An app audit command that compares an existing application with the Mobify Studio House knowledge base and Axiom standards, then reports and prioritises gaps.

It runs specialist audits for the detected platforms, records which checks ran or fell back, ranks findings by severity, and prepares follow-up work.

It makes missing or inconsistent standards visible across different parts of an app. It also turns findings into a remediation backlog and applies safe fixes while requesting approval for risky ones.

app-audit — 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-audit

Clone the repo

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

Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,964 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	$0.00048	$0.01964
Opus 5	$0.00024	$0.00982
Sonnet 5	$0.00010	$0.00393
Haiku 4.5	$0.00005	$0.00196

Measured 2d ago against content hash 6a36dade38ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

app-audit 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-audit.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/app-audit — Grade the app, then close the gaps

Dimension (optional, default = all): $ARGUMENTS

Preconditions

Requires the as-built baseline from /app-onboard (at least docs/20-architecture.md). If it's missing, run /app-onboard first, then continue.
Invoke house-conventions and brownfield-onboarding before auditing.

Steps

Fan out the auditors in parallel (single message), matched to the detected platform(s). Each checks ONE dimension against the House KB pack it owns and returns findings, read-only:
- iOS — code-reviewer grading against ios-conventions.md, always. The axiom:* auditors are external and optional (separate plugin, not this one's skills/) and are listed in exactly one place: the canonical auditor list in agents/code-reviewer.md. Read the roster and the detect-else-degrade rule there — do not re-list them here, because the copy that drifts is always the one nobody is looking at.
  
  State which auditors ran and which dimensions fell back, in the scorecard. Never skip a dimension silently: an unaudited dimension that prints no findings is indistinguishable from a clean one, and it is the scorecard the user makes the ship decision on.
- Android — code-reviewer against android-conventions.md (the five ViewModel patterns, Room/DataStore rules, no logic in composables), plus lint/detekt/ktlint results.
- Monetization — monetization-engineer vs monetization.md (paywall gateway, entitlement source of truth, AdGate ordering, NO-AD zones, consent, test-IDs-by-default).
- Analytics — data-analyst vs analytics.md (consent gate, PII, event coverage of P0 features).
- ASO / store — aso-specialist vs aso.md (readiness, Data Safety / Privacy Manifest).
- DevOps — devops-engineer vs git-workflow.md (branch model, CI, signing, secrets hygiene).
- Security — security-reviewer (MASVS). If a single dimension was named in $ARGUMENTS, run only that one.

Read the full file on GitHub · 127 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.

2d ago First seen · 127 lines · 48 tokens per session scan A 6a36dade38ed

Subscribe to this mod's changes

app-audit is a command published in the GitHub repository vmobifystudio/app-dev-team (4 stars, last pushed 22d ago), licensed MIT. It adds 48 tokens to every session and 1,964 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.

Autonomous Agents Memory and context Mobile Project management agent-orchestration ai-agents android claude-code claude-code-plugin

app-audit

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/app-audit — Grade the app, then close the gaps

Preconditions

Steps

What this file has done since we first saw it

Other commands, from other repositories

factory-report

project

feature

commit-all

test-feature

android-build