runtime-gate

runtime-gate is a skill for Claude Code, Codex from vmobifystudio/app-dev-team. It costs 74 tokens per session (1,146 once invoked), scanned A, original, MIT.

Use before advancing a ticket past QA and before any release — builds the app and launches it, then drives the P0 journey where UI automation exists. Triggers from /app-build's QA wave, /app-ship, qa-engineer and verification-engineer, and any moment someone is about to certify that an app works without having run it.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside the plugin that ships it — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed.

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 skills/vmobifystudio/app-dev-team/runtime-gate
Any agent
npx skills add vmobifystudio/app-dev-team --skill runtime-gate
Clone the repo
git clone --depth 1 https://github.com/vmobifystudio/app-dev-team

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for runtime-gate

README.md
[![agentmods](https://agentmods.dev/badge/skills/vmobifystudio/app-dev-team/runtime-gate.svg)](https://agentmods.dev/skills/vmobifystudio/app-dev-team/runtime-gate)
Your own site
<a href="https://agentmods.dev/skills/vmobifystudio/app-dev-team/runtime-gate"><img src="https://agentmods.dev/badge/skills/vmobifystudio/app-dev-team/runtime-gate.svg" alt="Measured on agentmods" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,146 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00074 $0.01146
Opus 5 $0.00037 $0.00573
Sonnet 5 $0.00015 $0.00229
Haiku 4.5 $0.00007 $0.00115

Measured today against content hash 41a0260f9f2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

runtime-gate 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.

skills/runtime-gate/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Runtime gate

Every other gate in this plugin verifies that the process was followed. verify-done.sh checks the branch exists and the test command exited zero. board-doctor checks the board is coherent. ship-gate.sh checks nothing is in flight and no S1/S2 is open. code-reviewer checks the diff reads correctly. A sprint can run green through all four on an app that does not compile in Xcode, does not launch, or launches to a blank screen — because nothing ever ran it.

This is defect-hunting §2 — never certify by reading, execute it — pointed at the app itself.

Run it

sh "${CLAUDE_PLUGIN_ROOT}/scripts/runtime-gate.sh" [--platform ios|android|auto] [--project-root .]
Exit Meaning What to do
0 PASS — built and launched Record the evidence path. Continue.
1 FAIL — does not build, or does not launch Blocks the row. Re-spawn the developer with the compiler output the gate printed, verbatim.
2 CANNOT EVALUATE — the toolchain is not on this machine Not a pass. Report it as CANNOT EVALUATE in the standup and in the verdict block.

Exit 2 is the point of the script. A machine without Xcode is a normal state — a CI runner, a Linux box, an Android-only project. It is not an error and it is not a pass. The gate prints what was missing and what would make it evaluable; surface those lines rather than paraphrasing them.

Two traps it already closes, so do not re-open them by hand: command -v xcodebuild succeeds on a Command-Line-Tools-only Mac where every invocation fails, and a build that compiles is not a pass — "BUILDS, but launch UNKNOWN" is exit 2. Timeouts are stated and enforced; a hung simulator produces CANNOT EVALUATE, never an infinite wait.

Escalate past the script when the toolchain allows

The script is the floor — it proves the app starts. On iOS the Axiom toolchain, when installed, gives far more, and you should route to it:

  • axiom:simulator-tester — drives the running app, captures screenshots, reads the log for crashes and errors. This is what turns "it launched" into "the journey works".
  • axiom:test-runner — runs XCUITests and parses the .xcresult for real failure detail.
  • XcodeBuildMCP (the xcodebuildmcp skill) — build, install, launch and UI automation as tools.

Read the full file on GitHub · 85 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. today First seen · 85 lines · 74 tokens per session scan A 41a0260f9f2b

Subscribe to this mod's changes

runtime-gate is a skill published in the GitHub repository vmobifystudio/app-dev-team (4 stars, last pushed 24d ago), licensed MIT. It adds 74 tokens to every session and 1,146 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.

Related

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…

inkatze/planwright · 111 tokens

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…

inkatze/planwright · 100 tokens

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…

inkatze/planwright · 100 tokens

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…

inkatze/planwright · 75 tokens

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…

inkatze/planwright · 101 tokens

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…

inkatze/planwright · 108 tokens