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 commands/vmobifystudio/app-dev-team/app-portfoliogit clone --depth 1 https://github.com/vmobifystudio/app-dev-teamWhat 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 | $0.00016 | $0.01262 |
| Opus 5 | $0.00008 | $0.00631 |
| Sonnet 5 | $0.00003 | $0.00252 |
| Haiku 4.5 | $0.00002 | $0.00126 |
Grade A, and why
app-portfolio scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/app-portfolio — Where should the next hour go?
/app-status and /app-dashboard answer "what is happening in this project". A studio shipping
several apps has a different problem: which of them is quietly stuck. That is not the busy one —
the busy one is being looked after.
Steps
-
Run it. Anywhere; it does not care about the current directory.
node "${CLAUDE_PLUGIN_ROOT}/scripts/portfolio.mjs" $ARGUMENTSPrint its output verbatim. Do not re-rank it in prose and do not summarise a project as "fine" — the score is the deliverable and the reasons are printed beside it.
-
Exit codes are the contract, same as every other gate here:
Code Meaning 0 a portfolio was reported — including any UNREADABLErows, which are reported, not skipped1 bad usage 2 CANNOT EVALUATE — no registry, an unreadable registry, or a registry naming no projects On exit 2, show the message and stop. An empty portfolio is never "nothing needs attention".
-
Machine-readable:
--jsonemits the whole model — the same fields, unranked prose removed — for anything that wants to render it elsewhere.
The registry
One project path per line. # comments and blank lines are ignored, ~ is expanded, and relative
paths resolve against the registry file's own directory.
# ~/.app-dev-team/projects.txt
~/apps/tipjar
~/apps/notes
~/clients/acme/reader
Default location: $APP_TEAM_REGISTRY, else ~/.app-dev-team/projects.txt. Override per run with
--registry <path>.
The registry is the studio's, not a project's — it lives outside every repo on purpose, because a list of a studio's apps checked into one of those apps is a list that goes stale in the other N-1.
What it reports per project
Everything is read through lib/board.mjs and lib/events.mjs — the same parsers as
board-render, board-doctor, ship-gate and the dashboard — plus round-journal.mjs for the
budget. There is no portfolio-specific reading of anything.
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.
- 2d ago First seen · 112 lines · 0 tokens per session scan A 33cab16004d3
app-portfolio is a command published in the GitHub repository vmobifystudio/app-dev-team (4 stars, last pushed 22d ago), licensed MIT. It adds 16 tokens to every session and 1,262 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.
Other commands, from other repositories
test-feature
Test a React Native feature on the running simulator/emulator. Verifies UI, user flows, and internal state. Generates a persistent Maestro test file.
factory-next
Recommend and optionally run the next factory stage for this repo.
compose-preview
Generate and verify Compose previews for UI components.
android-build
Build Android project with Gradle, fix errors, generate APK/AAB. Invokes android-build-resolver for issues.
figma-apply
피그마 변경을 현재 design/ 브랜치에 반영(커밋·푸시). /figma-start 이후에 사용.
compose-test
Run Compose UI tests with Espresso. Verify critical user flows.