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.
npx agentmods add skills/vmobifystudio/app-dev-team/brownfield-onboardingnpx skills add vmobifystudio/app-dev-team --skill brownfield-onboardinggit clone --depth 1 https://github.com/vmobifystudio/app-dev-teamWrote 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.
[](https://agentmods.dev/skills/vmobifystudio/app-dev-team/brownfield-onboarding)<a href="https://agentmods.dev/skills/vmobifystudio/app-dev-team/brownfield-onboarding"><img src="https://agentmods.dev/badge/skills/vmobifystudio/app-dev-team/brownfield-onboarding.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00081 | $0.01170 |
| Opus 5 | $0.00041 | $0.00585 |
| Sonnet 5 | $0.00016 | $0.00234 |
| Haiku 4.5 | $0.00008 | $0.00117 |
Grade A, and why
brownfield-onboarding 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brownfield onboarding
Greenfield commands generate vision → PRD → architecture → code. For an app that already exists, you go the other way: read the code, snapshot what's there, grade it against the House KB, and plan the gap. This skill is the procedure for the "read and understand" half.
When to use
/app-onboard(adopt an existing codebase) and/app-audit(grade it) both start here./app-runinvokes this when the target directory already contains an app (see Detection).
Step 1 — Detect the app
Scan the target directory (not deeper than ~3 levels) to establish ground truth before any agent reasons about it:
- iOS:
*.xcodeproj/*.xcworkspace/Package.swift; readproject.yml(XcodeGen),*.xcconfig,Info.plist,Package.resolved. Note Swift version, min iOS target, SwiftUI vs UIKit. - Android:
settings.gradle*,app/build.gradle(.kts),gradle/libs.versions.toml. Note Kotlin/AGP,compileSdk/minSdk/targetSdk, Compose vs XML, the module list. - Both / signals: existing
CLAUDE.md,README,docs/, CI under.github/workflows,google-services.json/GoogleService-Info.plistpresence (Firebase), ads/billing SDKs in deps. - Neither iOS nor Android: that is a normal answer, not a dead end. Read the package manifests —
package.json,go.mod,Cargo.toml,pyproject.toml,pom.xml— plusDockerfile,Procfile, and whether there is a UI surface or a binary entry point.role-activation's detection table maps what you find to one of the seven product types. - Record the raw findings; do not guess where you can read. The product type you land on decides which specialists ever get spawned, so an ambiguous tree earns one question to the user.
Step 2 — Reverse-engineer the as-built baseline
Produce the docs the team normally writes, but describing what exists, not what's wished for:
docs/20-architecture.md— the actual stack, module/folder layout, state/persistence/DI/nav patterns in use, backend, CI, signing. Mark anything inferred as(inferred).- A feature inventory in
docs/10-prd.md— the screens/features that exist, derived from the code (navigation graph, view/screen files). Ask the user only for product intent you cannot read. CLAUDE.mdat the project root if missing — seeded from the as-built architecture + the House KB, pinning the real stack, build/run commands, and canonical type/property names found in the code.
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.
- today First seen · 82 lines · 81 tokens per session scan A 178c20f085e7
brownfield-onboarding is a skill published in the GitHub repository vmobifystudio/app-dev-team (4 stars, last pushed 24d ago), licensed MIT. It adds 81 tokens to every session and 1,170 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
execute-task
Implement one task (or a cohesion bundle) from a signed-off spec (Ready or Active): recompute the execution freshness gate, write the verifying test first, implement to green, run the project's full CI with adaptive retry, converge via the configured reviewsequence (default /polish --nested), then open a draft PR…
builder
Detect a project's stack and recommend or apply the universal mechanical quality guards from planwright's core catalog (formatter, linters, type-checker, test runner, secret scan, commit hooks, CI gate), plus the growable breadth dimensions. Escalates stake-bearing decisions (auth, data modeling, security posture…
spec-walkthrough
Render a spec bundle (or a chosen slice) into a plain-language, didactic comprehension artifact a human reads and judges for themselves: an unaided cold read before kickoff, re-orientation mid-execution, or onboarding to a finished or abandoned spec. Standalone and strictly read-only: it renders any status, never…
drain
Run the on-demand drain pass over every spec bundle's Gate deferral entries: evaluate structured GATE(when:) conditions, surface date and free-text gates, report malformed ones, inventory each live bundle's [manual] test-spec entries, and surface the observations log's unmined state. Read-only; nothing is…
orchestrate
Advance one planwright spec by one step: pick the next ready unit critical-path-first (or a cohesion bundle), run the freshness gate, record the dispatch under the per-spec lock, and dispatch /execute-task via the backend. A stateless, disposable control tower; a reconcile sweep rebuilds from disk. Never merges, marks…
spec-kickoff
Walk a spec bundle section by section to mutual understanding, producing the signed-off kickoff brief downstream skills execute from. On sign-off: runs the Discovery-Rigor lens pass, flips Draft to Ready, records the sign-off record (anchor last), commits, pushes, opens a draft PR, then on clean completion marks the…