A project status command that summarizes the product vision, current sprint goal, task board, blockers, and completed quality-assurance work. A task board is a list showing what work is planned, active, under review, tested, finished, or blocked.

Use it for daily project checks, sprint reviews, and finding tasks that will not be picked up automatically. It also checks whether work marked for testing has actually reached the project.

It puts the most important project problems, especially stranded tasks and board errors, in one report.

app-status — Command by vmobifystudio

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-status

Clone the repo

git clone --depth 1 https://github.com/vmobifystudio/app-dev-team

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,232 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.

Model	Per session	Once invoked
Fable 5	$0.00019	$0.02232
Opus 5	$0.00010	$0.01116
Sonnet 5	$0.00004	$0.00446
Haiku 4.5	$0.00002	$0.00223

Measured yesterday against content hash 2d44098568a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

app-status 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 yesterday.

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-status.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/app-status — Where are we?

Steps

Print the project's one-line vision from docs/00-vision.md (first heading + first paragraph).
Print the current sprint goal from docs/30-sprint-plan.md.
Print the board summary from docs/31-board.md:
- Count of tickets per status (todo / in_progress / review / qa / done / blocked)
- List any blocked rows or rows with notes
- Run the board doctor (board-doctor skill) and print its verdict:
```
node "${CLAUDE_PLUGIN_ROOT}/scripts/board-doctor.mjs" docs/31-board.md
```
  Anomalies go at the top of the status output, not the bottom. A stranded ticket is the single most important thing on this screen: it is work the sprint loop will never surface on its own. 3aa. Say which qa rows have actually landed. qa now covers two states and they need different answers:
```
node "${CLAUDE_PLUGIN_ROOT}/scripts/merge-reconcile.mjs" --root .
```
- AWAITING INTEGRATION: … → those tickets passed the merge gate and the wave has not run. Print them as "gated, not yet landed" with the command that lands them (wave-integrate.mjs --wave <N>). This is the loop working, not a fault.
- BLOCKED — claims integrated code that is NOT in <base> → a ticket says it shipped and git disagrees. That goes at the top of this screen next to the doctor's anomalies.
Without this, a founder reading 4 in qa cannot tell "four features are on the integration branch" from "four features are approved and still sitting on their own branches".

3a. Render the board so the shape is visible, not tabular:

node "${CLAUDE_PLUGIN_ROOT}/scripts/board-render.mjs" docs/31-board.md --out docs/32-board-view.md

Print the kanban, the per-owner load, and the NEEDS ATTENTION block. --out is not optional: without it, checking status never refreshes the committed docs/32-board-view.md, which is the view humans actually read on GitHub — it silently drifts away from the board it claims to show.

Read the full file on GitHub · 145 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.

yesterday First seen · 145 lines · 19 tokens per session scan A 2d44098568a1

Subscribe to this mod's changes

app-status is a command published in the GitHub repository vmobifystudio/app-dev-team (4 stars, last pushed 22d ago), licensed MIT. It adds 19 tokens to every session and 2,232 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.

Autonomous Agents Code review Project management Testing agent-orchestration ai-agents android claude-code claude-code-plugin

app-status

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/app-status — Where are we?

Steps

What this file has done since we first saw it

Other commands, from other repositories

factory-report

analyze-cluster-postmortem

ab

factory-ticket

factory-next

sprint-status