mnzralee/claude-multi-agent-architecture
Settings file Claude Code
claude-multi-agent-architecture: base project settings. Safe-by-default permissions, real executable hooks, no secrets. Per-agent model and tool scoping live in .claude/agents/ .md frontmatter. Personal and machine-specific overrides go in settings.local.json (gitignored). The Stop verification-gate hook is wired.
mnzralee/claude-multi-agent-architecture
Skill Claude CodeCodex
Design RESTful APIs with consistent conventions for resource URLs, response shapes, HTTP semantics, versioning, and security across every service in the project.
mnzralee/claude-multi-agent-architecture
Skill Claude CodeCodex
Backend development skill for microservices following Clean Architecture, CQRS with a transactional outbox, the repository/use-case pattern, and a Testing-Trophy strategy.
mnzralee/claude-multi-agent-architecture
Skill Claude CodeCodex
Switch Claude to telegraphic compressed-prose mode to reduce token usage in long sessions. Drops filler, articles where unambiguous, courtesy words, and meta-commentary. Preserves code, paths, identifiers, negations, numbers exactly. Use when context window pressure matters or the developer asks for terse mode. Do not…
mnzralee/claude-multi-agent-architecture
Skill Claude CodeCodex
Git Commit Skill for creating well-structured, atomic commits following conventional-commits discipline.
mnzralee/claude-multi-agent-architecture
Skill Claude CodeCodex
A generator-plus-critic loop that improves output against an explicit rubric before acceptance. Use when you have clear acceptance criteria and iteration measurably helps (specs, prompts, important docs, tricky implementations). Includes a seed eval set for regression-testing prompt and rule changes.
mnzralee/claude-multi-agent-architecture
Skill Claude CodeCodex
Drive Playwright against a running application step-by-step, screenshot, analyze, decide, act. Applies to any web frontend regardless of stack.
mnzralee/claude-multi-agent-architecture
Skill Claude CodeCodex
Plan a new module or feature area end-to-end using a structured Explore, Plan, and Document workflow before any code is written.
mnzralee/claude-multi-agent-architecture
Skill Claude CodeCodex
Coordinate complex development tasks using hierarchical agent teams with supervisors, prompt writers, debuggers, and work recorders. Encodes the TDD-with-agents protocol, premature-completion red flags, and cross-agent file-race avoidance.
mnzralee/claude-multi-agent-architecture
Skill Claude CodeCodex
The Explore to Plan to Code to Commit workflow for any non-trivial change. Forces understanding and an explicit plan before edits, with a one-sentence skip heuristic for trivial work. Use when starting a feature, a refactor, or any change whose steps are not obvious. Pairs with plan mode.
mnzralee/claude-multi-agent-architecture
Skill Claude CodeCodex
Pull Request skill for creating well-structured, consistently formatted PRs using the GitHub CLI.
mnzralee/claude-multi-agent-architecture
Skill Claude CodeCodex
Endless-iteration discipline for long-arc goals. Bounded iterations with /clear between, persistent state, a 9-agent review-board escalation when stuck, brownfield-first audits, show-your-work artifact requirement, two-failure-clear trigger, archetype-filename serialization, cross-arc isolation, and measurable 10/10…
mnzralee/claude-multi-agent-architecture
Skill Claude CodeCodex
Run the multi-wave Software Engineering Review Board (SERB) over a proposed plan before execution. A read-only board of specialist agents gathers ground truth, critiques from architecture/testing/security/devops/quality lenses, then synthesizes a refined, executable plan with a go/no-go. Use for high-stakes or…
mnzralee/claude-multi-agent-architecture
Skill Claude CodeCodex
Code review skill covering security, correctness, type safety, and maintainability for any software project.
mnzralee/claude-multi-agent-architecture
Skill Claude CodeCodex
Methodical problem-solving approach for diagnosing and resolving code issues in any stack before attempting a fix.
mnzralee/claude-multi-agent-architecture
Skill Claude CodeCodex
Test-Driven Development workflow for implementing features with tests first; enforces the two-commit audit trail (failing-test commit, then green commit) and shows-your-work verification for agent-driven work.
mnzralee/claude-multi-agent-architecture
Skill Claude CodeCodex
Comprehensive five-level validation checklist that every agent must pass before declaring any task or work package complete.
mnzralee/claude-multi-agent-architecture
Skill Claude CodeCodex
Structured multi-phase verification of implementations before deployment, covering static analysis, testing, functional checks, security, and documentation.
mnzralee/claude-multi-agent-architecture
Skill Claude CodeCodex
Transform development sessions into compelling engineering stories that capture not just what happened, but why it mattered and what was learned. Covers journal discipline, session templates (planning, bug hunt, feature build, multi-agent orchestration), and the mandatory end-of-day deliverable summary.
mnzralee/claude-multi-agent-architecture
Instructions file CodexOpenCode
Instructions for mnzralee/claude-multi-agent-architecture, covering agents.md - cross-tool agent configuration, project overview, conventions, code style (illustrative defaults; adapt to your stack) and git.
mnzralee/claude-multi-agent-architecture
Instructions file
Instructions for mnzralee/claude-multi-agent-architecture, covering quick start (every session), common commands, when rules conflict, multi-agent orchestration and reasoning effort.