xcodebuildmcp-tool-contract-review

xcodebuildmcp-tool-contract-review is a skill for Claude Code, Codex from getsentry/XcodeBuildMCP. It costs 37 tokens per session (367 once invoked), scanned A, original, MIT.

A review checklist for changes to XcodeBuildMCP tool contracts, including their implementation, manifests, workflows, output descriptions, and follow-up templates. XcodeBuildMCP is a system that exposes Xcode build actions to agents through tools.

In plain words
What is it for?
Use it to review new or changed tool definitions, check manifest and workflow membership, confirm output schemas and identifiers, and run the project’s type-checking validation.
Why use it?
It catches mismatches that can make a tool unavailable, incorrectly described, or inconsistent across code and configuration. The review is read-only unless implementation work is explicitly requested.

Skill for Claude CodeCodex

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/getsentry/xcodebuildmcp/xcodebuildmcp-tool-contract-review
Any agent
npx skills add getsentry/XcodeBuildMCP --skill xcodebuildmcp-tool-contract-review
Clone the repo
git clone --depth 1 https://github.com/getsentry/XcodeBuildMCP

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 xcodebuildmcp-tool-contract-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/getsentry/xcodebuildmcp/xcodebuildmcp-tool-contract-review.svg)](https://agentmods.dev/skills/getsentry/xcodebuildmcp/xcodebuildmcp-tool-contract-review)
Your own site
<a href="https://agentmods.dev/skills/getsentry/xcodebuildmcp/xcodebuildmcp-tool-contract-review"><img src="https://agentmods.dev/badge/skills/getsentry/xcodebuildmcp/xcodebuildmcp-tool-contract-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 367 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 $0.00037 $0.00367
Opus 5 $0.00018 $0.00183
Sonnet 5 $0.00007 $0.00073
Haiku 4.5 $0.00004 $0.00037

Measured 3d ago against content hash 5b596ed25e2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

xcodebuildmcp-tool-contract-review 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 3d 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/skills/xcodebuildmcp-tool-contract-review/SKILL.md · 44 lines

What it actually says

XcodeBuildMCP Tool Contract Review

Review guardrails for tool contract changes across implementation, manifests, and workflow exposure.

Review scope

  • Review-only by default.
  • Do not edit product code unless the user explicitly requests implementation changes.

Files to inspect

  • src/mcp/tools/**
  • manifests/tools/*.yaml
  • manifests/workflows/*.yaml
  • src/core/manifest/schema.ts
  • src/runtime/tool-catalog.ts
  • src/runtime/types.ts
  • xcodebuildmcp.com/app/docs/_content/tool-authoring.mdx
  • xcodebuildmcp.com/app/docs/_content/architecture-manifest-visibility.mdx

Guardrails

  • Manifest id matches filename.
  • Manifest module points to implementation path without extension.
  • Tool module exports named schema and handler.
  • names.mcp remains globally unique.
  • names.cli stays workflow-local and consistent with CLI docs/fixtures.
  • Tool appears in at least one workflow unless intentionally hidden by availability.
  • outputSchema is present for tools that set ctx.structuredOutput.
  • nextSteps.toolId references existing manifest tool IDs.
  • Avoid parallel legacy paths or duplicate implementation paths.

Validation

  • npm run typecheck
  • npm test -- src/core/manifest/__tests__/schema.test.ts
  • npm test -- src/runtime/__tests__/tool-invoker.test.ts
  • npx skill-check .agents/skills/xcodebuildmcp-tool-contract-review
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. 3d ago First seen · 44 lines · 37 tokens per session scan A 5b596ed25e2e

Subscribe to this mod's changes

xcodebuildmcp-tool-contract-review is a skill published in the GitHub repository getsentry/XcodeBuildMCP (6,321 stars, last pushed 2d ago), licensed MIT. It adds 37 tokens to every session and 367 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 2026-08-30.

Related

Other skills, from other repositories

rn-expo

The RN/Expo dev-build recipe for adb-mcp — adbreverse before launching (or the dev client silently runs its embedded bundle), appstate to confirm it is on Metro, on the RIGHT Metro, and not serving stale JavaScript after a git checkout, then reloadapp. Use whenever driving a React Native or Expo dev build, or when…

iksnerd/adb-mcp · 84 tokens

crash-triage

Using logcat to surface the real "Caused by:" root cause hidden behind a generic UI error, plus app lifecycle tools for reproducing failures. Use when an app crashes, shows a generic error dialog, or a task needs to find why a native call failed.

iksnerd/adb-mcp · 60 tokens

driving

The core observe→locate→act→re-observe loop for driving an Android UI with adb-mcp — true-pixel coordinates, and gotchas like overlays eating taps, keyboards covering buttons, and settle delays. Use whenever tapping, swiping, typing, or otherwise interacting with an Android screen.

iksnerd/adb-mcp · 64 tokens

getting-started

How to list AVDs, boot an emulator, target a device with the serial argument, and run a first interaction with adb-mcp. Use when starting a new Android automation task, or when no device/emulator is booted yet.

iksnerd/adb-mcp · 53 tokens

opik-diagnose

Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…

comet-ml/opik-mcp · 147 tokens

heimdall

Work with an Apple App Store Connect account through Heimdall's MCP servers — App Store listings and metadata, TestFlight builds and testers, subscription and in-app-purchase prices, customer reviews, sales and analytics reports, certificates and provisioning profiles. Use this whenever the user asks about their app…

erayendes/app-store-connect-mcp · 180 tokens