Workflow Orchestration Provisioning

This provisioning installed workflow orchestration conventions into two new files:

• ./CLAUDE.md — created, block inserted at top
• ./AGENTS.md — created, block inserted at top
• Monorepo safety block — skipped (not a monorepo)

Both files contain the orchestration block exactly once. Source/verification notes written to both files.

Workflow Orchestration

1. Plan Mode Default

• Enter plan mode for ANY non-trivial task (3+ steps or architectural decisions)
• If something goes sideways, STOP and re-plan immediately
• Verification is mandatory, but routine no-op verification runs inside the active execution/shipping step
• Write detailed specs upfront to reduce ambiguity
• In Codex: use update_plan in Default mode and request_user_input only when already in Plan mode
• Do not assume a Claude-style clear-context-on-accept flow or related JSON setting exists

2. Subagent Strategy

• Use subagents liberally to keep main context window clean
• Offload research, exploration, and parallel analysis to subagents
• For complex problems, throw more compute at it via subagents
• One task per subagent for focused execution
• For agent-team parallel write lanes, require separate GitHub branches per lane and include a consolidation/PR review step

3. Self-Improvement Loop

• After ANY correction from the user: update tasks/lessons.md with the pattern
• Write rules for yourself that prevent the same mistake
• Ruthlessly iterate on these lessons until mistake rate drops
• Review lessons at session start for relevant project

4. Verification Before Done

• Never mark a task complete without proving it works
• Diff your behavior between main and your changes when relevant
• Ask yourself: "Would a staff engineer approve this?"
• Run tests, check logs, demonstrate correctness

5. Demand Elegance (Balanced)

• For non-trivial changes: pause and ask "is there a more elegant way?"
• Skip this for simple, obvious fixes
• Challenge your own work before presenting it

6. Autonomous Bug Fixing

• When given a bug report: just fix it
• Point at logs, errors, failing tests — then resolve them
• Zero context switching required from the user

Task Management

1. Plan First: Write plan to tasks/roadmap.md and tasks/todo.md
2. Verify Plan: Check in before starting implementation
3. Track Progress: Mark items complete as you go
4. Explain Changes: High-level summary at each step
5. Document Results: Add review section to tasks/todo.md
6. Capture Lessons: Update tasks/lessons.md after corrections

Core Principles

• Simplicity First
• No Laziness — find root causes
• Minimal Impact — only touch what's necessary
• Direct-To-Primary Git Flow — commit to main by default
• Always Ship Mutations — commit and push before stopping
• No GitHub Actions — unless explicitly asked

Same structure as CLAUDE.md with these differences:

• Subagent Strategy: Subagents only when Codex tool instructions allow them; do not override Codex's current subagent permission
• Always Ship Mutations: Codex $run ships by default — use $ship only to package existing work or unpushed commits

Result: Not a monorepo

• pnpm-workspace.yaml: not found
• package.json workspaces field: no package.json
• lerna.json: not found
• packages/ directory: not found
• apps/ directory: not found

Monorepo safety block was skipped.