greenfield

name	greenfield
description	[Planning] Use when you need to start a new project from scratch with full waterfall inception — idea, research, domain modeling, tech stack, and implementation plan.

Codex compatibility note:

• Invoke repository skills with $skill-name in Codex; this mirrored copy rewrites legacy Claude /skill-name references.
• Prefer the plan-hard skill for planning guidance in this Codex mirror.
• Task tracker mandate: BEFORE executing any workflow or skill step, create/update task tracking for all steps and keep it synchronized as progress changes.
• User-question prompts mean to ask the user directly in Codex.
• Ignore Claude-specific mode-switch instructions when they appear.
• Strict execution contract: when a user explicitly invokes a skill, execute that skill protocol as written.
• Subagent authorization: when a skill is user-invoked or AI-detected and its protocol requires subagents, that skill activation authorizes use of the required spawn_agent subagent(s) for that task.
• Do not skip, reorder, or merge protocol steps unless the user explicitly approves the deviation first.
• For workflow skills, execute each listed child-skill step explicitly and report step-by-step evidence.
• If a required step/tool cannot run in this environment, stop and ask the user before adapting.

Codex Project-Reference Loading (No Hooks)

Codex does not receive Claude hook-based doc injection. When coding, planning, debugging, testing, or reviewing, open project docs explicitly using this routing.

Always read:

• docs/project-config.json (project-specific paths, commands, modules, and workflow/test settings)
• docs/project-reference/docs-index-reference.md (routes to the full docs/project-reference/* catalog)
• docs/project-reference/lessons.md (always-on guardrails and anti-patterns)

Situation-based docs:

• Backend/CQRS/API/domain/entity changes: backend-patterns-reference.md, domain-entities-reference.md, project-structure-reference.md
• Frontend/UI/styling/design-system: frontend-patterns-reference.md, scss-styling-guide.md, design-system/README.md
• Spec/test-case planning or TC mapping: feature-docs-reference.md
• Integration test implementation/review: integration-test-reference.md
• E2E test implementation/review: e2e-test-reference.md
• Code review/audit work: code-review-rules.md plus domain docs above based on changed files

Do not read all docs blindly. Start from docs-index-reference.md, then open only relevant files for the task.

Quick Summary

Goal: Guide greenfield project inception from raw idea to an approved, implementable project plan using a full waterfall process.

Workflow (16 steps):

1. Discovery ($idea) — Interview user about problem, vision, constraints, team skills, scale. DO NOT ask about tech stack — keep business-focused.
2. Market Research ($web-research) — WebSearch for competitors, market landscape, existing solutions
3. Deep Research ($deep-research) — WebFetch top sources, extract key findings
4. Business Evaluation ($business-evaluation) — Viability assessment, risk matrix, value proposition
5. Domain Analysis & ERD ($domain-analysis) — Bounded contexts, aggregates, entities, ERD diagram, domain events. Validate every context boundary with user.
6. Tech Stack Research ($tech-stack-research) — Derive technical requirements from business + domain analysis. Research top 3 options per stack layer (backend, frontend, database, messaging, infra). Detailed pros/cons matrix, team-fit scoring, market analysis. Present comparison report for user to decide.
7. Architecture Design ($architecture-design) — Research and compare top 3 architecture styles (Clean, Hexagonal, Vertical Slice, etc.). Evaluate design patterns (CQRS, Repository, Mediator). Audit against SOLID, DRY, KISS, YAGNI. Validate scalability, maintainability, IoC, technical agnosticism. Present comparison with recommendation. Harness output required: produce a "Scaffold Handoff — Harness Plan" table in the architecture report: (a) feedforward guides to create (AGENTS.md sections, skill activation rules, pattern catalog), (b) computational feedback sensors to install (linter, formatter, pre-commit, CI), (c) inferential feedback sensors to configure (review skills, AI gates). This table feeds $scaffold → $linter-setup → $harness-setup.
8. Implementation Plan ($plan-hard) — Create phased plan using confirmed tech stack + architecture + domain model
9. Security Audit ($security) — Review plan for OWASP Top 10, auth patterns, data protection concerns
10. Performance Audit ($performance) — Review plan for performance bottlenecks, scalability, query optimization
11. Plan Review ($plan-review) — Full plan review, risk assessment, approval
12. Refine to PBI ($refine) — Transform idea + reviewed plan into actionable PBI with acceptance criteria
13. User Stories ($story) — Break PBI into implementable user stories
14. Plan Validation ($plan-validate) — Interview user with critical questions to validate plan + stories
15. Test Strategy ($tdd-spec) — Test pyramid, frameworks, spec outline
16. Workflow End ($workflow-end) — Clean up, announce completion

Key Rules:

• PLANNING ONLY: never implement code
• Every stage saves artifacts to plan directory
• MANDATORY IMPORTANT MUST ATTENTION every stage requires a direct user question validation before proceeding
• Delegate architecture decisions to solution-architect agent
• Present 2-4 options for every major decision with confidence %
• Business-First Protocol: Tech stack is NEVER asked upfront. Business analysis (steps 1-5) + domain modeling (step 6) must complete first. Tech stack is derived from requirements through research and presented as a comparison report with options.
• MANDATORY IMPORTANT MUST ATTENTION architecture design MUST produce a "Scaffold Handoff — Harness Plan" table covering: feedforward guides, computational sensors ($linter-setup handles install), and inferential sensors ($harness-setup configures). The scaffold + linter-setup + harness-setup triad are NON-SKIPPABLE infrastructure — code without a harness accumulates technical debt from day one.

Entry Point

This skill is the explicit entry point for the greenfield-init workflow.

When invoked:

1. Activate the greenfield-init workflow via $workflow-start greenfield-init
2. The workflow handles step sequencing, task creation, and progress tracking
3. Each step delegates to the appropriate skill (idea, web-research, domain-analysis, tech-stack-research, etc.)
4. The solution-architect agent provides architecture guidance throughout

When to Use

• Starting a brand-new project from scratch
• No existing codebase (empty project directory)
• Planning a new application before writing any code
• Want structured waterfall inception with user collaboration at every step

When NOT to Use

• Existing codebase with code (use $plan-hard or $feature instead)
• Bug fixes, refactoring, or feature implementation
• Quick prototyping (use $cook-fast instead)

Output

All artifacts saved to plan directory:

plans/{id}/
  research/
    discovery-interview.md
    market-research.md
    deep-research.md
    business-evaluation.md
    domain-analysis.md
    tech-stack-comparison.md
    architecture-design.md
  phase-01-domain-model.md
  phase-02-tech-stack.md
  phase-02b-architecture.md
  phase-03-project-structure.md
  phase-04-test-strategy.md
  phase-05-backlog.md
  plan.md (master plan with YAML frontmatter)

After completion, recommend next step: $cook to scaffold the project structure.

Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).

---

MANDATORY IMPORTANT MUST ATTENTION break work into small todo tasks — one per workflow step. MANDATORY IMPORTANT MUST ATTENTION validate with user at EVERY step — never auto-decide. MANDATORY IMPORTANT MUST ATTENTION add a final review todo task to verify work quality and identify fixes/enhancements.

---

MANDATORY IMPORTANT MUST ATTENTION use task tracking to break ALL work into small tasks BEFORE starting. MANDATORY IMPORTANT MUST ATTENTION use a direct user question at EVERY stage — validate decisions before proceeding. MANDATORY IMPORTANT MUST ATTENTION NEVER ask tech stack upfront — business analysis and domain modeling first.

AI Mistake Prevention — Failure modes to avoid on every task:

Check downstream references before deleting. Deleting components causes documentation and code staleness cascades. Map all referencing files before removal. Verify AI-generated content against actual code. AI hallucinates APIs, class names, and method signatures. Always grep to confirm existence before documenting or referencing. Trace full dependency chain after edits. Changing a definition misses downstream variables and consumers derived from it. Always trace the full chain. Trace ALL code paths when verifying correctness. Confirming code exists is not confirming it executes. Always trace early exits, error branches, and conditional skips — not just happy path. When debugging, ask "whose responsibility?" before fixing. Trace whether bug is in caller (wrong data) or callee (wrong handling). Fix at responsible layer — never patch symptom site. Assume existing values are intentional — ask WHY before changing. Before changing any constant, limit, flag, or pattern: read comments, check git blame, examine surrounding code. Verify ALL affected outputs, not just the first. Changes touching multiple stacks require verifying EVERY output. One green check is not all green checks. Holistic-first debugging — resist nearest-attention trap. When investigating any failure, list EVERY precondition first (config, env vars, DB names, endpoints, DI registrations, data preconditions), then verify each against evidence before forming any code-layer hypothesis. Surgical changes — apply the diff test. Bug fix: every changed line must trace directly to the bug. Don't restyle or improve adjacent code. Enhancement task: implement improvements AND announce them explicitly. Surface ambiguity before coding — don't pick silently. If request has multiple interpretations, present each with effort estimate and ask. Never assume all-records, file-based, or more complex path.

Critical Thinking Mindset — Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination.

MUST ATTENTION apply critical thinking — every claim needs traced proof, confidence >80% to act. Anti-hallucination: never present guess as fact.

MUST ATTENTION apply AI mistake prevention — holistic-first debugging, fix at responsible layer, surface ambiguity before coding, re-read files after compaction.

Closing Reminders

• MANDATORY IMPORTANT MUST ATTENTION break work into small todo tasks using task tracking BEFORE starting
• MANDATORY IMPORTANT MUST ATTENTION search codebase for 3+ similar patterns before creating new code
• MANDATORY IMPORTANT MUST ATTENTION cite file:line evidence for every claim (confidence >80% to act)
• MANDATORY IMPORTANT MUST ATTENTION add a final review todo task to verify work quality

[TASK-PLANNING] Before acting, analyze task scope and systematically break it into small todo tasks and sub-tasks using task tracking.

Hookless Prompt Protocol Mirror (Auto-Synced)

Source: .claude/hooks/lib/prompt-injections.cjs + .claude/.ck.json

[WORKFLOW-EXECUTION-PROTOCOL] [BLOCKING] Workflow Execution Protocol — MANDATORY IMPORTANT MUST CRITICAL. Do not skip for any reason.

1. DETECT: Match prompt against workflow catalog
2. ANALYZE: Find best-match workflow AND evaluate if a custom step combination would fit better
3. ASK (REQUIRED FORMAT): Use a direct user question with this structure:
   • Question: "Which workflow do you want to activate?"
   • Option 1: "Activate [BestMatch Workflow] (Recommended)"
   • Option 2: "Activate custom workflow: [step1 → step2 → ...]" (include one-line rationale)
4. ACTIVATE (if confirmed): Call $workflow-start <workflowId> for standard; sequence custom steps manually
5. CREATE TASKS: task tracking for ALL workflow steps
6. EXECUTE: Follow each step in sequence [CRITICAL-THINKING-MINDSET] Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination principle: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination. AI Attention principle (Primacy-Recency): Put the 3 most critical rules at both top and bottom of long prompts/protocols so instruction adherence survives long context windows.

Learned Lessons

Lessons Learned

[CRITICAL] Hard-won project debugging/architecture rules. MUST ATTENTION apply BEFORE forming hypothesis or writing code.

Quick Summary

Goal: Prevent recurrence of known failure patterns — debugging, architecture, naming, AI orchestration, environment.

Top Rules (apply always):

• MUST ATTENTION verify ALL preconditions (config, env, DB names, DI regs) BEFORE code-layer hypothesis
• MUST ATTENTION fix responsible layer — NEVER patch symptom sites with caller-specific defensive code
• MUST ATTENTION use ExecuteInjectScopedAsync for parallel async + repo/UoW — NEVER ExecuteUowTask
• MUST ATTENTION name by PURPOSE not CONTENT — adding member forces rename = abstraction broken
• MUST ATTENTION persist sub-agent findings incrementally after each file — NEVER batch at end
• MUST ATTENTION Windows bash: verify Python alias (where python/where py) — NEVER assume python/python3 resolves

---

Debugging & Root Cause Reasoning

• [2026-04-11] Holistic-first: verify environment before code. Failure → list ALL preconditions (config, env vars, DB names, endpoints, DI regs, credentials, permissions, data prerequisites) → verify each via evidence (grep/cat/query) BEFORE code-layer hypothesis. Worst rabbit holes: diving nearest layer while bug sits elsewhere — e.g., hours debugging "sync timeout", real cause: test appsettings pointing wrong DB. Cheapest check first.
• [2026-04-01] Ask "whose responsibility?" before fixing. Trace: bug in caller (wrong data) or callee (wrong handling)? Fix responsible layer — NEVER patch symptom site masking real issue.
• [2026-04-01] Trace data lifecycle, not error site. Follow data: creation → transformation → consumption. Bug usually where data created wrong, not consumed.
• [2026-04-01] Code is caller-agnostic. Functions/handlers/consumers don't know who invokes them. Comments/guards/messages describe business intent — NEVER reference specific callers (tests, seeders, scripts).

Architecture Invariants

• [2026-03-31] ParallelAsync + repo/UoW MUST use ExecuteInjectScopedAsync, NEVER ExecuteUowTask. ExecuteUowTask creates new UoW but reuses outer DI scope (same DbContext) — parallel iterations sharing non-thread-safe DbContext silently corrupt data. ExecuteInjectScopedAsync creates new UoW + new DI scope (fresh repo per iteration).
• [2026-03-31] Bus message naming MUST include service name prefix — core services NEVER consume feature events. Prefix declares schema ownership (AccountUserEntityEventBusMessage = Accounts owns). Core services (Accounts, Communication) are leaders. Feature services (Growth, Talents) sending to core MUST use {CoreServiceName}...RequestBusMessage — never define own event for core to consume.

Naming & Abstraction

• [2026-04-12] Name PURPOSE not CONTENT — "OrXxx" anti-pattern. HrManagerOrHrOrPayrollHrOperationsPolicy names set members, not what it guards. Add role → rename = broken abstraction. Rule: names express DOES/GUARDS, not CONTAINS. Test: adding/removing member forces rename? YES = content-driven = bad → rename to purpose (e.g., HrOperationsAccessPolicy). Nuance: "Or" fine in behavioral idioms (FirstOrDefault, SuccessOrThrow) — expresses HAPPENS, not membership.

Environment & Tooling

• [2026-04-20] Windows bash: NEVER assume python/python3 resolves — verify alias first. Python may not be in bash PATH under those names. Check: where python / where py. Prefer py (Windows Python Launcher) for one-liners, node if JS alternative exists.

Test-specific lessons → docs/project-reference/integration-test-reference.md Lessons Learned section. Production-code anti-patterns → docs/project-reference/backend-patterns-reference.md Anti-Patterns section. Generic debugging/refactoring reminders → System Lessons in .claude/hooks/lib/prompt-injections.cjs.

---

Closing Reminders

• IMPORTANT MUST ATTENTION holistic-first: verify ALL preconditions (config, env, DB names, endpoints, DI regs) BEFORE code-layer hypothesis — cheapest check first
• IMPORTANT MUST ATTENTION fix responsible layer — NEVER patch symptom site; trace caller (wrong data) vs callee (wrong handling), fix root owner
• IMPORTANT MUST ATTENTION parallel async + repo/UoW → ALWAYS ExecuteInjectScopedAsync, NEVER ExecuteUowTask (shared DbContext = silent data corruption)
• IMPORTANT MUST ATTENTION bus message prefix = schema ownership; feature services NEVER define events for core services — use {CoreServiceName}...RequestBusMessage
• IMPORTANT MUST ATTENTION name by PURPOSE — adding/removing member forces rename = broken abstraction
• IMPORTANT MUST ATTENTION sub-agents MUST write findings after each file/section — NEVER batch all findings into one final write
• IMPORTANT MUST ATTENTION Windows bash: NEVER assume python/python3 resolves — run where python/where py first, use py launcher or node

[LESSON-LEARNED-REMINDER] [BLOCKING] Task Planning & Continuous Improvement — MANDATORY. Do not skip.

Break work into small tasks (task tracking) before starting. Add final task: "Analyze AI mistakes & lessons learned".

Extract lessons — ROOT CAUSE ONLY, not symptom fixes:

1. Name the FAILURE MODE (reasoning/assumption failure), not symptom — "assumed API existed without reading source" not "used wrong enum value".
2. Generality test: does this failure mode apply to ≥3 contexts/codebases? If not, abstract one level up.
3. Write as a universal rule — strip project-specific names/paths/classes. Useful on any codebase.
4. Consolidate: multiple mistakes sharing one failure mode → ONE lesson.
5. Recurrence gate: "Would this recur in future session WITHOUT this reminder?" — No → skip $learn.
6. Auto-fix gate: "Could $code-review/$code-simplifier/$security/$lint catch this?" — Yes → improve review skill instead.
7. BOTH gates pass → ask user to run $learn. [TASK-PLANNING] [MANDATORY] BEFORE executing any workflow or skill step, create/update task tracking for all planned steps, then keep it synchronized as each step starts/completes.