fastcampus-harness-engineering-course

사용자의 막연한 아이디어를 한 질문씩 인터뷰해서 실행 가능한 MVP 스펙으로 만든다

Socratic deep interview with mathematical ambiguity gating before explicit execution approval

Consensus planning entrypoint that auto-gates vague team/ultragoal requests before execution

Multi-worker GJC tmux team orchestration

Create and execute durable repo-native multi-goal plans over GJC goal mode artifacts.

QA the omo Codex Light edition (lazycodex / packages/omo-codex) itself, in strict isolation so ONLY our plugin is exercised, never the user's real ~/.codex. The first-party method drives the real `codex app-server` against an isolated CODEX_HOME plus a LOCAL mock model (no real API call), and proves a plugin hook fired by asserting hook/started + hook/completed notifications. Also: isolated install verification, per-component hook probes, a tmux TUI smoke, and runtime log observation (RUST_LOG / logs SQLite / /debug-config). Ships tested helper scripts each with a --self-test. Use whenever someone changes anything under packages/omo-codex or wants to QA, smoke-test, verify, or debug the Codex plugin, its hooks/components, the installer/config.toml, the app-server flow, or the Codex TUI. Triggers: codex qa, qa codex, codex-qa, test codex plugin, verify codex hook, codex app-server, lazycodex qa, isolated CODEX_HOME, prove codex hook fired, codex tui test.

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', 'adversarial plan', 'hostile planning', 'cross-critique plan', '하이퍼플랜', '적대적 계획', '교차 비평'.

Easter egg command - about oh-my-opencode. Triggers: omomomo, about, easter egg.

QA opencode itself, per case: verify the CLI/terminal (opencode run, db, serve, export), prove a specific plugin hook/action/event fired via the SSE event stream, smoke-test the TUI under tmux, and investigate sessions in opencode's SQLite DB by id, title/name, or message text. Ships tested helper scripts (each with a --self-test) plus per-domain references. Use whenever someone wants to QA, smoke-test, verify, or debug opencode's CLI, HTTP server, plugin hooks/events, or TUI, or to find/inspect opencode sessions in the database. Triggers: opencode qa, qa opencode, test opencode, verify opencode hook, opencode session db, find opencode session by id/name/text, opencode tui test, opencode server health, opencode event stream.

Nuclear-grade 16-agent pre-publish release gate. Runs /get-unpublished-changes to detect all changes since last npm release, spawns up to 10 ultrabrain agents for deep per-change analysis, invokes /review-work (5 agents) for holistic review, and 1 oracle for overall release synthesis. Use before EVERY npm publish. Triggers: 'pre-publish review', 'review before publish', 'release review', 'pre-release review', 'ready to publish?', 'can I publish?', 'pre-publish', 'safe to publish', 'publishing review', 'pre-publish check'.

Publish oh-my-opencode to npm via GitHub Actions workflow. Argument: <patch|minor|major>. Triggers: publish, release, deploy, npm publish.

Full PR lifecycle in an isolated git worktree: implement via the ulw-loop skill with mandatory evidence-bound manual QA → detailed English PR → verification loop (CI + review-work reviewers + Cubic, where Cubic is skipped only when its quota is exhausted) → merge by default → worktree cleanup. Decomposes one task into the smallest atomic, independently-mergeable PRs and builds the independent ones concurrently via a worktree per PR driven by parallel subagents or a team. Unbounded loop: any failing gate sends you back to fix-and-re-QA inside the worktree. Use whenever implementation work needs to land as a PR. Triggers: 'create a PR', 'implement and PR', 'work on this and make a PR', 'implement issue', 'land this as a PR', 'split into atomic PRs', 'parallel PRs', 'work-with-pr', 'PR workflow', 'implement end to end', even when user just says 'implement X' if the context implies PR delivery.

MUST USE for planning before coding: 5+ steps, ambiguous scope, multiple modules, architecture decisions, a vague 'just make it good / figure out what to build' brief, or any request to plan, interview, or break work down. Explore-first planning consultant (Prometheus) that grounds in the codebase, asks only the forks exploration cannot resolve - or researches them to best practice when the intent is fuzzy - waits for explicit approval, then writes ONE decision-complete work plan a worker executes with zero further interview. Triggers: ulw-plan, plan this, make a plan, plan before coding, interview me, break this down, start planning, plan mode, just make it good, figure out what to build.

Goal-like loop that uses ultrawork mode to decompose work into systematic, evidence-bound steps.

MUST USE for ANY frontend, web UI, UX, or visual work — building, styling, or redesigning pages/components, React project setup, performance audits, design QA. Routes three rulesets: design (anti-slop taste router over 12 taste skills + 69 brand DESIGN.md refs — Apple, Stripe, Linear, Notion, Vercel, Claude, Nike — plus React dev tooling gate: react-grab, react-scan, react-doctor), perfection (Lighthouse 100 in every category via real Playwright Chromium audits, NEVER the lighthouse CLI, never by weakening UX), ui-ux-db (searchable 50+ styles, 97 palettes, 57 font pairings, 99 UX guidelines). Triggers: frontend, UI, UX, design, redesign, styling, layout, animation, motion, taste, premium, luxury, minimal, brutalist, Awwwards, anti-slop, polish, DESIGN.md, mockup, react setup, react-scan, react-doctor, lighthouse, performance, Core Web Vitals, LCP, CLS, INP, SEO, accessibility, a11y, WCAG, audit my site, make this faster, color palette, font pairing, looks generic, make it pretty, like X brand.

MUST USE for any real runtime debugging across ANY language or binary — crashes, silent failures, wrong responses, stuck processes, memory leaks, async misbehavior, unexplained timing, reverse engineering. Runs a hypothesis-driven loop: form ≥3 hypotheses, investigate in parallel, after 2 failed rounds spawn Oracles from orthogonal angles, confirm root cause, lock with a failing test, fix minimally, QA by actually USING the system, scrub artifacts. The actual HOW lives in `references/` — READ THEM. Triggers: 'debug this', 'why is X not working', 'hanging', 'attach a debugger', 'reverse engineer', 'pwndbg', 'gdb', 'lldb', 'node inspect', 'tsx debug', 'pdb', 'dlv', 'delve', 'rust-gdb', 'set a breakpoint', 'context window exploded', 'why is the response empty', 'attach the debugger', 'debug it', 'why is this happening', 'trace this bug', 'reproduce and fix', 'silent failure', 'HTTP 200 but empty', 'why did it stop', 'inspect the binary', 'reverse engineering', 'playwright'.

MUST USE for ANY frontend, web UI, UX, or visual work — building, styling, or redesigning pages/components, React project setup, performance audits, design QA. Routes three rulesets: design (anti-slop taste router over 12 taste skills + 69 brand DESIGN.md refs — Apple, Stripe, Linear, Notion, Vercel, Claude, Nike — plus React dev tooling gate: react-grab, react-scan, react-doctor), perfection (Lighthouse 100 in every category via real Playwright Chromium audits, NEVER the lighthouse CLI, never by weakening UX), ui-ux-db (searchable 50+ styles, 97 palettes, 57 font pairings, 99 UX guidelines). Triggers: frontend, UI, UX, design, redesign, styling, layout, animation, motion, taste, premium, luxury, minimal, brutalist, Awwwards, anti-slop, polish, DESIGN.md, mockup, react setup, react-scan, react-doctor, lighthouse, performance, Core Web Vitals, LCP, CLS, INP, SEO, accessibility, a11y, WCAG, audit my site, make this faster, color palette, font pairing, looks generic, make it pretty, like X brand.

MUST USE whenever a task needs a commit or git-history investigation. Covers atomic commits, staging, commit-message style, rebase, squash, fixup/autosquash, blame, bisect, reflog, git log -S/-G, and questions like who wrote this or when was this added. Do not use for ordinary code edits unless the user asks for git work.

(builtin) Initialize hierarchical AGENTS.md knowledge base

Contribute a verified bug fix for LazyCodex, lazycodex-ai, omo-codex, bundled Codex skills, or upstream Codex CLI bugs. Opens a fork PR only for upstream openai/codex; LazyCodex-owned defects become a verified-fix issue on code-yeongyu/lazycodex (never a PR — that repo is a generated distribution mirror). Use when the user asks to fix a bug, contribute a bug fix, contribute to fix bug, open a PR for a bug, or debug and PR a LazyCodex/Codex defect.

Diagnose LazyCodex and Codex CLI installation health against the latest sources. Use whenever the user asks for a doctor or health check, says LazyCodex, lazycodex-ai, omo-codex, or Codex behaves oddly after an install, update, or config change, suspects a stale, drifted, or broken setup, or wants the local install audited and compared with the latest LazyCodex and Codex code.

Create a high-signal bug issue or PR in the repo that owns the defect. Use this whenever the user asks to report, file, open, or triage a LazyCodex, lazycodex-ai, omo-codex, Codex plugin, or upstream Codex CLI bug, especially when they need source-backed root cause, reproduction steps, fix guidance, and GitHub routing.

MUST USE for ANY work on .py .pyi .rs .ts .tsx .mts .cts .go files. One philosophy: strict types, modern stacks (Pydantic v2 / serde+thiserror / Zod / gin+sqlc+pgx+slog), modern toolchains (uv+basedpyright+ruff / cargo+clippy+miri / Bun+Biome+tsc / gofumpt+golangci-lint v2+nilaway+go-race), parse-don't-validate, exhaustive match, typed errors, no any/unwrap/panic, 250 LOC ceiling, TDD. Routes to references/{python,rust,typescript,rust-ub,go}/. Triggers: write/edit Python/Rust/TypeScript/Go code, new project, gin server, bubbletea TUI, CJK IME, connect-go RPC, sqlc pgx, branded ids, exhaustive match, unsafe Rust, miri, oversized file, refactor, TDD, e2e test, arena, allocator, bumpalo, const fn, const generics, comptime, zero-alloc, bitfield, repr, scopeguard, errdefer, Zig-like, zerocopy, packed struct.

Remove AI-generated code smells (slop) from branch changes or an explicit file list. Locks behavior with regression tests FIRST, then runs categorized cleanup via parallel `deep` agents in batches of 5, then verifies with quality gates. Covers 10 slop categories including performance equivalences, excessive complexity (object annotations, if/elif variant chains), and oversized modules (250+ pure LOC with mandatory modular refactoring). MUST USE when the user asks to "remove slop", "clean AI code", "deslop", "clean up AI-generated code", "remove AI slop", or wants to clean up AI-generated patterns from recent changes. Triggers - "remove ai slops", "clean ai code", "deslop", "cleanup AI generated", "remove AI slop", "clean up AI-generated code", "strip slop", "ai-slop cleanup".

Post-implementation review orchestrator. Launches 5 parallel background sub-agents: Oracle (goal/constraint verification), Oracle (code quality), Oracle (security), unspecified-high (hands-on QA execution), unspecified-high (context mining from GitHub/git/Slack/Notion). All must pass for review to pass. MUST USE after completing any significant implementation work. Triggers: 'review work', 'review my work', 'review changes', 'QA my work', 'verify implementation', 'check my work', 'validate changes', 'post-implementation review'.

Execute a Prometheus work plan in Codex with Boulder state, evidence ledger updates, worktree discipline, parallel subagents, and Stop-hook continuation. Use after planning when the user says start work, execute plan, continue plan, resume plan, or asks to run a .omo/plans plan.

Maximum-saturation research orchestration: parallel explore+librarian swarms across codebase, web, official docs, and OSS repos; a recursive EXPAND loop driven by leads workers return in message text; empirical verification by running code; cited synthesis and optional MD/HTML/PDF/PPTX reports. ACTIVATES ONLY on an explicit user demand for research — the word 'ultraresearch' ('/ultraresearch', '$ultraresearch') or an explicit request for research / deep research / an ultra-precise investigation, in any language. Never self-activates for ordinary questions, debugging, or implementation context-gathering. While active it overrides exploration-bounding defaults: exhaustive coverage is the goal.

MUST USE for planning before coding: 5+ steps, ambiguous scope, multiple modules, architecture decisions, a vague 'just make it good / figure out what to build' brief, or any request to plan, interview, or break work down. Explore-first planning consultant (Prometheus) that grounds in the codebase, asks only the forks exploration cannot resolve - or researches them to best practice when the intent is fuzzy - waits for explicit approval, then writes ONE decision-complete work plan a worker executes with zero further interview. Triggers: ulw-plan, plan this, make a plan, plan before coding, interview me, break this down, start planning, plan mode, just make it good, figure out what to build.

Rigorous visual QA for any UI you built or changed, across BOTH web/page UIs and TUI/terminal UIs. MUST USE after building or changing any UI to verify it visually before declaring it done. Captures objective reference evidence with a bundled diff script (image-diff for screenshots, tui-check for terminal captures), then runs two parallel read-only oracle passes (design-system and functional integrity; visual fidelity and CJK precision) and synthesizes one good/bad verdict. Triggers: visual QA, visual regression, screenshot diff, pixel diff, image comparison, UI looks wrong, design system check, is this really a design system or just an image, alpha channel breakage, responsive check, CJK text, Korean/Japanese/Chinese text clipping, baseline drop, glyph drop, TUI alignment, terminal UI, tmux capture, box-drawing border misalignment, wide-character column drift. Use it even when the user does not say visual QA but asks whether a page, component, or terminal layout looks right.

Minimal shared skill fixture used to demonstrate Claude Code and Codex skill sync.

Second minimal shared skill fixture used to verify skill sync drift detection.

Use when code changes may affect API contracts, architecture, workflows, or user-facing behavior. Updates only the affected documentation sections.

Use for commits, pull requests, policy changes, release preparation, and any task requiring team Agent workflow evidence.

Use when a test fails, an error log is given, or a user says the implementation is wrong. Reproduces first, hypothesizes, then applies the smallest fix and verifies.

Review code changes for correctness, security, test coverage, and documentation impact. Use when reviewing a diff, branch, or pull request.

Generate and maintain hierarchical AGENTS.

A beginner-friendly guide to CLI basics and Git fundamentals for non-developers, grounded in the Harness Engineering framework. Uses everyday analogies, real examples, and evidence-based reasoning (including the ~45% Silent Failure Rate in AI-generated code) to explain why CLI and Git are essential control surfaces for AI coding agents. Supports both Claude Code and Codex. Use this skill whenever users mention terminal, CLI, commands, command line, Git, version control, development basics, coding beginner, dev-basics, learn-cli-git, harness engineering, AI safety, vibe coding, or say they don't know terminal/Git commands, or want to learn development tool basics, or ask why CLI/Git matter for AI agents.