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.
git clone --depth 1 https://github.com/fledgeling-co/fledgeling-pluginsWrote 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.
[](https://agentmods.dev/plugins/fledgeling-co/fledgeling-plugins/proctor)<a href="https://agentmods.dev/plugins/fledgeling-co/fledgeling-plugins/proctor"><img src="https://agentmods.dev/badge/plugins/fledgeling-co/fledgeling-plugins/proctor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/fledgeling-co/fledgeling-plugins/proctor"><img src="https://agentmods.dev/badge/plugins/fledgeling-co/fledgeling-plugins/proctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
proctor 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 1mo 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.
What it actually says
{
"name": "proctor",
"description": "Run a real test campaign against a native macOS app or an iOS Simulator: exploratory sweep, acceptance criteria turned into executable flows, state-matrix and edge coverage, accessibility audit, visual fidelity, determinism measurement, and a report that separates what was proven from what was assumed. Ships with the Proctor MCP server: an unsandboxed launchd agent that reads the accessibility tree and screen contents, and captures through ScreenCaptureKit so every frame carries its own trustworthiness rather than being believed on sight. Actuation runs on Proctor's own process-directed plane by default, so background, occluded and other-Space windows are reachable without stealing focus, and can be delegated to Cua Driver when an operator selects that lane. iOS is a second lane: deep links through simctl and Maestro flow files, scored for determinism. Also ships an embeddable DEBUG reflector that gives apps you own a real computed-style source. Use it when someone asks to test, QA, exercise or find bugs in a Mac or iOS app, whether a flow still works, why a test is flaky, or what breaks in dark mode.",
"version": "0.7.2",
"author": {
"name": "Fledgeling",
"email": "[email protected]"
}
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 450 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 1mo ago Changed 904a8e3f9488
- 1mo ago First seen · 10 lines scan A 742f7f346dd0
proctor is a plugin published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 4d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-04.
Other plugins, from other repositories
serve-sim
Control and stream a running iOS, iPad, or Apple Watch Simulator with serve-sim.
greenlight
Run every App Store and Google Play compliance check in one command: code patterns, privacy manifests, Android manifests and Gradle, IPA/APK/AAB binaries, metadata. Catches rejections before you submit. Claude Code integration: run, fix, re-run until GREENLIT.
apple-skills
164 Apple platform development skills across 23 categories (iOS, macOS, watchOS, visionOS): code generators, product workflow, App Store/ASO, testing and TDD, design, performance, security, and more. Surfaced as 23 category skills that route to the full library.
ios-all
All 11 iOS skills: swiftui-mvvm, uikit-mvvm, viper-uikit, tca-swiftui, swift-concurrency, gcd-operations, ios-testing, ios-security, ios-accessibility, ios-localization, ios-logging.
xcode-cli
Xcode CLI — Build, test, run, and manage Xcode projects from Claude Code.
aco
Drive a live Appium session from Claude Code with the aco CLI — start/stop sessions, find elements, tap, swipe, type, screenshot, read page source, switch web contexts, and call platform mobile: extensions on iOS simulators/emulators and real devices.