LLM Mart Basic
@llm-mart · Joined Jun 2026
Default minimum deployment target for Apple-platform Swift Apps — iOS 26 / macOS 26 on the Xcode 26 toolchain (Swift 6 language mode) — and how to deviate down (iOS 18 / 17) or up. Use when starting a new Apple-platform project, writing the Package.swift `platforms:` list, decidi
Use when a repo goes public or open-sources, when a CloudKit server-to-server PEM, ASC API `.p8`, APNs key, signing `.p12`, or provisioning profile first enters the pipeline, or when asked how to prevent or respond to a secret leak (gitleaks, lefthook, GitHub Secret Scanning, `gi
Choose analytics and metrics sources for a solo / small-team Apple app and decide whether a third-party tracking SDK is justified. Use when picking an analytics SDK; when asked "should I add Firebase / Mixpanel / Amplitude / TelemetryDeck"; when asked what App Store Connect Analy
Use when wiring a value that ships in the binary but must stay out of public-repo diffs until launch (AdMob `GADApplicationIdentifier` / banner unit ID, a third-party SDK app key) into an Apple build via xcconfig, Info.plist `$()` substitution and a guarded `Bundle.main` read, in
Committed `.ckdb` as the CloudKit schema source of truth, with `xcrun cktool` export / validate / import against Development and Production promotion kept as a Console-only gate. Use when a CloudKit-backed persistence layer adds or edits a record type, field, or index; before any
Wire and debug launch-the-app XCUITest E2E tests in a Tuist project: a native `.uiTests` target needs its own scheme with `testAction: .targets([...])`, not `.xctestplan` membership; a name that does not collide with an SPM UITests package target; window-frame-anchored clicks for
Audit an iOS/iPadOS app's live behavior on a booted Simulator by driving it with `idb` (accessibility tree, taps, screenshots) to find bugs a fixed-frame snapshot cannot show — navigation and modal flows, back-stack, completion screens, safe-area / Dynamic Island clipping, offlin
Implement and audit VoiceOver (`accessibilityLabel` / `Value` / `Hint`, traits, `accessibilityElement(children:)`, `AccessibilityNotification`), Dynamic Type (text styles, caps, AX5), 44pt touch targets, and Reduce Motion / Transparency for SwiftUI and UIKit, with a WCAG 2.2 mapp
Generate a single-file HTML iOS design mockup from a written spec (PRD / requirements / user stories) — a designer-style user-flow canvas: iPhone frames, SVG navigation arrows, a design-tokens panel. Use when asked to "turn this spec into a mockup", "show me the screens", "visual
Measure and fix iOS/macOS performance with Instruments (Time Profiler, Allocations, Hangs, App Launch), `xctrace` in CI, `OSSignposter`, MetricKit field telemetry (`MXMetricManager`, `MXHangDiagnostic`), `XCTMetric` baselines, launch time, memory footprint, binary size, and crash
Use when a build must reach TestFlight without Xcode Cloud (quota, outage, CI not wired yet), or when a local `xcodebuild archive` / `-exportArchive -exportOptionsPlist` / `xcrun altool --upload-package` command fails — `ExportOptions.plist` keys (`method`, `destination`, `teamID
Use when pinning binary CLI / build tools (swiftlint, xcbeautify, gitleaks, lefthook) with mise so dev machines and CI share one `.mise.toml` — choosing mise vs asdf / Homebrew / manual, writing `.mise.toml` (`aqua:` / `github:` backends, `os = ["macos"]` guards), running `mise t
Use when adding, upgrading, or auditing a third-party monetization SDK (AdMob / Google Mobile Ads incl. UMP consent; the same contract applies to any other ad or subscription SDK), or when a PR adds `import GoogleMobileAds` outside the single live-bridge file, breaks `canImport`
Set up logging for an Apple-platform Swift app with `os.Logger` and decide its `subsystem` / `category` naming and `privacy:` interpolation. Use when choosing a logging library (`os.Logger` vs swift-log `import Logging` vs CocoaLumberjack); when writing the first `Logger(subsyste
Default StoreKit 2 architecture for a single non-consumable IAP (Remove Ads, Pro Unlock): `StoreKitBridge` isolates `import StoreKit` to one Live file; launch-time `Transaction.updates`; `Transaction.currentEntitlements` for unlock state; `finish()` timing; `AppStore.sync()` rest
Design injectable seams so Swift services can be swapped for fakes in tests. Use when a type reaches for `URLSession.shared`, `Date()`, `UUID()`, `random(in:)` or a singleton; when asked "how do I inject CloudKit / network / clock" or "should this be a singleton"; when choosing c
Default test stack for new Apple-platform Swift projects — Swift Testing (`@Test` / `#expect`, no XCTest), pointfreeco/swift-snapshot-testing with baselines in git, CI policy for fakes (no live CKContainer / GKLocalPlayer / network in tests). Use when creating the first test targ
Swift 6 language mode with complete concurrency checking from the first line of a new Apple-platform project; `MainActor` default isolation per the Xcode 26 template, `Sendable` only where a value crosses an isolation boundary; `@preconcurrency import` for lagging deps. Use when
Default module shape for Apple-platform Swift Apps — one Swift Package, multiple targets, a thin App target (`@main` + DI root), CloudKit / GameKit / StoreKit imports confined to service targets, one test target per production target. Use when laying out targets in Package.swift,
Checklist of SwiftUI interaction bugs that pass code review but break at runtime: tap-target shrink under `.buttonStyle(.plain)`, inert sidebar `Label`s, `horizontalSizeClass` on Mac, `.task` re-fire, blank `fullScreenCover(isPresented:)` race, stale `dynamicTypeSize` in modals,
Fourteen posts of being wrong in production, compressed to checkboxes
Healthy nodes, a quiet network, 300 restarts in three days, and a latency budget measured in milliseconds
Discovery worked. Ping worked. Every TCP connection timed out, and later the tunnel only worked when someone had a terminal open.
Every VM came back. The cluster did not. Declarative systems converge on config, and the datapath isn't config.
A surprising share of AI-in-the-terminal failures aren't the AI. They're zsh, and a version of bash from 2006.
A Claude Code plugin turns standalone project configuration into a namespaced, installable extension that teams and communities can update as one unit.
None of the safety came from the model. It came from six boring habits.
Skills package instructions and references. Subagents run work in a separate context and return results. They solve different problems and can be composed deliberately.
Six hours in, one step left, everything green, and the incident that didn't happen
CLAUDE.md carries persistent project context. Skills load reusable procedures when relevant. Separating stable facts from task-specific workflows keeps both easier to maintain.
Twenty minutes recovering secrets that never existed, and the one sentence from a human that ended it
An API request routing a model's tool call through an approval gate to a remote MCP server
31 config keys, two audits, and why the first one was wrong in both directions
The official MCP Registry stores standardized server metadata rather than package code. Publishers verify a namespace, describe installation or remote access, and submit immutable versions.
Everyone looks at the Dockerfile. The file that actually leaked the key was the project file.
Remote MCP authorization uses established OAuth standards, but secure integration still requires issuer validation, least-privilege scopes, protected token handling, and server-side enforcement.
"Copy it over and switch the reference" is two steps, and the outage lives in the one nobody checks
stdio fits local processes and prototypes. Streamable HTTP fits hosted services and shared integrations. The right choice follows where the capability runs and who must reach it.
The most important rule wasn't about what I could change. It was about what I was allowed to display.
Tools perform operations, resources expose readable context, and prompts provide reusable templates. Choosing the correct primitive makes an MCP server easier to understand and govern.
/chore
Chore
This is the lane for changes with no behavior to test-drive — prose edits, a version bump on an
/cleanup
Cleanup
Use this after a pull request has merged but your local checkout is still on the topic branch.
/commands
Commands
Prints the public command catalog straight from `COMMANDS.md` — the plugin's own single source
/commit
Commit
This is the single entry point for turning staged work into a commit — nothing in codeArbiter
/conflict
Conflict
The protocol for a rule conflict — not a skill route, an orchestrator-level halt. When two sources
/context-check
Context check
An optional, on-demand drift audit for the bypass case: a merge, a direct push, or a manual edit
/create-context
Create context
This is the populator for a project that already has code to read. Instead of interviewing you about
/debug
Debug
`/ca:debug` investigates an unexplained symptom and returns a cited diagnosis or a bounded
/decompose
Decompose
This is the populator for a project that has no code yet to read. Rather than guessing at
/doctor
Doctor
Proves the install is actually enforcing, rather than just present. codeArbiter's worst failure
/feature
Feature
This is the standard entry point for new work with a human in the loop at every step. A short
/fix
Fix
This is the entry point for an authorized repair of a confirmed code defect. Give the observed
/init
Init
This is how a repository opts into codeArbiter for the first time. It writes the root-level state
/metrics
Metrics
A bare-numbers governance glance — three metrics, each with a trend arrow against the prior
/override
Override
The sanctioned, logged escape hatch. A routine gate — a lint rule, a style check, a non-security
/pr
Pr
Explicit PR entry and a direct request to open a PR use the same branch-finishing owner.
/preview
Preview
A zero-onboarding, read-only dry-run of the reviewer fleet against whatever is currently
/prune
Prune
This is a Feature Forge preview command — the after-each-turn service ships **off** by default and
/reconcile
Reconcile
Compares architectural records with the scaffold and prior decisions using SMARTS.
/refactor
Refactor
This is the lane for moving or reshaping code without changing what it does — a rename, an extract,
Atom Agent, Open-Source Governed AI Agent Platform for Self-Hosted Automation
13 views 0 likesThe agent engineering intelligence harness, optimized tools, memory system, subagents and mixture of models packages ⚚
16 views 0 likesSesori iOS/Android app and the Sesori Bridge CLI — drive Claude, Codex, OpenCode, Cursor, Pi, OMP, Hermes coding sessions from your phone
14 views 0 likes🧠 RepoBrain (formerly Antigravity) — Give your repo a brain. ChatGPT for your codebase: works in Claude Code, Cursor, Codex, Windsurf & more.
14 views 0 likesUse ChatGPT (Codex), Claude, and Grok (X Premium) subscriptions as DeepSeek Harness LLM providers — OAuth login in the web UI, no API keys
15 views 0 likesLatitude is the open-source AI monitoring platform.
16 views 0 likesOpen-source AI browser agent for Chrome and Firefox (monorepo) 🧠
16 views 0 likesOfficial Model Studio CLI(阿里云百炼 CLI)built for AI Agent frameworks, exposing models, search, multimodal, and workflow capabilities as structured tool calls.
15 views 0 likesCurated DeepSeek Harness (DSH) plugins, extensions, tools, skills, clients, runtimes, integrations, and verified references — English and Chinese.
16 views 0 likesTurn papers, code, and docs into presentation-ready, natively editable PPTX in Codex / Claude Code. Native charts and equations, speaker notes, click-build anim…
14 views 0 likesGrix : Work with agents like talking to people.
25 views 0 likesLocal First Ai Agent. Optimized for Local Ai models. Long context window. Proper tools callings. Runs privately on your device.
26 views 0 likesModel Context Protocol server that integrates AgentQL's data extraction capabilities.
15 views 0 likesAI that ships your tickets.
14 views 0 likesMetadata-driven CLI for AI Agent Bots — 48 operations across 7 domains, structured JSON envelope I/O, zero interactive prompts.
12 views 0 likesAn open-source, extensible, self-hosted agent workspace with multi-runtime support for Codex, Claude Code, and more, plus reusable local apps for custom interfa…
14 views 0 likesOpen-source Windows desktop client and GUI for DeepSeek Harness — zero-setup installer with Codex, plugins, skills, SSH, mobile remote access, and 11 skins.
12 views 0 likesThe open-source AI workbench for scientific research
15 views 0 likesDeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.
15 views 0 likesA Fully free agentic browser driver for AI , few tools, full control, real stealth, top-tier token efficiency.
12 views 0 likes