codex

Systematic development workflow: Analyze → Plan → Execute → eLicit → eXamine. Use for ANY development task: features, bug fixes, refactoring, hotfixes. Triggers: "implement", "create", "build", "fix", "add feature", "refactor", "develop". Auto-detects project type (Laravel, Next.js, React, Swift) and loads framework-specific references. Enforces: files <100 lines, interfaces separated, SOLID principles, expert self-review, sniper validation. Modes: --auto (default), --manual, --skip-elicit

Auto-review skill for expert agents. After coding, expert applies elicitation techniques to self-correct before sniper validation. Inspired by BMAD-METHOD. Use when: an expert agent needs to self-review and self-correct code after the Execute phase, before sniper validation.

Use when marking a task as complete, finishing a feature, or claiming a bug is fixed. Ensures functional resolution is verified with evidence before closing. Do NOT use for: lint/type/code-quality validation (use code-quality / sniper AFTER functional verification passes).

Smart conventional commit with security validation, branch flow enforcement, and auto-detection. Use when committing changes, saving work, staging and committing, or choosing a conventional commit message.

Use when committing, branching, opening PRs, or deciding merge strategy. Covers GitHub Flow (default), trunk-based, branch naming conventions, squash vs rebase, branch lifecycle, and protected branch enforcement.

Universal post-commit actions. CHANGELOG update for all repos (git tag is created POST-MERGE, not here — see `commit` command Step 8). Plugin version bumping for marketplace repos. Triggered after any code commit (except wip/amend/undo).

Prisma 7 ORM with Rust-free client, 90% smaller bundles, TypedSQL, Omit API, and ESM-first architecture. Use when working with database, schema, migrations, queries, or relations.

Use when creating expert agents. Generates an agent .toml with the required fields, attached skills, and required sections.

Use when user requests creative work - creating features, building components, adding functionality, or modifying behavior. Activates BEFORE APEX Analyze phase to refine requirements through structured questioning.

Adversarial verification protocol for claims, plans, and root causes -- refute by default, fresh-context intake, sources-backed, bounded rounds. Runs SYSTEMATICALLY, by claim TYPE (not a stakes judgment), before reporting to the owner any of: a root-cause conclusion, a done/verified claim, an irreversible action (commit/deploy/rm/push), or a 2nd-time fix -- WHETHER inside an APEX task OR in plain conversation. Also runs systematically at every APEX eLicit round and every Verify gate, exactly like sniper runs systematically at eXamine, NO EXCEPTIONS. Do NOT use for: code correctness/lint/type validation (use code-quality/sniper).

Code quality validation with linters, SOLID principles, DRY detection, error detection, and architecture compliance across all languages. Use when: validating code quality after modifications — SOLID compliance, DRY duplication, linter errors, or architecture violations. Do NOT use for: verifying the original problem is functionally resolved (run verification FIRST — code-quality validates quality AFTER functional verification passes).

Codebase exploration techniques for rapid discovery, architecture analysis, pattern detection, and dependency mapping.

Efficient fuse-browser usage: web fetch, crawl, SERP, browser session, screenshot, webapp testing, console errors. Read this BEFORE any mcp__fuse-browser__* tool call — it routes fetch/crawl/serp vs live session vs visual capture and enforces the 4 ZERO-TOLERANCE rules.

Use when converting existing code to modular architecture. Detects Laravel (FuseCore or standard) / Next.js / React and applies correct modular patterns. Triggers: "modularize", "convert to modules", "migrate to modular", "restructure modules".

Summarize current pull request with diff, comments, and changed files. Use when reviewing PRs or before merging.

Audit React components for unnecessary useEffect patterns. Detects 9 anti-patterns from "You Might Not Need an Effect" and proposes fixes with severity levels. Use when: auditing React or Next.js components for unnecessary or unsafe useEffect usage.

Technical research methodology using Context7, Exa, and Sequential Thinking for documentation, best practices, and complex investigations.

Use when creating new skills, restructuring existing skills, or improving skill documentation. Generates SKILL.md + references/ structure with proper patterns.

Use when validating code quality after modifications. Runs sniper agent in isolated forked context for clean, fast validation.

Expert Astro 7 framework (stable, 7.0.9) — routing, output modes, middleware, Vite Environment API, single Rust compiler, Content Security Policy, Live Collections, Fonts API. Use when building Astro sites, configuring output, or upgrading from Astro 5/6.

Expert Astro Server Actions — defineAction, astro:actions, Zod validation, ActionError, HTML form actions, accept form, progressive enhancement, redirect patterns. Use when handling form submissions, mutations, or any server-side logic with type safety.

Image and asset optimization in Astro 7 — <Image />, <Picture />, getImage(), remote images, @astrojs/sharp, Fonts API, OG image generation with Satori, Cloudinary/Imgix. Use for any image optimization or asset handling task.

Expert Astro Content Layer API — content.config.ts, glob/file loaders, custom loaders, getCollection, getEntry, render(), Zod schemas, MDX, Remark/Rehype plugins. Use when managing structured content, blog posts, or any typed data collections.

Astro DB — defineDb, defineTable, column types, CRUD with db.select/insert/update/delete, db/config.ts, db/seed.ts, Turso for production, type-safety, integration with Astro Actions. Use for any database operation in an Astro project.

Deploying Astro 7 apps — @astrojs/cloudflare (Workers, D1, KV, R2), @astrojs/vercel (Serverless/Edge, Image CDN), @astrojs/netlify (Edge Functions), @astrojs/node (standalone), ISR patterns, edge middleware, skew protection. Use for any deployment configuration.

Use when implementing internationalization in Astro, configuring i18n routing, setting up locale strategies, using getRelativeLocaleUrl/getAbsoluteLocaleUrl, handling Astro.currentLocale, or adding hreflang tags with sitemap.

Expert Astro UI framework integrations — @astrojs/react, @astrojs/vue, @astrojs/svelte, @astrojs/solid-js, @astrojs/preact, @astrojs/alpinejs, @astrojs/lit, @qwikdev/astro, @analogjs/astro-angular. Setup, multi-framework config, usage patterns.

Expert Astro Islands Architecture — client:load, client:idle, client:visible, client:media, client:only, server:defer (Server Islands), fallback slots, transition:persist, prop serialization. Use when adding interactivity to Astro pages or rendering dynamic server content.

Use when configuring Content Security Policy (CSP) in Astro 7, setting security headers, managing script/style hashes, using nonces, or implementing experimentalStaticHeaders for adapter deployments.

SEO for Astro sites — meta tags, Open Graph, Twitter Cards, JSON-LD structured data, sitemap, RSS, robots.txt, canonical URLs, hreflang, Core Web Vitals. Use when optimizing search engine visibility or social sharing.

Astro Starlight documentation theme — setup, sidebar config, Pagefind search, dark/light mode, plugins (DocSearch, blog, openapi, typedoc, versions), multi-language, Content Layer API, llms.txt, customization. Use for building documentation sites.

Use when styling Astro components with scoped CSS, CSS Modules, Tailwind CSS, UnoCSS, or Sass. Covers class:list directive, global styles, CSS custom properties, and Vite-powered preprocessors.

Use when applying SOLID principles and clean architecture to Astro projects. Enforces files < 100 lines, src/interfaces/ for types, JSDoc on all exports, modular directory structure, and DRY enforcement.

Enrich auto-generated .cartographer/ maps with full descriptions from source files. Use when: cartography index descriptions are truncated, a new plugin/skill was just added, or after a session start regenerates the map.

Detect breaking changes in Codex updates by comparing the current API surface against the changelog. Maps impacts to specific plugin files. Use when: checking whether a Codex update breaks our plugin ecosystem (hooks, agent TOML frontmatter, plugin manifest schema, or skill format).

Scan the Codex changelog for new versions, features, and changes. Fetches official release notes, parses them, and generates a structured update report. Use when: checking for new Codex versions, features, or changes since the last known release.

Monitor community feedback on Codex via Exa search. Gathers sentiment, real-world usage patterns, bug reports, and feature requests from blogs, forums, and social media. Use when: gauging community sentiment, bug reports, or feature requests about Codex.

Detects optimal commit type from git changes. Use when analyzing commits, determining commit type, or before committing.

Optimization guide for the commit-pro commit workflow. Documents how to keep the plugin authoritative and reduce token usage.

Android mockups and handoff specs — Material 3 Expressive type scale (baseline + emphasized), full color-role system (45 roles incl. surface-container ramp + dynamic color), elevation tokens, shape scale, window size classes, FAB tiers, motion, device-framed HTML mockup, and a Compose-ready handoff spec. Produces tokens + mockup only, never Compose code.