Local-first agent platform: board + role agents + agent CLI runs (Claude Code, Cursor, Antigravity, OpenCode) or local and API models (Ollama, LM Studio), all on your own Mac
This repository also configures its own agents. See what tasktrooper tells them →
Skill Claude CodeCodex
Use when touching Unity per-frame code, spawning, physics queries, UI updates or rendering setup - profiling with numbers, zero-GC hot paths (caching, NonAlloc queries, no LINQ/closures/boxing, TMP SetText), ObjectPool, allocation tests, Burst/Jobs for bulk math, and rendering/physics settings that cost frames.
Skill Claude CodeCodex
Use when writing or restructuring Unity C# code - assembly definitions and dependency direction, small components with cached references, ScriptableObjects for data and events, DI instead of singletons, Input System, Addressables, serialization safety and Unity 6 API changes.
Skill Claude CodeCodex
Use when writing or running Unity tests - Unity Test Framework EditMode vs PlayMode, test assembly definitions, testing plain C# and ScriptableObjects, PlayMode scene/physics/input tests, batchmode CLI with result XML, coverage, and the dotnet test fallback when no editor is installed.
Skill Claude CodeCodex
Use when writing Unreal Engine 5 C++ - the gameplay framework classes and where logic belongs, UObject/AActor/UActorComponent lifecycle, UPROPERTY/UFUNCTION and GC-safe pointers (TObjectPtr, TWeakObjectPtr), subsystems, the C++/Blueprint boundary, Enhanced Input, tick discipline, and compiling from the command line.
Skill Claude CodeCodex
Use when working with Unreal's Gameplay Ability System - when GAS is worth it, where the AbilitySystemComponent lives and how it is initialised on server and client, AttributeSets with correct clamping and replication, GameplayEffects and execution calculations as data, abilities with commit/end, gameplay tags…
Skill Claude CodeCodex
Use when building a 3D web game with three.js, Babylon.js or PlayCanvas - render loop and delta per library, fixed-step physics with Rapier or Havok, explicit dispose of GPU resources, instancing and draw-call budgets, glTF with Draco/meshopt/KTX2, pixel ratio and resize, WebGPU opt-in, React Three Fiber notes, and…
Skill Claude CodeCodex
Use when working on any browser game (Phaser, PixiJS, three.js, Babylon.js, PlayCanvas, Excalibur, KAPLAY) - requestAnimationFrame with clamped delta and visibility pause, zero-allocation frame loops, measuring in DevTools, bundle and asset size budgets, Vitest with seeded RNG and injected time, and a seeded…
Skill Claude CodeCodex
Use when your context carries "The approved design this task builds" - comparing the running UI with the approved hand-off and mockup at each width and state, evidence screenshots attached to the task, Blocker/High/Medium/Nitpick findings and which of them fail the round.
Skill Claude CodeCodex
Use when the diff adds or changes an endpoint, resolver, RPC, job or query that takes an object id, a role check, a request binding or a tenant filter - BOLA/IDOR, function-level authorization, mass assignment and tenant scoping.
Skill Claude CodeCodex
Use when the diff touches login, password storage, sessions, cookies, JWT verification, OAuth/OIDC flows, password reset, webhook signatures, API keys or headers used to identify a caller.
Skill Claude CodeCodex
Use when the diff changes a GitHub Actions workflow, a reusable action, a Dockerfile or compose file, Terraform/HCL, Kubernetes manifests or Helm values, or a cloud OIDC trust policy - judged only where concretely exploitable.
Skill Claude CodeCodex
Use when you have a candidate security finding and before it goes in a comment - restate it, prove reachability, impact and a concrete exploit, apply triage dismissals, then the self-refute pass naming attacker and victim.
Skill Claude CodeCodex
Use when reviewing game code in C#, GDScript or C++ (Unity, Godot, Unreal, custom engines) - client vs server authority, RPC and packet validation, in-app purchases and economy, save and replay files, mod and script loading, secrets in client builds.
Skill Claude CodeCodex
Use when reviewing Go changes - net/http and Fiber handlers, database/sql and GORM queries, os/exec, filepath and os.Root, html/template, crypto, TLS and SSH clients, JSON binding.
Skill Claude CodeCodex
Use when the diff builds a query, a shell command or argv, a subprocess environment, a template, an XML parse, an eval or a deserialization from data that may be attacker-controlled - SQL/NoSQL, OS command, argument, env-var, template and code injection, XXE, unsafe deserialization.
Skill Claude CodeCodex
Use when reviewing Java or Kotlin server changes on Spring or Quarkus - security config and method security, JPA/JPQL and JdbcTemplate queries, request binding, deserialization, XML parsers, SpEL, templates, Actuator, JNDI and reflection.
Skill Claude CodeCodex
Use when the diff calls a model, exposes a tool to one, feeds it fetched or user content, renders or executes its output, stores agent memory, or changes agent settings, MCP configs, tool policies or prompt files - including this platform's own agents.
Skill Claude CodeCodex
Use when reviewing iOS (Swift), Android (Kotlin) or Flutter changes - token storage, ATS and cleartext config, TLS trust, exported components, deep links, WebView JavaScript bridges, certificate pinning claims, secrets bundled in the app, Firebase rules.
Skill Claude CodeCodex
Use when reviewing Node.js or TypeScript server code - Express/Fastify/Nest handlers, Next.js server actions and route handlers, childprocess, ORM raw queries, prototype pollution, template engines, JWT and outbound HTTP clients.
Skill Claude CodeCodex
Use when the diff builds a filesystem path from input, extracts an archive, accepts an upload, serves a file or writes a temp file - traversal, symlinks, zip-slip, upload type and served content-type.
Skill Claude CodeCodex
Use when reviewing Python changes - Django, Flask and FastAPI handlers, subprocess, SQL, Jinja2, format strings, and data/ML code that loads pickles, models, notebooks or remote model code.
Skill Claude CodeCodex
Use when you want deterministic evidence for a review - which already-installed scanners may be run against the checkout, their exact read-only invocations, how to triage their output, and what must never be run or installed.
Skill Claude CodeCodex
Use when the diff adds or moves a credential, logs or returns data, builds a URL or argv with a token, generates a random value, encrypts, signs, hashes, configures TLS or writes a credential file.
Skill Claude CodeCodex
Use when starting any security review in codereview - risk-tier each changed file, read the repo's own security patterns, compare, then trace source to sink, including removed guards and blast radius.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: