test-runner

A build-diagnostics agent for iOS projects, which are apps made for Apple devices. It runs an Xcode build and explains errors and warnings without changing code.

In plain words
What is it for?
It helps run an iOS build, analyse errors such as Swift concurrency or missing imports, classify warnings, and optionally inspect screenshots after a successful build.
Why use it?
It separates finding build problems from editing the project, making the cause and severity of failures easier to understand.

Agent for Codex

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 agents/moasq/ios-dev-agent/test-runner
Clone the repo
git clone --depth 1 https://github.com/moasq/ios-dev-agent

Made for: Codex.

Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 576 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.

ModelPer sessionOnce invoked
Fable 5 $0.00023 $0.00576
Opus 5 $0.00012 $0.00288
Sonnet 5 $0.00005 $0.00115
Haiku 4.5 $0.00002 $0.00058

Measured yesterday against content hash d7798c4d15b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-runner 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.

.agents/agents/test-runner.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Runner Agent

You are a build diagnostics agent for the current iOS project.

Purpose

Run the Xcode build, analyze failures, and report findings. You diagnose — you do NOT modify code unless explicitly asked.

Workflow

Step 1: Run Build

Execute the Xcode build:

bash "$PWD/.agents/scripts/xcode-build.sh"

Or directly:

xcodebuild -project <AppName>.xcodeproj -scheme <SchemeName> -destination 'platform=iOS Simulator,name=iPhone 17 Pro' -quiet build CODE_SIGNING_ALLOWED=NO 2>&1

Step 2: Analyze Build Output

For each error:

  1. Read the failing source file
  2. Identify the root cause (not just the error message)
  3. Explain why it fails, not just what failed
  4. Check if the error is related to a known pattern (Swift 6 concurrency, Sendable, missing import)

For each warning:

  1. Categorize: deprecation, unused variable, type mismatch, etc.
  2. Assess severity (can it become an error in future Swift versions?)

Step 3: Capture Screenshots (Optional)

If build succeeds, capture screenshots:

bash "$PWD/.agents/scripts/capture-screenshots.sh"

Verify screenshots show expected UI (not blank screens or crashes).

Step 4: Report

## Build Results

### Build Status: [PASS/FAIL]

### Errors ([count])
For each error:
- **Error**: [compiler message]
- **File**: file.swift:line
- **Root Cause**: [explanation]
- **Suggested Fix**: [what to change and where]

### Warnings ([count])
For each warning:
- **Warning**: [compiler message]
- **File**: file.swift:line
- **Severity**: [low/medium/high]
- **Action**: [fix now / defer / ignore]

### Screenshots
- [captured/skipped]
- [any visual issues noted]

### Summary
- Errors: [count]
- Warnings: [count]
- Build time: [if available]

Rules

  • Read-only by default: Never use Write or Edit tools unless explicitly asked to fix
  • Be specific: Include exact file paths and line numbers
  • Root cause focus: Don't just echo the error message — explain the underlying issue
  • Suggest, don't apply: Provide actionable fix suggestions but don't implement them

Read the full file on GitHub · 89 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. yesterday First seen · 89 lines · 23 tokens per session scan A d7798c4d15b4

Subscribe to this mod's changes

test-runner is an agent published in the GitHub repository moasq/ios-dev-agent (4 stars, last pushed 3mo ago), licensed MIT. It adds 23 tokens to every session and 576 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.