codexai-agentic-workflow

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work — guides completion of development work by presenting structured options for merge, PR, or cleanup

Use when a project has 50+ files, missing context, or explicit $codex-genome request; generates multi-layer project context to reduce hallucination.

Use when the user asks for art direction or a new visual identity; studio mode of codex-frontend-design.

Use for DESIGN.md visual identity contracts; author, scaffold, lint, diff, and export design contracts with the upstream spec and CLI.

Use when applying visual grammar, type, color, composition, and anti-slop to UI work.

Use when the task involves reading, creating, or editing `.docx` documents, especially when formatting or layout fidelity matters; prefer `python-docx` plus the bundled `scripts/render_docx.py` for visual checks.

Use when code changes may require documentation updates; maps git diff to candidate docs without auto-editing documentation.

Use for documents, reports, memos, guides, academic papers, or formal text that needs clear structure, reliable tone, formatting, and diagrams.

Use when frontend, backend, mobile, data, DevOps, or security work needs domain routing and at most four focused references.

Use before completion, PR, deploy, handoff, or when verifying code changes. Runs advisory or blocking checks and reports evidence.

Use when building or redesigning UI; pick fast path for a page/component or studio path for a new visual identity.

Use when implementing web UI in React, Next.js, Tailwind, CSS, or GSAP against an approved or fast-path brief.

Use when committing or pushing completed work; automates gate-aware conventional commits with optional signing and CI/CD checks.

Use when implementation needs isolation from the current workspace; creates git worktrees with safe directory selection and baseline verification.

Use before build, fix, debug, review, or docs implementation; converts prompts into structured intent JSON with goal, constraints, and routing.

Use when work is ambiguous or has multiple viable paths; compares options, assumptions, evidence, tradeoffs, and the best next action.

Use when starting any CodexAI task; load this baseline before routing, editing, or claiming work is done.

Use for complex coding requests that need a structured implementation plan with dependencies, checkpoints, and verification criteria.

Use for project memory, decisions, handoffs, genome, knowledge index, changelog, and patterns that must persist across sessions.

Use when asking project status, next priority, sprint health, blockers, deadlines, risk register, or daily brief generation.

Use when work needs deeper thinking, less generic output, repo evidence, tradeoffs, monitoring signals, or stronger quality discipline.

Use for role-scoped FE/BE/DevOps/Admin/QA project docs under .codex/project-docs to preserve micro-context across long projects.

Use at the start of a Codex task to inspect repo readiness, project profile, monorepo shape, role docs, spec status, knowledge index, and recommend the next workflow.

Use when work needs Scrum roles, ceremonies, backlog refinement, sprint planning, story delivery, release readiness, or role handoffs.

Use for security review, audit, hardening, compliance, DevSecOps, network, infrastructure, or application security with focused references.

Use for prototype, MVP, fullstack feature, from-scratch feature, or multi-domain work that needs a SPEC.md before planning or implementation. Do not use for tiny one-file edits.

Use when an approved plan has independent tasks ready for delegated execution with fresh subagents and two-stage review.

Use for bugs, test failures, broken behavior, or unexpected results; enforces 4-phase root-cause debugging before fixes.

Use before feature, bugfix, or refactor implementation when behavior can be tested; enforces Red-Green-Refactor discipline.

Use when writing UX contracts for flows, IA, states, and a11y before visual decoration.

Use when about to claim work is complete, fixed, or passing; run verification and read the output before any success claim.

Use after UI implementation for mechanical source checks and a rendered or fresh-eyes review.

Use after intent is known to route build, fix, review, debug, docs, or Scrum requests into ordered workflow steps with exit criteria.