print the skill's ACTIVATION REFUSED block and stop: onboarding a codebase no IC on this team can work on produces a baseline nobody can act on. Otherwise print the tier, the product type, and the off-list. A brownfield backend service that spawns an aso-specialist and gets store-listing homework is the failure this closes.

  1. Spawn the active roles in parallel (single message), each reading the codebase and writing an as-built snapshot — describe what exists, mark guesses (inferred), change no code:
    • cto + tech-leaddocs/20-architecture.md (actual stack, layering, state/persistence/DI/ navigation, backend, CI, signing) and per-platform docs/22-impl-spec-<platform>.md snapshots.
    • cpodocs/10-prd.md feature inventory derived from the navigation graph and screen files, and from that same inventory docs/11-backlog.md and a minimal docs/00-vision.md. Ask the user only for product intent that cannot be read from code.

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. 2d ago First seen · 84 lines · 41 tokens per session scan A 98cbf8b2cdad

Subscribe to this mod's changes

app-onboard is a command published in the GitHub repository vmobifystudio/app-dev-team (4 stars, last pushed 23d ago), licensed MIT. It adds 41 tokens to every session and 1,329 once invoked, about $0.0002 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.