ulpi-io/autonomous-engineering
Skill Claude CodeCodex
Turn a raw feature request into a grounded, TESTABLE spec — autonomously. It recons the real repo and domain to ground every claim, drafts a spec (objectives, user-visible behavior, acceptance criteria, explicit non-goals, constraints, interfaces, risks), then runs a completeness-critic loop that adversarially hunts…
ulpi-io/autonomous-engineering
Skill Claude CodeCodex
Raise test health to a green, MEANINGFUL suite: find untested behaviors, write real tests, loop-until-green — with every added test MUTATION-CHECKED (break the code, the test must fail; tautologies rejected). Fails closed: never games the suite green (a skill-scoped hook mechanically blocks .skip/.only/suppressions in…
ulpi-io/autonomous-engineering
Skill Claude CodeCodex
Run the whole engineering lifecycle end-to-end from one request — spec → plan → build → simplify → test → review → performance → ship — as a single autonomous pass with ONE human approval (the plan) and hard-gated escalation for anything irreversible. It chains the auto- phase skills, carries a durable pipeline…
ulpi-io/autonomous-engineering
Skill Claude CodeCodex
The discipline that keeps an autonomous run from becoming a runaway: before any unattended loop or workflow, declare the five stop conditions — done-condition, hard cap, token/time budget, no-progress rule, escalation triggers — then hold the run to them and stop the instant one fires. Fails closed: a capped run…
ulpi-io/autonomous-engineering
Skill Claude CodeCodex
Make long autonomous work durable and resumable: a live .ulpi/runs/ .json status file (per-unit + per-phase state, atomic locked writes via the bundled scripts/checkpoint.mjs CLI) that a resume reads to SKIP everything already done — session-independent. Status writes are non-fatal observability. Use for any…
ulpi-io/autonomous-engineering
Skill Claude CodeCodex
Run a bounded, self-correcting loop that drives code toward a target state and STOPS honestly — until-green (validate → diagnose → minimal fix → re-run) or until-dry (find → act → re-find until N dry rounds). Every loop declares a termination set (done-condition, max iterations, budget, no-progress stop) and compiles…
ulpi-io/autonomous-engineering
Skill Claude CodeCodex
Cover a large work-list in parallel without losing correctness or honesty — scout the items inline, then run each through its stages concurrently (map, optionally reduce) via the Workflow tool, with concurrency caps, per-item isolation where items mutate files, and an explicit account of anything dropped. Use when the…
ulpi-io/autonomous-engineering
Skill Claude CodeCodex
Stand up a recurring scheduled agent for standing work (triage, monitoring, audits, digests): a self-contained IDEMPOTENT brief (each run wakes memory-less and must dedup prior work), a cadence matched to how often work actually arrives, a per-run BOUND, escalation rules, and a teardown condition. For durable…
ulpi-io/autonomous-engineering
Skill Claude CodeCodex
Wait on an EXTERNAL signal the harness can't notify you about — CI, a deploy, a queue, an endpoint — polling on a cache-aware cadence (≤270s active, ≥1200s idle, never 300s), bounded by a deadline, acting on the transition. Prefers a NATIVE wait/monitor capability when present; when polling must cross a turn it…
MCP server Claude CodeCodexCursor
Gives the agent up-to-date documentation and code examples for libraries and frameworks, fetched on demand so answers are not stuck at the model's training cutoff. Runs locally from the @upstash/context7-mcp npm package.
MCP server Claude CodeCodexCursor
MCP server "chrome-devtools", hosted remotely at localhost, as configured in ulpi-io/agent-library.
Agent Claude Code
Expert AWS and DevOps engineer specializing in cloud architecture, infrastructure as code with CDK/CloudFormation/Terraform, serverless applications, CI/CD pipelines, monitoring, and production-ready AWS deployments.
Agent Claude Code
Expert Docker and DevOps engineer specializing in containerization, Docker Compose, multi-stage builds, CI/CD pipelines, orchestration, and production-ready container deployments.
Agent Claude Code
Expert Express.js developer specializing in middleware architecture, RESTful APIs, queue systems with Bull, production-ready Node.js applications with Pino logging, and enterprise-grade server-side development.
Agent Claude Code
Expert Flutter developer specializing in widgets, navigation (GoRouter/Navigator 2.0), state management (Riverpod/Provider/Bloc), talker logging, testing with fluttertest, Firebase integration, and production-ready cross-platform mobile applications.
Agent Claude Code
Expert Laravel 12.x developer specializing in multi-database architectures (MySQL, Redis, DynamoDB), queue systems with Horizon, service layer patterns, API development, and production-ready enterprise applications.
Agent Claude Code
Expert Magento 2 developer specializing in module development, dependency injection, plugins, service contracts, REST/GraphQL APIs, Monolog logging, testing with PHPUnit, and production-ready e-commerce applications.
Agent Claude Code
Expert NestJS developer specializing in TypeScript, dependency injection, microservices architecture, queue systems with Bull/BullMQ, production-ready API development, and enterprise-grade server-side applications.
Agent Claude Code
Expert Next.js 14/15 developer specializing in App Router, React Server Components, Server Actions, streaming patterns, advanced caching strategies, and production-ready full-stack applications.
Agent Claude Code
Expert Remix developer specializing in loaders, actions, progressive enhancement, streaming patterns, authentication, and production-ready full-stack applications with Vite.
Skill Claude CodeCodex
Automatically orchestrate multiple specialized agents working in parallel when building independent features, modules, or performing separate investigations. Use when the task list contains 3+ unrelated features/tasks that don't share state, don't have execution dependencies, and can be understood independently. Match…
Skill Claude CodeCodex
Automatically orchestrate multiple specialized agents working in parallel to debug, diagnose, and fix independent problems across different subsystems. Use when encountering 3+ unrelated bugs, test failures, or issues in isolated modules that don't share root causes. Match each problem to the right expert agent…
Skill Claude CodeCodex
MANDATORY for starting any conversation or task. Establishes required workflows: discovering and using skills, invoking the Skill tool before announcing usage, performing brainstorming before coding, creating TodoWrite todos for all checklists, and selecting/invoking the correct specialized agent persona for the task…
Skill Claude CodeCodex
Use when user has just installed framework agents and CLAUDE.md contains generic examples - systematically discovers actual project patterns (custom commands, architecture decisions, team conventions) and updates CLAUDE.md and imported files with real project-specific information.