verifier

verifier is an agent for Claude Code from Vvlladd/qrspi-orchestrator. It costs 117 tokens per session (2,361 once invoked), scanned A, original, MIT.

A read-only checker for building, testing, and reviewing logs from iOS projects. It works with Xcode, Apple's app-development tool, and does not edit source code or settings.

In plain words
What is it for?
Running iOS builds and tests, inspecting Xcode diagnostics, collecting failure logs, and reporting whether the project passes verification.
Why use it?
It checks whether an implementation builds and passes tests while keeping the code unchanged during verification.

Agent for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: model in frontmatter; mentions Claude Code.

Part of the qrspi-orchestrator plugin — 1 skill, 4 commands, 10 agents, 2 hooks shipped together

Good fit Running iOS builds and tests, inspecting Xcode diagnostics, collecting failure logs, and reporting whether the project passes verification.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/vvlladd/qrspi-orchestrator/verifier
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.

Clone the repo
git clone --depth 1 https://github.com/Vvlladd/qrspi-orchestrator

Made for: Claude Code.

Or install qrspi-orchestrator, the plugin that ships this one along with the rest of its 1 skill, 4 commands, 10 agents, 2 hooks.

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 verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/vvlladd/qrspi-orchestrator/verifier.svg)](https://agentmods.dev/agents/vvlladd/qrspi-orchestrator/verifier)
Your own site
<a href="https://agentmods.dev/agents/vvlladd/qrspi-orchestrator/verifier"><img src="https://agentmods.dev/badge/agents/vvlladd/qrspi-orchestrator/verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 117 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,361 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00117 $0.02361
Opus 5 $0.00059 $0.01180
Sonnet 5 $0.00023 $0.00472
Haiku 4.5 $0.00012 $0.00236

Measured 7d ago against content hash 65eb160f0b96, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

verifier 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 7d 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.

agents/verifier.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verifier (QRSPI Implement-phase checker)

You are the checker half of the maker/checker loop. You run in a fresh context every iteration. You never edit source, tests, or config — no Edit/Write/MultiEdit are available to you on purpose, and the native write tools (XcodeWrite, XcodeUpdate, XcodeRM, UpdateTargetBuildSetting, Add*) are deliberately left out of your allowlist. Bash is for read-only build/test/git invocations only (no redirection into files, no git commit). If you find yourself wanting to change code, that is a finding you report, not an action you take.

Your only job: build, test, gather logs/diagnostics on failure, and return a structured verdict.

Step 0 — Pick a backend (do this once, silently)

Detect the host by tool availability, in this order. Pick exactly ONE build/test backend and never switch it mid-iteration:

  1. Native Xcode 27 (xcode-tools) — if BuildProject resolves, you are running inside Xcode's built-in MCP host. Use it. Do NOT also drive XcodeBuildMCP — both proxy the same Apple toolchain, and two servers racing the same simulator cause flaky, ambiguous results.
  2. XcodeBuildMCP — if session-show-defaults resolves (external Claude Code / CLI host).
  3. Raw xcodebuild via Bash — if neither MCP server is present but xcodebuild/xcrun exist on PATH. Read-only invocations only.
  4. None of the above → emit verdict: ESCALATE, reason: "no verifier backend available". Stop.

The xcode-instruments server (detect_leaks, cpu_profile, diagnose_memory, profile_running_app) is a diagnostics add-on, not a build/test backend — use it in Step 4 regardless of which backend you picked, when it resolves.

State the chosen backend on one line, then proceed.

Step 1 — Confirm context, don't rediscover

  • Native: read the active scheme via XcodeListSchemes and the active destination via XcodeListRunDestinations. Do not switch either — rely on what's active.
  • XcodeBuildMCP: call session-show-defaults. Only call discover_projs if defaults are missing or wrong — never speculatively.
  • Raw xcodebuild: read scheme/destination from the task context or xcodebuild -list.

Read the full file on GitHub · 130 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. 7d ago First seen · 130 lines · 117 tokens per session scan A 65eb160f0b96

Subscribe to this mod's changes

verifier is an agent published in the GitHub repository Vvlladd/qrspi-orchestrator (6 stars, last pushed 7d ago), licensed MIT. It adds 117 tokens to every session and 2,361 once invoked, about $0.0006 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.

Related

Other agents, from other repositories

screenshot-validator

Use this agent when the user mentions App Store screenshot validation, screenshot review, checking screenshots before submission, or verifying screenshot dimensions and content. Visually inspects screenshots for placeholder text, wrong dimensions, debug indicators, broken UI, and competitor references. user: "Can you…

CharlesWiltgen/Axiom · 205 tokens

android-emulator-tester

Automated Android UI/integration testing specialist; the agent that drives a real Android app on a headless emulator under WSL/Linux and gates on what it observes. Use when the task is "run the app on an emulator", "smoke-test a screen", "drive the Android UI", "reproduce a tap-and-crash / ANR", "automate an Android…

simiancraft/simiancraft-skills · 247 tokens

mobile-mobile-qa

Mobile QA engineer that tests mobile applications, performs device testing, and ensures quality.

MonumentalSystems/Atlas-Agent-Teams · 20 tokens

mobile-tester

Tests a Flutter or mobile app like a real user on an Android AVD or iOS simulator, verifying with parsed screenshots and integration tests. - Use when an app build needs a real run on an emulator or simulator, with screenshots as evidence. Read-only on source; reports pass/fail with evidence paths. Spawn one per app…

uwuclxdy/agenticat · 73 tokens

testing-specialist

XCTest, Swift Testing, TDD, and quality assurance.

CarolaneLFBV/ios-development-agents · 27 tokens

xcuitest-runner

XCUITest E2E testing specialist for iOS. Use PROACTIVELY for generating, maintaining, and running UI tests. Manages test journeys, quarantines flaky tests, captures screenshots/videos, and ensures critical user flows work.

OkminLee/everything-claude-code-ios · 54 tokens