Local-first completion-evidence system for AI-built apps: read-only audit, verifier-executed challenges, evidence-based 0-100 score, guided fixes, learning plan, CLI, and MCP.
This repository also configures its own agents. See what checkyourself tells them →
Skill Claude CodeCodex
Use this capability whenever the user asks for a production-ready plan, full-stack review, hardening audit, launch checklist, architecture critique, or multi-layer implementation. Trigger even when the user only says “make it production ready”, “ship this”, “harden it”, “review this stack”, or “what am I missing”.
Skill Claude CodeCodex
Use this capability when defining, refining, or reviewing a feature before implementation. Trigger on requirements, user stories, acceptance criteria, OpenAPI, AsyncAPI, JSON Schema, contracts, ADRs, RFCs, roadmap items, or “turn this idea into buildable work”.
Skill Claude CodeCodex
Use this capability for UI architecture, frontend performance, accessibility, routing guards, forms, client state, design-system integration, browser security boundaries, and user-facing AI interfaces. Trigger on React, Vue, Angular, Svelte, components, UI, a11y, WCAG, Core Web Vitals, forms, routing, lazy loading…
Skill Claude CodeCodex
Use this capability for REST, GraphQL, gRPC, webhooks, background jobs, service-layer design, middleware, validation, idempotency, pagination, API versioning, error handling, and backend business rules. Trigger on API, endpoint, controller, service, webhook, job, queue, validation, middleware, status code, OpenAPI…
Skill Claude CodeCodex
Use this capability for database schema design, SQL/NoSQL selection, migrations, indexing, query review, connection pooling, backups, object storage, event storage, data retention, and data lifecycle planning. Trigger on database, schema, migration, index, SQL, PostgreSQL, MySQL, MongoDB, Redis, S3, ORM, transaction…
Skill Claude CodeCodex
Use this capability for login, signup, session management, OAuth/OIDC, SSO, JWT, cookies, MFA, RBAC, ABAC, ReBAC, permission checks, service identities, and access reviews. Trigger on auth, login, signup, token, JWT, OAuth, OIDC, SSO, session, cookie, role, permission, MFA, 2FA, tenant access, or service account.
Skill Claude CodeCodex
Use this capability whenever multi-tenancy, tenant isolation, Row-Level Security, shared-schema SaaS, organization-scoped data, tenantid, database policies, cross-tenant access, or tenant-aware caching appears. Trigger even if the user only says “orgs”, “workspaces”, “teams”, “customers”, or “B2B SaaS”.
Skill Claude CodeCodex
Use this capability for threat modeling, secure code review, OWASP risk review, API abuse, input/output validation, injection, XSS, CSRF, SSRF, deserialization, security headers, encryption, secrets exposure, audit logging, privacy-by-design, or security acceptance gates.
Skill Claude CodeCodex
Use this capability for environment variables, config schemas, secrets, key rotation, feature flags, runtime toggles, service discovery, dotenv cleanup, secret scanning, config drift, and environment parity. Trigger on env, config, secret, API key, credentials, feature flag, toggle, runtime, staging, production…
Skill Claude CodeCodex
Use this capability for test plans, unit/integration/e2e tests, contract tests, property tests, snapshot strategy, mocks, test data, coverage, flaky tests, regression suites, quality gates, AI evals, and release verification. Trigger on test, QA, coverage, flaky, regression, e2e, integration, contract test, unit test…
Skill Claude CodeCodex
Use this capability for Git workflow, pull request policy, branch protection, CI/CD, build pipelines, release automation, dependency management, SBOM, provenance, SLSA, signing, container scanning, lockfiles, and supply-chain security. Trigger on CI, CD, pipeline, Git, branch, PR, release, dependency, SBOM…
Skill Claude CodeCodex
Use this capability for hosting decisions, platform selection, container deployment, serverless deployment, domains, DNS, TLS, staging/production environments, blue-green, canary, rolling deploys, migrations during deploy, health checks, smoke tests, and rollback plans.
Skill Claude CodeCodex
Use this capability for cloud architecture, IaC, Terraform/OpenTofu/Pulumi, Kubernetes, networking, VPC/VNet, IAM, compute, storage, managed databases, queues, cost controls, policy-as-code, drift detection, and infrastructure review.
Skill Claude CodeCodex
Use this capability for performance optimization, load tests, k6/JMeter/Locust plans, caching, Redis, CDN, Cache-Control, invalidation, rate limiting, quotas, token bucket, sliding window, 429 behavior, abuse protection, and cost-based throttling.
Skill Claude CodeCodex
Use this capability for load balancing, autoscaling, horizontal scaling, capacity planning, queues, workers, circuit breakers, retries, timeouts, backpressure, bulkheads, thundering herd control, graceful degradation, chaos testing, and resilience patterns.
Skill Claude CodeCodex
Use this capability for logging, metrics, traces, OpenTelemetry, error tracking, correlation IDs, dashboards, alerts, SLO burn alerts, runbooks, incident triage, root-cause analysis, postmortems, and on-call readiness.
Skill Claude CodeCodex
Use this capability for availability targets, SLAs, SLOs, SLIs, error budgets, backups, restores, RTO, RPO, failover, multi-region, DR, business continuity, recovery runbooks, chaos/game days, and resilience evidence.
Skill Claude CodeCodex
Use this capability for AI features, RAG, citations, model-agnostic prompts, evals, hallucination reduction, prompt injection, tool use, agent sandboxes, policy gates, audit trails, autonomy levels, human approval, and AI-assisted coding governance.
Skill Claude CodeCodex
Use this capability for PII, PHI, PCI, GDPR/CCPA-style obligations, consent, retention, deletion, DSAR/export, data classification, data residency, audit evidence, compliance controls, records of processing, and privacy-by-design reviews.
Skill Codex
Use when completed work makes claims — "done", "tests pass", "it works", "ready to launch" — that must be verified before they are believed. Re-derive each claim from the work itself and report CONFIRMED / REFUTED / UNVERIFIABLE with evidence. Fast claim-verification by default; the deterministic production-readiness…
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: