engmahmoudhafez/hafez-development-system
A skills-first project operating system that inspects, resumes, builds, verifies, and hands off software work.
Route a software project from discovery through delivery, or recover and continue a partially built project using Hafez state, evidence, slices, verification, and handoffs. Use for end-to-end project work or when the correct current phase is unclear.
Add resumable Hafez project state and operating documentation to an existing repository without restructuring production code, installing packages, or running migrations.
Design, review, evolve, and verify API contracts across backend and frontend consumers, including OpenAPI, versioning, errors, pagination, idempotency, compatibility, generated clients, and contract drift.
Run a project continuously from its current state to the next verified milestone, automatically adopting safe Hafez metadata, fixing failures, delegating bounded work to helper models, reviewing their output, integrating approved changes, and stopping only at genuine decision or authority boundaries.
Review and evolve relational database schemas, migrations, indexes, queries, data integrity, and high-volume data changes safely. Use for Laravel/MySQL/PostgreSQL database work, migration planning, query performance, pagination correctness, and production-safe schema evolution.
Diagnose and repair reproducible project failures continuously using evidence-first debugging, regression tests, bounded delegation, and repeated verification until the failure is fixed or a genuine external decision is required.
Decompose an active project slice into bounded AI work units with explicit ownership, risk, parallelism, file scopes, verification, and worker tiers so a strong lead model can delegate safely to helper models.
Delegate bounded project work across Codex, Claude Code, Kimi Code, Antigravity, Zed, or compatible providers using structured task packets, isolated write scopes, and evidence-based returns.
Set up Hafez safely for an unfamiliar project or multi-repository workspace, explain the available installation modes, and select the first evidence-based action without changing application code.
Create a durable project handoff when work pauses, changes owner, becomes blocked, or reaches a verified release checkpoint.
Inspect an unfamiliar or partially built repository, infer its stack and current project focus from evidence, and recommend the next safe action without changing files.
Apply evidence-based Laravel API architecture and vertical-slice delivery inside a Hafez-managed project, for either greenfield work or gradual adoption of an existing codebase.
Build or adopt Nuxt and Vue applications in Hafez vertical slices with generated API contracts, mock-to-real adapters, explicit session states, RTL/i18n support, and frontend quality gates.
Plan a vertical project slice with business rules, acceptance criteria, dependencies, bounded work units, and verification before implementation begins.
Resume work in a Hafez-managed project by reconciling saved state with current Git evidence, gates, capabilities, blockers, and the latest handoff.
Review delegated AI work as the lead model before integration, checking scope, Git evidence, acceptance criteria, security, tests, and architectural fit, then explicitly approve or reject the exact delegated revision.
Perform evidence-based application security review and safe remediation for authentication, authorization, input handling, secrets, uploads, dependencies, tenancy, logging, rate limits, and common web/API vulnerability classes.
Run the project-defined quality gates, record durable evidence, and determine readiness without treating skipped or unavailable checks as success.
Model and inspect a software product spanning multiple repositories using explicit members and contract relationships, without inferring architecture from repository names or modifying member repositories.