swift-release-auditor

swift-release-auditor is an agent for Claude Code from charlesjones-dev/claude-code-plugins-dev. It costs 55 tokens per session (382 once invoked), scanned A, original, MIT.

A read-only reviewer for Swift, iOS, and macOS repositories that checks whether a project is ready for Xcode Cloud and TestFlight release.

In plain words
What is it for?
Use it for unattended or scheduled pre-release audits and receive a structured pass, warning, or failure report after it checks the project setup and applicable release conditions.
Why use it?
It finds release blockers that a local build may not reveal, including signing, CI, entitlements, test isolation, and flaky user-interface tests.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the ai-swift plugin — 5 skills, 1 agent shipped together

Good fit Use it for unattended or scheduled pre-release audits and receive a structured pass, warning, or failure report after it checks the project setup and applicable release conditions.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/charlesjones-dev/claude-code-plugins-dev/swift-release-auditor
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/charlesjones-dev/claude-code-plugins-dev

Made for: Claude Code.

Or install ai-swift, the plugin that ships this one along with the rest of its 5 skills, 1 agent.

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 swift-release-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/charlesjones-dev/claude-code-plugins-dev/swift-release-auditor.svg)](https://agentmods.dev/agents/charlesjones-dev/claude-code-plugins-dev/swift-release-auditor)
Your own site
<a href="https://agentmods.dev/agents/charlesjones-dev/claude-code-plugins-dev/swift-release-auditor"><img src="https://agentmods.dev/badge/agents/charlesjones-dev/claude-code-plugins-dev/swift-release-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 382 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 $0.00055 $0.00382
Opus 5 $0.00028 $0.00191
Sonnet 5 $0.00011 $0.00076
Haiku 4.5 $0.00006 $0.00038

Measured yesterday against content hash 1c2fc87ff302, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

swift-release-auditor 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.

plugins/ai-swift/agents/swift-release-auditor.md · 21 lines

What it actually says

Load the swift-preflight skill and follow its methodology, providing a structured PASS / WARN / FAIL report using the skill's defined report format.

Probe the project shape first (XcodeGen vs plain .xcodeproj vs SwiftPM vs Tuist; iOS / macOS / both; Xcode Cloud ci_scripts; signing posture) and run only the applicable checks. Focus on the failures that pass a local build but break later:

  • XcodeGen pbxproj drift from project.yml (bundle id, development team, code-sign settings)
  • Static build numbers with no CI_BUILD_NUMBER stamping (duplicate-build-number TestFlight rejections)
  • Missing or malformed ci_scripts/ci_post_clone.sh on generator projects
  • macOS App Store Info.plist + entitlements gaps (ITMS-90242 LSApplicationCategoryType, ITMS-90296 App Sandbox, ITMS-90683 usage strings, export-compliance prompt, network.client)
  • CI test isolation: tests that touch the real keychain / UserDefaults.standard / disk / network and break on a headless runner (errSecAuthFailed -25293)
  • Ad-hoc signing carrying capability entitlements that require a development certificate
  • Unshared schemes and flaky UITests gating a release; missing unit-test-only CI scheme

This is a read-only audit. Do not modify files. Cite file:line for every finding, give the concrete remedy and a one-line why, and point at the writer skills (/swift-ci-scaffold, /swift-verify) for the automatable fixes.

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 · 21 lines · 55 tokens per session scan A 1c2fc87ff302

Subscribe to this mod's changes

swift-release-auditor is an agent published in the GitHub repository charlesjones-dev/claude-code-plugins-dev (34 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 382 once invoked, about $0.0003 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 2026-09-06.