Skip to content
Codexpiator

Ship code. Skip the sins.

Codexpiator is a Claude Code plugin: one router skill and eight topic skills covering frontend, backend, security, testing, architecture, devops, git/DX, and AI integration, plus three commands and a read-only review agent.

claude

> /plugin marketplace add emanuelegreco29/codexpiator

> /plugin install codexpiator

Already installed? Browse the Codex.

codexpiator router

you 

Real dispatch triggers from the router's own classification table. Ask any of these and Codexpiator hands you to the matching skill.

Built by what it documents

This site was generated by Codexpiator itself, from a single prompt, running inside Claude Code.

claude

> /codexpiator:codexpiator-setup do the setup and use /codexpiator:codexpiator to create a frontend for the plugin itself. You have full power.

1
prompt
Claude Sonnet 5, medium effort
no other model used
under 60% of a 5-hour session's token budget
session token usage

The Codex

Eight topic skills, each a set of single-purpose reference files. Expand one to see what's inside, or open its full page.

View as a page
  1. FEcodexpiator-frontendComponent architecture, styling, forms, routing, performance, a11y, SEO

    Frontend engineering guidance covering component architecture, state management, CSS/styling architecture, forms and validation, routing, responsive/mobile design, frontend performance, SEO/AI-visibility, and accessibility.

    component-architecture.md
    Structuring components, deciding what to extract, naming, folder layout
    state-management.md
    Choosing where state lives, local vs global, server vs client state
    styling-and-css.md
    Choosing a styling approach, design tokens, theming, responsive strategy
    forms-and-validation.md
    Building forms, validation timing, accessible error handling
    routing-and-navigation.md
    Route structure, code-splitting by route, auth-gated routes
    responsive-and-mobile.md
    Breakpoints, touch targets, mobile web specifics
    frontend-performance.md
    Bundle size, lazy loading, images, layout shift
    frontend-testing.md
    What to unit/integration/E2E test on the frontend
    accessibility.md
    Semantic HTML, ARIA, keyboard nav, contrast, focus management
    seo-and-launch-checklist.md
    Pre-launch pass: metadata, SEO tags, legal pages, conversion essentials
    seo-strategy-and-ai-visibility.md
    Deep SEO strategy + GEO: ranking in search and being cited by AI answer engines
    external-skills-map.md
    Whether a specialized design skill should lead instead
    Open codexpiator-frontend
  2. BEcodexpiator-backendAPI design, data modeling, auth, error handling, caching, resilience

    Backend engineering guidance covering API design and contracts, data modeling and databases, authentication and authorization implementation, error handling and logging, caching, background jobs and queues, resilience and rate limiting, backend performance, and backend testing.

    api-design.md
    Designing endpoints, naming, pagination, response shape
    data-modeling-and-db.md
    Schema design, indexing, migrations, SQL vs NoSQL
    auth-and-authorization.md
    Authentication mechanism, session/token trade-offs, password storage
    error-handling-and-logging.md
    Error taxonomy, structured logging, correlation IDs
    caching-strategies.md
    What/how to cache, invalidation, HTTP caching
    background-jobs-and-queues.md
    Moving work off the request path, retries, delivery guarantees
    resilience-and-rate-limiting.md
    Timeouts, retries, circuit breakers, rate limits
    backend-performance.md
    Profiling, DB bottlenecks, scaling direction
    backend-testing.md
    Unit vs integration tests, test data for the backend
    Open codexpiator-backend
  3. SECcodexpiator-securitySecure coding, injection defense, secrets, dependency & supply-chain risk

    Security guidance covering the secure coding checklist, authn/authz threat-model and hardening, input validation and injection defense, secrets and config management, dependency and supply-chain risk, infrastructure and access control, business-logic/webhook security, and security testing.

    secure-coding-checklist.md
    Quick OWASP-Top-10-mapped pass over any change
    authn-authz-patterns.md
    Login, sessions, MFA, password reset, IDOR/BOLA, privilege checks
    input-validation-and-injection.md
    SQL/NoSQL injection, XSS, CSRF, uploads, path traversal, SSRF
    secrets-and-config-management.md
    Credentials, .env files, secrets in git/JS/logs, cookies, storage
    dependency-and-supply-chain.md
    Vulnerable/malicious packages, CI/CD supply-chain risk
    infrastructure-and-access-control.md
    Cloud/DB permissions, admin routes, headers, CORS, rate limits
    business-logic-and-webhooks.md
    Payments, webhooks, business-logic abuse, race conditions
    security-testing.md
    How to actually test security controls, not just implement them
    external-skills-map.md
    When security-review should lead instead of this skill
    Open codexpiator-security
  4. QAcodexpiator-testing-qaTesting pyramid, TDD workflow, mocking strategy, CI quality gates

    General testing strategy and quality gates: the testing pyramid, TDD workflow, mocking and test data, and CI quality gates.

    testing-pyramid-and-strategy.md
    Deciding what level to test something at, avoiding a flaky suite
    tdd-workflow.md
    Following red-green-refactor while building a feature
    mocking-and-test-data.md
    What to mock, test data setup, avoiding over-mocking
    ci-quality-gates.md
    What should block a merge vs. only warn
    Open codexpiator-testing-qa
  5. ARCcodexpiator-architectureProject structure, design patterns, API contracts, scalability

    Software architecture guidance covering project structure conventions, design patterns catalog, API contracts and versioning, scalability trade-offs, and monolith vs microservices.

    project-structure-conventions.md
    Laying out folders, monorepo vs polyrepo
    design-patterns-catalog.md
    Deciding whether a pattern (DI, repository, strategy, observer) fits
    api-contracts-and-versioning.md
    Breaking-vs-compatible change policy, deprecation
    scalability-and-tradeoffs.md
    Deciding if/how to scale, avoiding premature scaling
    monolith-vs-microservices.md
    Deciding whether to split a service
    Open codexpiator-architecture
  6. OPScodexpiator-devopsCI/CD pipelines, environments, containers, observability, incidents

    DevOps guidance covering CI/CD pipelines, environments and config, containerization, observability and monitoring, incident response and rollback, and deployment platforms.

    ci-cd-pipelines.md
    Setting up or changing a build/deploy pipeline
    environments-and-config.md
    Managing dev/staging/prod parity and config
    containerization.md
    Writing or reviewing a Dockerfile
    observability-and-monitoring.md
    Setting up logs/metrics/traces/alerts
    incident-response-and-rollback.md
    Handling or preparing for a production incident
    deployment-platforms.md
    Choosing where/how to deploy
    Open codexpiator-devops
  7. GITcodexpiator-dx-gitBranching, commit & PR conventions, code review, repo hygiene

    Git workflow and developer experience guidance covering branching strategy, commit and PR conventions, code review checklist, documentation practices, and repo hygiene/onboarding.

    git-workflow-and-branching.md
    Choosing a branching strategy, rebase vs merge
    commit-and-pr-conventions.md
    Writing a commit message or PR description
    code-review-checklist.md
    Reviewing a PR
    documentation-practices.md
    Writing a README, comments, or an ADR
    repo-hygiene-and-onboarding.md
    Setting up a new repo or onboarding a contributor
    Open codexpiator-dx-git
  8. AIcodexpiator-ai-integrationLLM integration patterns, prompting, agent safety, MCP

    AI/LLM integration guidance covering LLM integration patterns, prompt engineering basics, agentic and tool-use safety and security, and MCP usage and recommendations.

    llm-integration-patterns.md
    Wiring an LLM call into a product feature
    prompt-engineering-basics.md
    Writing/iterating on a prompt
    agentic-and-tool-use-safety.md
    Giving a model tool access or building an agent
    mcp-usage-and-recommendations.md
    Deciding whether/which MCP server to use
    Open codexpiator-ai-integration

Commands & agent

Three commands drive the workflows above; a fourth, silent piece keeps the heavy multi-file reads out of your main conversation.

/codexpiator-audit

Full frontend + backend + security + testing audit

Dispatches the codexpiator-reviewer agent to read the relevant checklists and the whole project (or a given path), then returns one prioritized list of findings, most severe first. Nothing praised, nothing re-narrated.

/codexpiator-setup

Bootstrap baseline project structure and conventions

Applies the architecture and repo-hygiene conventions to a project: folder layout, .gitignore, .env.example, a README skeleton, and a CI config skeleton matched to the detected stack. It never overwrites a file that already exists without asking first.

/codexpiator-review

Review a diff or PR against Codexpiator's own checklists

Reviews the current diff or a given PR/branch against the code-review checklist plus whatever security, frontend, or backend checklist applies to what changed. Complements /code-review and security-review, and doesn't replace them.

R/O

codexpiator-reviewer

Isolated, read-only multi-file auditor

The subagent behind both audit commands. It reads the project (or a diff) and the matching checklists, then reports findings compactly. It has no write access and never touches code, so findings are always handed back to you or the user to act on.

Knows its own limits

For visual design, motion, or a deep security audit, Codexpiator would rather defer to a specialized skill than guess from condensed notes.

  1. 1

    Check what's available

    Codexpiator looks at the skills installed in the current session before it answers a design- or security-heavy request.

  2. 2

    Found it, hand off

    It invokes the specialized skill and lets it do the work, instead of duplicating that skill's content from memory.

  3. 3

    Missing: say so, then fall back

    It names the skill, names what it would have provided, and continues with its own checklist. You're never left blocked on an install.

A slice of the external skills registry Codexpiator checks against
SkillPrefer it when
security-reviewAny pre-merge or periodic security audit pass
frontend-designBuilding new UI from scratch that needs a strong visual point of view
design-motion-principlesAdding or reviewing animations, transitions, micro-interactions
web-design-guidelinesA pre-ship accessibility/UX guideline audit
redesign-existing-projectsModernizing an existing app without breaking it

Stack policy

Universal principles first, always, with call-outs for the stacks these skills see most often.

React / Next.js

  • Server Components / server-rendered data fetching by default
  • Colocate a component's styles, tests, and types with the component itself
  • Memoization is a targeted fix for a measured problem, not a default habit

Vue / Nuxt

  • Composition API for anything with non-trivial logic reuse
  • Composables are the React-hooks equivalent for shared stateful logic
  • Don't hand-roll what file-based routing and auto-imports already provide

Node.js / Express

  • Keep route handlers thin; business logic lives in plain, testable functions
  • Centralize error handling in one middleware, not repeated try/catch blocks
  • Async/await over callback chains

Python / FastAPI

  • uv, pdm, or poetry, never a bare, unpinned requirements.txt
  • Ruff, always, checked against the current recommended rule set
  • Pydantic models double as validation and documentation

Go

  • Explicit error returns over exceptions, checked at every call site
  • Small interfaces defined by the consumer, not the producer
  • context.Context threaded through any call chain that might cancel