Instructions file CodexOpenCode
Instructions for KaimingWan/oh-my-kiro, covering agent framework v3, identity, roles, principles and workflow.
Instructions file CodexOpenCode
Instructions for KaimingWan/oh-my-kiro, covering agent framework v3, identity, roles, principles and workflow.
Agent
You are a research specialist for codebase exploration and web research.
Agent
You are a senior reviewer. Your job is to catch issues that would cause failure or wrong results — not to pursue perfection.
Command
You MUST follow this exact sequence. @auto is a fully automated pipeline — no user confirmation between stages except during Expansion questions.
Command
Checkout a branch in a submodule, with fuzzy search support. (CK = Checkout).
Command
Commit all changes, push to remote, and create a Pull Request. (CPR = Commit Push PR).
Command
Commit all changes, push to remote, and complete branch lifecycle. (CPU = Commit Push Update-readme).
Command
You MUST follow this exact sequence. @debug is a fully automated debugging pipeline — no user confirmation between stages. The goal is systematic root cause analysis, not guess-and-check.
Command
Lightweight command for small tasks (< 1 hour). No plan file, no review dispatch. Prevents context drift across multi-turn interactions.
Command
Command "evaluate" from KaimingWan/oh-my-kiro, covering step 1: resolve evaluation target, step 2: gather context, step 3: dispatch 4 parallel evaluator subagents, subagent #2: "product manager" — alignment and subagent #3: "breaker" — correctness + robustness.
Command
Execute an approved plan with Ralph Loop hard constraint. Agent stops don't matter — bash loop keeps going until all checklist items are done.
Command
Automated PR fixer: fetch all review comments, triage each one, fix or pushback, reply + resolve every thread. Zero unresolved threads when done.
Command
Run these health checks and report results.
Command
You MUST follow this exact sequence. Do NOT skip or reorder any step.
Command
You MUST read skills/omk-research/SKILL.md first, then follow its search level strategy.
Command
Before dispatching the reviewer, determine the correct working directory.
Command
Read skills/find-skills/SKILL.md, then follow its methodology to help the user find a skill that matches their need.
Command
Manage worktrees: list status, clean up merged branches.
Skill Claude CodeCodex
Distill a top-level principle into knowledge/rules.md. Trigger when user says 'add rule', 'new principle', 'enforce this', '@agent', or wants to codify an architectural decision, workflow principle, or behavioral guideline into persistent rules.
Skill Claude CodeCodex
Enforces coding best practices: deep-read before modify, LSP-first navigation, TDD red-green-refactor, minimal changes, self-review, verification. Trigger when writing code, modifying source files, fixing bugs, refactoring, optimizing code, entering a worktree or submodule, or when user says 'write code', 'implement'…
Skill Claude CodeCodex
Fetch current library/framework documentation via Context7. Trigger when user asks about libraries, frameworks, API references, code examples, setup/configuration, or mentions specific frameworks like React, Vue, Next.js, Prisma, Supabase, Express, Tailwind, Django, FastAPI, Spring Boot, etc. Also trigger when user…
Skill Claude CodeCodex
Systematic debugging: reproduce → hypothesize → verify → fix. Trigger when encountering bugs, test failures, errors, crashes, unexpected behavior, or when user says 'debug', 'not working', 'broken', 'fails', 'error', 'exception', 'why does this happen', 'investigate'. Also trigger on stack traces, error logs, or…
Skill Claude CodeCodex
Branch completion workflow: verify tests → present 4 options (merge/PR/keep/discard) → execute → cleanup worktree. Trigger when implementation is complete, all tests pass, user says 'done', 'finish', 'merge', 'create PR', 'push', 'wrap up', '@cpu', or when ready to integrate work back to main branch.
Skill Claude CodeCodex
Capture knowledge into episodes.md. Trigger when user says 'remember', 'capture this', 'lesson learned', 'note this', '@know', or when preserving insights, corrections, or discoveries from the current conversation.