Does lazycodex auto-invoke its skills?

Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.

Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.

Development

Plugin

lazycodex

The one and only agent harness for complex codebases. Project memory, planning, execution, and verified completion inside Codex.

FLOW.md

code-yeongyu@code-yeongyu

GitHub

Plugin Signal91/100Strong

maintained100

capable83

documented100

adopted74

Install

$ npx -y skills add code-yeongyu/lazycodex --agent claude-code

Run the curl in your terminal, the rest in Claude Code.

Stats

Python TypeScript JavaScript React Next.js

+7 tags

Bash Cloudflare Git GitHub Anthropic OpenAI MCP

3,163

Stars

198

Forks

Active

Maintenance

TypeScript

Language

MIT

License

15h ago

Last commit

2mo ago

Created

Repo: code-yeongyu/lazycodex

In this plugin

26 skills 10 agents 6 MCP

See everything inside

What's inside

Skills

/comment-checkerUse when Codex needs to understand or respond to automatic comment-checker feedback emitted after an edit-like PostToolUse hook./lcx-contribute-bug-fixContribute 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 /lcx-doctorDiagnose 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 /lcx-report-bugCreate 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 /lspUse when Codex needs language-server diagnostics, definitions, references, symbols, or rename safety checks in the current workspace./rulesUse when the user asks about Codex Rules behavior, injected project rules, supported rule file locations, matching, or environment configuration.

Show all 36 skills

/teammodeCodex-only team orchestration: run a named team of cooperating Codex workers with durable, script-managed state. MUST USE when the user asks Codex to create, run, coordinate, inspect, archive, or delete a team of agents/threads/sessions, or to work on something as a team in /ultraworkBinding ultrawork mode directive for omo on Codex. When a prompt contains ultrawork or ulw, the omo UserPromptSubmit hook injects a short bootstrap that points at this file. Read the whole file and follow every rule in it for the rest of the task./ulw-planACTIVATES ONLY on an explicit user request for the ulw-plan workflow: the user themselves saying ulw-plan, ulw plan, /skill:ulw-plan, or asking in their own words for a work plan before coding. NEVER self-activates: a bare ulw/ultrawork run, an agent-side routing decision, or /ulw-loopGoal-like loop that uses ultrawork mode to decompose work into systematic, evidence-bound steps./ast-grepUse ast-grep (sg) for AST-aware code search and rewrite across 25 languages. Trigger for structural code matching or deterministic codemods: find every function/call/class/import shaped like X, rewrite console.log to logger.info, strip `as any`, migrate require() to import, find /coding-agent-sessionsMUST USE when asked to find, read, list, search, inspect, fetch, export, or reconstruct coding-agent sessions across Codex, Claude Code/Desktop, OpenCode, Senpi/pi, oh-my-pi (omp), gajae-code (gjc), OpenClaw, Factory Droid, Amp, Gemini/Kimi/Qwen CLIs, Codebuff, Roo/Kilo/Cline,/comment-checkerUse when Codex needs to understand or respond to automatic comment-checker feedback emitted after an edit-like PostToolUse hook./data-scientistExpert data processing specialist with intelligent DuckDB/Polars selection for maximum performance. Always includes numpy, never uses pandas, runs everything through uv. Triggers: 'analyze the data', 'analyze this file', 'what is in this CSV/parquet/json', 'summarize this',/debuggingMUST 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 /frontendMUST USE for frontend/web UI/UX/visual work: building, styling, redesigning pages/components, React setup, performance audits, visual QA, taste, and polish. Routes four rulesets: design taste router and brand references; perfection for Playwright/Chromium Lighthouse/Core Web /git-masterMUST 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 /init-deep(builtin) Initialize hierarchical AGENTS.md knowledge base /lcx-contribute-bug-fixContribute 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 /lcx-doctorDiagnose 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 /lcx-report-bugCreate 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 /lsp-setupConfigure a Language Server (LSP) for a specific language so editor/agent tooling — diagnostics, go-to-definition, find-references, rename — works. Use when you need to: configure LSP, lsp setup, set up or install a language server, fix 'no LSP server configured' / 'server not /lspUse when Codex needs language-server diagnostics, definitions, references, symbols, or rename safety checks in the current workspace./programmingMUST 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 /refactorIntelligent refactor command. Triggers: refactor, refactoring, cleanup, restructure, extract, simplify, modernize./remove-ai-slopsRemove 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 /review-workPost-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 /rulesUse when the user asks about Codex Rules behavior, injected project rules, supported rule file locations, matching, or environment configuration./start-workExecute 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./teammodeCodex-only team orchestration: run a named team of cooperating Codex workers with durable, script-managed state. MUST USE when the user asks Codex to create, run, coordinate, inspect, archive, or delete a team of agents/threads/sessions, or to work on something as a team in /ultimate-browsingEscalation skill for blocked or hard-to-reach web access — load it when a normal browse/fetch is blocked (WAF, 403, Cloudflare, JS-only render, login-gated, or a platform a generic fetcher cannot read). Tiered router: TIER 1 insane-search (headless extraction + WAF bypass via /ultraworkBinding ultrawork mode directive for omo on Codex. When a prompt contains ultrawork or ulw, the omo UserPromptSubmit hook injects a short bootstrap that points at this file. Read the whole file and follow every rule in it for the rest of the task./ulw-loopGoal-like loop that uses ultrawork mode to decompose work into systematic, evidence-bound steps./ulw-planACTIVATES ONLY on an explicit user request for the ulw-plan workflow: the user themselves saying ulw-plan, ulw plan, /skill:ulw-plan, or asking in their own words for a work plan before coding. NEVER self-activates: a bare ulw/ultrawork run, an agent-side routing decision, or /ulw-researchMaximum-saturation research orchestration: ALWAYS proposes the final materials first (PDF+DOCX default), then parallel explore+librarian swarms across codebase, web, official docs, and OSS repos — max-roster teammode when the harness has it — with live journaling, a recursive /visual-qaMUST USE after building/changing any UI or when asked whether a page, component, or TUI looks right. Rigorous visual QA across web/page and terminal UIs. Prefer browser:control-in-app-browser for unauthenticated browser/page QA in Codex, then

Agents

accessibility-reviewerUse this agent to review any design output — code, mockups, specifications, or prototypes — for inclusive design compliance. Evaluates against WCAG, COGA, and inclusive design principles. Dispatch after design work and before handoff.content-writerUse this agent for UX writing, interface copy, labels, error messages, empty states, onboarding text, help text, tooltips, alt text, link text, form instructions, and any words users read in the interface. Writes in plain language with cognitive accessibility built in. Dispatch design-builderUse this agent for building production-ready prototypes and implementations from design specs — assembling components into full pages, wiring up interactions, integrating with APIs, setting up project scaffolding, and bridging the gap between design decisions and working design-criticUse this agent to review design work against the original plan, design brief, and design principles. Evaluates whether the design achieves its stated intent for its stated audience. Dispatch at review checkpoints or before handoff.design-leadUse this agent for visual design execution — layouts, colour systems, typography, component design, responsive behaviour, interaction patterns, and design system work. Dispatch when the design plan is approved and implementation begins. Produces design decisions grounded in the design-scoutUse this agent for competitive UX analysis, design benchmarking, user insight synthesis, design pattern research, accessibility audits of competitors, trend analysis, and inclusion-aware research that informs design decisions. Dispatch before the team starts designing, or when

Show all 10 agents

design-strategistUse this agent for upstream design thinking — user flows, information architecture, journey mapping, persona development, design principles, experience mapping, and setting design direction before visual work begins. Dispatch during discovery and strategy phases. Use this heuristic-evaluatorUse this agent to evaluate a design against established usability heuristics (Nielsen's 10) and conduct cognitive walkthroughs of key tasks. Dispatch after design-builder completes, alongside design-critic and accessibility-reviewer. Catches usability problems that craft inspiration-scoutUse this agent to find aesthetic references, interaction examples, and visual inspiration that match the project brief and the user's taste profile. Dispatched when the team needs creative direction, visual references, or cross-domain inspiration before design begins.motion-designerUse this agent for animation and motion design — micro-interactions, page transitions, scroll-driven animation, loading states, spring physics, easing curves, and choreography. Ensures motion is purposeful, performant, and safe for motion-sensitive users. Dispatch when a design

MCP

next-devtoolsnpx grep_appstdio context7stdio codegraphnode git_bashnode lspnode

README

Read on GitHub

[!NOTE] [OmO] 60K Stars: the terrifying token burner has arrived in LazyCodex.

Sisyphus Labs' OmO is the quality-obsessed agent harness whose public lore says it loved Anthropic models hard enough to get third-party clients blocked. Now that same OmO quality bar is available for Codex through LazyCodex.

If you wanted OmO but did not want the setup ceremony, start here:
npx lazycodex-ai install
Context: OmO 60K Stars on X

🚀 Install

One line. No global install, no npm i -g. Always use npx:

npx lazycodex-ai install

This is shorthand for npx --yes --package oh-my-openagent omo install --platform=codex. For a fully autonomous, no-TUI setup:

npx lazycodex-ai install --no-tui --codex-autonomous

Install from the Codex marketplace (experimental)

The npx installer above stays the primary path. As an additive, experimental alternative you can install from inside Codex itself: type /plugins, open the Add Marketplace tab ("Add a marketplace from a Git repo or local root."), and enter https://github.com/code-yeongyu/lazycodex, then install omo from the sisyphuslabs marketplace. Or from the CLI:

codex plugin marketplace add https://github.com/code-yeongyu/lazycodex
codex plugin add omo@sisyphuslabs

On the next launch, approve the omo hooks in Codex's startup review — hooks never run before approval. The first approved session prints LazyCodex bootstrap running in background — restart the session when it completes while a background worker finishes the setup (config blocks, agent roles, bin links, a pinned sg binary for the ast_grep MCP); restart when it is done. The marketplace path never touches Codex permission settings — autonomous mode remains the explicit npx lazycodex-ai install --no-tui --codex-autonomous choice.

Upgrade with codex plugin marketplace upgrade sisyphuslabs. The next startup review shows the hooks as Modified — expected after every upgrade — re-approve them and the following session re-runs bootstrap on the new version. If anything looks pending or degraded, npx lazycodex-ai doctor explains what and why. Full details: lazycodex.ai/docs.

Verify it worked

npx lazycodex-ai doctor

doctor prints the installation health report: plugin cache, hooks, MCP servers, agents, and config state. Inside Codex, type $ in the composer to browse every installed skill — init-deep, ulw-loop, ulw-plan, start-work, and the rest — and hooks announce themselves with LazyCodex(<version>): ... status messages during a session.

Uninstall

npx lazycodex-ai uninstall

Removes the installed plugin cache, bin links, agent roles, and the managed sections of ~/.codex/config.toml.

⚡ Commands

LazyCodex installs these as OmO commands for Codex. Invoke them with the $command syntax shown by the installer.

Command	Type this	What it does
`$ulw-loop`	`$ulw-loop "task" [--completion-promise=TEXT] [--strategy=reset\|continue]`	Self-referential loop that runs until Oracle-verified completion. Caps at 500 iterations in ultrawork mode, 100 in normal mode.
`$ulw-plan`	`$ulw-plan "what to build"`	Prometheus strategic planner. Writes a plan to `plans/<slug>.md`. Never writes product code.
`$start-work`	`$start-work [plan-name] [--worktree <path>]`	Executes a plan until every checkbox is done. Prints ORCHESTRATION COMPLETE.

Full documentation lives at lazycodex.ai/docs.

Use the built-in workflows

LazyCodex should be judged by the features it actually installs. It is the Codex distribution for OmO's agent harness: project memory, planning, execution, verified completion, skills, hooks, model routing, and diagnostics.

1. `$init-deep` creates project memory

$init-deep generates hierarchical AGENTS.md context. It scores complex directories, writes local guidance near the code that needs it, and gives future agents landmarks before they edit. Type $init-deep in the Codex composer — the $ prefix is how every installed skill is invoked.

Use it when the repository is too large to explain from memory. Run it again when the shape of the codebase changes.

2. The three command pillars stay up front

Use $ulw-plan when the work needs decisions before implementation. It writes a plan to plans/<slug>.md and does not touch product code.

Use $start-work when a plan is ready. It executes the checklist with durable Boulder progress and stops only when the plan is complete.

Use $ulw-loop when the task should keep moving until the result is verified by evidence instead of a hopeful status update.

3. Skills cover specialized work

The command layer stays simple. The skill layer adds specialist judgment for the actual work:

Feature	Use it for
`$init-deep`	Hierarchical project memory through `AGENTS.md`
`$ulw-plan`	Decision-complete planning before code changes
`$start-work`	Durable plan execution with Boulder progress
`$ulw-loop`	Verified completion for open-ended tasks
`review-work`	Multi-angle post-implementation review
`remove-ai-slops`	Behavior-preserving cleanup of AI-looking code
`frontend-ui-ux`	Polished UI surfaces
`programming`	Strict TypeScript, Rust, Python, or Go discipline
`LSP`	Diagnostics, definitions, references, symbols, and renames
`AST-grep`	Structural search and rewrite across code
`rules`	Project instructions from AGENTS, rules, and instruction files
`comment-checker`	Feedback after edit-like operations

4. Sub-agent roles ride Codex's native multi-agent tools

LazyCodex installs selectable agent roles into ~/.codex/agents/: explorer, librarian, plan, momus, metis, and codex-ultrawork-reviewer. Pick one by passing agent_type to Codex's spawn_agent tool — the child agent runs with that role's model and instructions:

spawn_agent({"message": "TASK: map the auth flow end to end.", "agent_type": "explorer"})

The installer exposes agent_type on multi_agent_v2 sessions (Codex hides it by default). If your Codex build's spawn tool has no agent_type parameter, describe the role inside message instead — the skills are written to fall back to that form automatically.

Start at https://lazycodex.ai.

💤 What is this?

LazyCodex packages OmO (oh-my-openagent) as the Codex agent harness for complex codebases.

Think LazyVim for lazy.nvim, but for Codex.

OmO is the agent harness: discipline agents, parallel orchestration, multi-model routing, skills, hooks, and verified completion. LazyCodex packages that harness for Codex.

"LazyVim made Neovim usable for the rest of us. LazyCodex does the same for Codex."

Credit: The LazyCodex name idea is inspired by LazyVim. The Ultragoal and UltraQA ideas are inspired by oh-my-codex, reimplemented from concept for this Codex setup.

🧩 What you get

Feature	Description
🤖 Discipline Agents	Sisyphus orchestrates Hephaestus, Oracle, Librarian. A full AI dev team
🔀 Parallel Execution	Multiple agents working simultaneously on subtasks
🎯 Multi-Model Routing	Automatic model selection per task category
🛠️ Skills System	Extensible skill library for specialized tasks
📋 Hooks & Lifecycle	Pre/post hooks for every agent action
🔧 Zero Config	Sensible defaults, override when you want

🧠 Why different GPT models appear

Do not be surprised if an OmO/LazyCodex run shows models like gpt-5.2 with xhigh, gpt-5.4-mini, gpt-5.3-codex, or newer equivalents like gpt-5.5 with xhigh. That is intentional.

OmO does not blindly spend your best model on every subtask. Its source defines task categories and fallback chains so the agent can pick the most appropriate model for the job: quick routes to gpt-5.4-mini for small edits, ultrabrain uses a high-reasoning GPT model for hard logic, and agentic coding paths can use Codex-tuned GPT models when available. See openai-categories.ts and model-requirements.ts.

The point is quota discipline: use the strongest model when the task needs deep reasoning, use a cheaper/faster model when that is enough, and keep parallel agent work efficient instead of burning premium quota on routine steps. This is benchmark-driven routing, not random model churn:

GPT-5.2 is documented by OpenAI as stronger at code review, bug finding, and complex tool use; the announcement notes that its maximum API reasoning effort uses xhigh.
GPT-5.3-Codex is OpenAI's Codex-tuned model for agentic software engineering, with public coding-agent benchmarks such as SWE-Bench Pro, Terminal-Bench 2.0, and OSWorld Verified reported in the GPT-5.3-Codex announcement.
GPT-5.4 mini is positioned for efficient everyday coding, computer use, and subagents; that is why lightweight OmO tasks can land there instead of spending a frontier reasoning model.

Reference links:

🏗️ Architecture

LazyCodex is a thin distribution layer. The core engine is oh-my-openagent (OmO), included as a submodule under src/.

lazycodex/
├── src/                     → oh-my-openagent (submodule)
├── packages/
│   └── web/                 → Next.js 15 + Tailwind v4 + opennextjs-cloudflare
│                              (deployed to lazycodex.ai via Cloudflare Workers)
├── .github/workflows/       → web-ci.yml + web-deploy.yml
├── README.md
└── ...

LazyCodex is part of the omo.dev project. omo in Codex, packaged for the lazy.

👷 Maintainer

LazyCodex is maintained by Jobdori, the AI assistant that builds and ships OmO in real-time.

Meet your own Jobdori, Dori. Learn more at sisyphuslabs.ai.

📄 License

MIT

File tree

1454

code-yeongyu/lazycodexView on GitHub

.agents/
  plugins/
    marketplace.json
.github/
  assets/
    lazycodex-logo.png
    omo-icon-light.svg
    omo-logo.png
    sisyphuslabs.png
  REPO_METADATA.md
  workflows/
    npm-ci.yml
    npm-publish.yml
    pr-source-guidance.yml
    web-ci.yml
    web-deploy.yml
.gitignore
.gitmodules
.omo/
  evidence/
    20260809-readme-light-logo/
      qa.md
    design-system-components-v3.md
    design-system-fidelity-v2.md
    v11-consolidation.md
    v11-demo-chip.png
    v11-full-e2e.txt
    v11-heph-loop.png
    v11-lighthouse.txt
    v11-skills-band.png
    v11-slop-report.md
    v12-full-e2e.txt
    v12-lighthouse.txt
    v12-mobile/
    v12-mobile-green.txt
    v12-mobile-red.txt
      after-demo-m375.png
      after-demo-m390.png
      after-demo-t768.png
      demo-m375.png
      demo-t768.png
      docs-m375-full.png
      docs-t768-full.png
      landing-m375-full.png
      landing-t768-full.png
      s0-header.png
      s1.png
      s10.png
      s2.png
      s3.png
      s4.png
      s5.png
      s6.png
      s7.png
      s8.png
      s9.png
      s99-footer.png
  scripts/
    design-system-fidelity/
      capture-and-drive.mjs
  ulw-loop/
    evidence/
      design-system-components-v3/
        capture-report.json
        diffs/
          docs-desktop-1280x800.json
          docs-mobile-390x844.json
          docs-tablet-768x1024.json
          landing-desktop-1280x800.json
          landing-mobile-390x844.json
          landing-tablet-768x1024.json
          summary.json
        screenshots/
          control/
            docs-desktop-1280x800.png
            docs-mobile-390x844.png
            docs-tablet-768x1024.png
            landing-desktop-1280x800.png
            landing-mobile-390x844.png
            landing-tablet-768x1024.png
          current/
            docs-desktop-1280x800.png
            docs-mobile-390x844.png
            docs-tablet-768x1024.png
            landing-desktop-1280x800.png
            landing-mobile-390x844.png
            landing-tablet-768x1024.png
          interactions/
            docs-desktop-search-hash-1280x800.png
            docs-mobile-menu-open-390x844.png
      design-system-fidelity-v2/
        capture-report.json
        diffs/
          docs-desktop-1280x800.json
          docs-mobile-390x844.json
          docs-tablet-768x1024.json
          landing-desktop-1280x800.json
          landing-mobile-390x844.json
          landing-tablet-768x1024.json
          summary.json
        screenshots/
          control/
            docs-desktop-1280x800.png
            docs-mobile-390x844.png
            docs-tablet-768x1024.png
            landing-desktop-1280x800.png
            landing-mobile-390x844.png
            landing-tablet-768x1024.png
          current/
            docs-desktop-1280x800.png
            docs-mobile-390x844.png
            docs-tablet-768x1024.png
            landing-desktop-1280x800.png
            landing-mobile-390x844.png
            landing-tablet-768x1024.png
          interactions/
            docs-desktop-search-hash-1280x800.png
            docs-mobile-menu-open-390x844.png
bin/
  lazycodex-ai.js
LICENSE
package-lock.json
package.json
packages/
  web/
    .gitignore
    .mcp.json
    AGENTS.md
    app/
      api/
        github-stars/
          route.ts
      apple-icon.png
      docs/
        page.tsx
      globals.css
      icon.svg
      layout.tsx
      manifest.ts
      og-brand-mark.tsx
      og-image-theme.ts
      opengraph-image.tsx
      page.tsx
      robots.ts
      sitemap.ts
      styles/
        design-system.css
        docs.css
        landing.css
        ulw-demo-app.css
        ulw-demo-panel.css
        ulw-demo-transcript.css
        ulw-demo.css
      twitter-image.tsx
    biome.json
    components/
      design-system/
        actions.tsx
        brand-mark.tsx
        docs-hero.tsx
        layout.tsx
        surfaces.tsx
        typography.tsx
        utils.ts
      docs/
        docs-prev-next.tsx
        docs-shell.tsx
        docs-sidebar.tsx
        docs-toc.tsx
      site/
        brand-image.tsx
        command-card.tsx
        command-cards.tsx
        copy-button.tsx
        docs-cta.tsx
        feature-workflows-section.tsx
        github-stars-pill.tsx
        hephaestus-section.tsx
        hero.tsx
        install-block.tsx
        site-footer.tsx
        site-header.tsx
        team-mode-section.tsx
        ultrawork-section.tsx
        ulw-demo/
          codex-window.tsx
          ulw-demo-section.tsx
          window-chrome.tsx
          window-icons.tsx
          window-panes.tsx
        ulw-research-section.tsx
    content/
      docs/
        cli.md
        configuration.md
        deploy.md
        discipline-agents.md
        faq.md
        getting-started.md
        git-workflow.md
        hooks-lifecycle.md
        init-deep.md
        installation.md
        manual-qa.md
        model-routing.md
        overview.md
        recommended-environment.md
        skills.md
        start-work.md
        tdd.md
        ultrawork.md
        ulw-loop.md
        ulw-plan.md
    DESIGN.md
    e2e/
      docs.spec.ts
      github-stars.spec.ts
      home.spec.ts
      landing-sections.spec.ts
      landing.spec.ts
      lighthouse.spec.ts
      responsive.spec.ts
      seo.spec.ts
      ulw-demo.spec.ts
    lib/
      commands.ts
      docs-content.generated.ts
      docs-sections.ts
      docs-source.ts
      github-stars-format.ts
      github-stars.ts
      site-config.ts
      ulw-demo-scenes.ts
    next.config.ts
    open-next.config.ts
    package.json
    playwright.config.ts
    pnpm-lock.yaml
    pnpm-workspace.yaml
    postcss.config.mjs
    public/
      img/
        badge-ultrawork.avif
        badge-ultrawork.png
        badge-ultrawork.webp
    scripts/
      generate-docs-content.mjs
      lighthouse-live.mjs
    tsconfig.json
    wrangler.toml
plugins/
  omo/
    .codex-plugin/
      plugin.json
    .mcp.json
    components/
      bootstrap/
        AGENTS.md
        dist/
          cli.js
        hooks/
          hooks.json
        manifests/
          node.json
        package.json
        scripts/
          bootstrap.ps1
          build.mjs
          generate-manifests.mjs
          node-dispatch.ps1
        src/
          cli.ts
          download.ts
          environment.ts
          hook.ts
          provision.ts
          setup.ts
          worker.ts
        test/
          download.test.ts
          environment.test.ts
          provision.test.ts
        tsconfig.json
      codegraph/
        AGENTS.md
        dist/
          cli.js
          serve.js
        LICENSE
        NODE-RUNTIME-LICENSES.md
        NOTICE
        package.json
        src/
          cache-gc.ts
          cli.ts
          hook-input.ts
          hook-sweep.ts
          hook-types.ts
          hook.ts
          mcp-bridge.ts
          mcp-unavailable.ts
          post-tool-use-hook.ts
          serve-invocation.ts
          serve.ts
          session-start-command.ts
          session-start-cooldown.ts
          session-start-hook-runtime.ts
          session-start-lock.ts
          session-start-outcome.ts
          session-start-paths.ts
          session-start-project.ts
          session-start-worker-result.ts
          session-start-worker.ts
          sweep-cli.ts
        test/
          cache-gc.test.ts
          hook-exclusion.test.ts
          hook-registration.test.ts
          hook-session-start-guard.test.ts
          hook-store-upgrade.test.ts
          hook-sweep.test.ts
          hook.test.ts
          mcp-bridge-fixtures.ts
          package-runtime.test.ts
          provisioned-node-guard.test.ts
          serve-built-wrapper.test.ts
          serve-mcp-bridge-lifecycle.test.ts
          serve-mcp-bridge.test.ts
          serve-mcp-facade.test.ts
          serve-node-support.test.ts
          serve-provision.test.ts
          serve-unavailable.test.ts
          serve.test.ts
          session-start-node-support.test.ts
          session-start-project.test.ts
          session-start-state.test.ts
          session-start-trust-boundary.test.ts
          session-start-worker-availability.test.ts
          session-start-worker-cooldown.test.ts
          session-start-worker-flow.test.ts
          sweep-cli.test.ts
        tsconfig.build.json
        tsconfig.json
      comment-checker/
        .gitattributes
        .github/
          branch-ruleset.json
          CODEOWNERS
          dependabot.yml
          ISSUE_TEMPLATE/
            bug.yml
            feature.yml
          pull_request_template.md
          workflows/
            ci.yml
            publish.yml
        AGENTS.md
        biome.json
        CHANGELOG.md
        dist/
          cli.js
        hooks/
          hooks.json
        LICENSE
        NOTICE
        package.json
        README.md
        skills/
          comment-checker/
            SKILL.md
        src/
          apply-patch.ts
          cli.ts
          codex-hook.ts
          core-values.ts
          core.ts
          hook-input.ts
          request-extractor.ts
          runner.ts
          types.ts
        test/
          codex-hook-newline.test.ts
          codex-hook.test.ts
          core.test.ts
          fixtures/
            apply-patch-mixed-requests.ts
            post-tool-use.json
          package-smoke.test.ts
          runner.test.ts
        tsconfig.build.json
        tsconfig.json
        vitest.config.ts
      git-bash/
      git-bash-mcp/
        dist/
          cli.js
        AGENTS.md
        dist/
          cli.d.ts
          cli.js
... 1386 more

More Flows by @code-yeongyu.

VerifiedPlugin

Development

oh-my-openagent

You're juggling Claude Code, Codex, and random OSS models. Configuring workflows. Debugging agents. We did the work. Tested everything. Kept what actually shipped. Install oh-my-openagent. Type ultrawork. Done.

36 skills

@code-yeongyu

View Plugin

VerifiedPlugin

Development

lazyclaudecode

The lazy way to run omo inside Claude Code. A native Claude Code plugin marketplace by Sisyphus Labs. What it is · Install · Components · MCP · Telemetry · omo

18 skills

@code-yeongyu

View Plugin

FAQ

lazycodex is a Claude Code plugin with 36 hand-picked skills for development work, indexed on Flowy. Install it with the command on its page. It includes comment-checker, lcx-contribute-bug-fix, lcx-doctor. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.

What is lazycodex?: The one and only agent harness for complex codebases. Project memory, planning, execution, and verified completion inside Codex.
How do I install lazycodex?: Run these in Claude Code: npx -y skills add code-yeongyu/lazycodex --agent claude-code. Then prompt normally.
Does lazycodex auto-invoke its skills?: Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
Is lazycodex free?: Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.

Development

Plugin

lazycodex

The one and only agent harness for complex codebases. Project memory, planning, execution, and verified completion inside Codex.

FLOW.md

code-yeongyu@code-yeongyu

GitHub

Plugin Signal91/100Strong

maintained100

capable83

documented100

adopted74

Install

$ npx -y skills add code-yeongyu/lazycodex --agent claude-code

Run the curl in your terminal, the rest in Claude Code.

Stats

Python TypeScript JavaScript React Next.js

+7 tags

Bash Cloudflare Git GitHub Anthropic OpenAI MCP

3,163

Stars

198

Forks

Active

Maintenance

TypeScript

Language

MIT

License

15h ago

Last commit

2mo ago

Created

Repo: code-yeongyu/lazycodex

In this plugin

26 skills 10 agents 6 MCP

See everything inside

What's inside

Skills

Show all 36 skills

Agents

Show all 10 agents

MCP

next-devtoolsnpx grep_appstdio context7stdio codegraphnode git_bashnode lspnode

README

Read on GitHub

[!NOTE] [OmO] 60K Stars: the terrifying token burner has arrived in LazyCodex.

Sisyphus Labs' OmO is the quality-obsessed agent harness whose public lore says it loved Anthropic models hard enough to get third-party clients blocked. Now that same OmO quality bar is available for Codex through LazyCodex.

If you wanted OmO but did not want the setup ceremony, start here:
npx lazycodex-ai install
Context: OmO 60K Stars on X

🚀 Install

One line. No global install, no npm i -g. Always use npx:

npx lazycodex-ai install

This is shorthand for npx --yes --package oh-my-openagent omo install --platform=codex. For a fully autonomous, no-TUI setup:

npx lazycodex-ai install --no-tui --codex-autonomous

Install from the Codex marketplace (experimental)

codex plugin marketplace add https://github.com/code-yeongyu/lazycodex
codex plugin add omo@sisyphuslabs

Verify it worked

npx lazycodex-ai doctor

Uninstall

npx lazycodex-ai uninstall

Removes the installed plugin cache, bin links, agent roles, and the managed sections of ~/.codex/config.toml.

⚡ Commands

LazyCodex installs these as OmO commands for Codex. Invoke them with the $command syntax shown by the installer.

Command	Type this	What it does
`$ulw-loop`	`$ulw-loop "task" [--completion-promise=TEXT] [--strategy=reset\|continue]`	Self-referential loop that runs until Oracle-verified completion. Caps at 500 iterations in ultrawork mode, 100 in normal mode.
`$ulw-plan`	`$ulw-plan "what to build"`	Prometheus strategic planner. Writes a plan to `plans/<slug>.md`. Never writes product code.
`$start-work`	`$start-work [plan-name] [--worktree <path>]`	Executes a plan until every checkbox is done. Prints ORCHESTRATION COMPLETE.

Full documentation lives at lazycodex.ai/docs.

Use the built-in workflows

1. `$init-deep` creates project memory

Use it when the repository is too large to explain from memory. Run it again when the shape of the codebase changes.

2. The three command pillars stay up front

Use $ulw-plan when the work needs decisions before implementation. It writes a plan to plans/<slug>.md and does not touch product code.

Use $start-work when a plan is ready. It executes the checklist with durable Boulder progress and stops only when the plan is complete.

Use $ulw-loop when the task should keep moving until the result is verified by evidence instead of a hopeful status update.

3. Skills cover specialized work

The command layer stays simple. The skill layer adds specialist judgment for the actual work:

Feature	Use it for
`$init-deep`	Hierarchical project memory through `AGENTS.md`
`$ulw-plan`	Decision-complete planning before code changes
`$start-work`	Durable plan execution with Boulder progress
`$ulw-loop`	Verified completion for open-ended tasks
`review-work`	Multi-angle post-implementation review
`remove-ai-slops`	Behavior-preserving cleanup of AI-looking code
`frontend-ui-ux`	Polished UI surfaces
`programming`	Strict TypeScript, Rust, Python, or Go discipline
`LSP`	Diagnostics, definitions, references, symbols, and renames
`AST-grep`	Structural search and rewrite across code
`rules`	Project instructions from AGENTS, rules, and instruction files
`comment-checker`	Feedback after edit-like operations

4. Sub-agent roles ride Codex's native multi-agent tools

spawn_agent({"message": "TASK: map the auth flow end to end.", "agent_type": "explorer"})

Start at https://lazycodex.ai.

💤 What is this?

LazyCodex packages OmO (oh-my-openagent) as the Codex agent harness for complex codebases.

Think LazyVim for lazy.nvim, but for Codex.

OmO is the agent harness: discipline agents, parallel orchestration, multi-model routing, skills, hooks, and verified completion. LazyCodex packages that harness for Codex.

"LazyVim made Neovim usable for the rest of us. LazyCodex does the same for Codex."

Credit: The LazyCodex name idea is inspired by LazyVim. The Ultragoal and UltraQA ideas are inspired by oh-my-codex, reimplemented from concept for this Codex setup.

🧩 What you get

Feature	Description
🤖 Discipline Agents	Sisyphus orchestrates Hephaestus, Oracle, Librarian. A full AI dev team
🔀 Parallel Execution	Multiple agents working simultaneously on subtasks
🎯 Multi-Model Routing	Automatic model selection per task category
🛠️ Skills System	Extensible skill library for specialized tasks
📋 Hooks & Lifecycle	Pre/post hooks for every agent action
🔧 Zero Config	Sensible defaults, override when you want

🧠 Why different GPT models appear

Do not be surprised if an OmO/LazyCodex run shows models like gpt-5.2 with xhigh, gpt-5.4-mini, gpt-5.3-codex, or newer equivalents like gpt-5.5 with xhigh. That is intentional.

GPT-5.2 is documented by OpenAI as stronger at code review, bug finding, and complex tool use; the announcement notes that its maximum API reasoning effort uses xhigh.
GPT-5.3-Codex is OpenAI's Codex-tuned model for agentic software engineering, with public coding-agent benchmarks such as SWE-Bench Pro, Terminal-Bench 2.0, and OSWorld Verified reported in the GPT-5.3-Codex announcement.
GPT-5.4 mini is positioned for efficient everyday coding, computer use, and subagents; that is why lightweight OmO tasks can land there instead of spending a frontier reasoning model.

Reference links:

🏗️ Architecture

LazyCodex is a thin distribution layer. The core engine is oh-my-openagent (OmO), included as a submodule under src/.

lazycodex/
├── src/                     → oh-my-openagent (submodule)
├── packages/
│   └── web/                 → Next.js 15 + Tailwind v4 + opennextjs-cloudflare
│                              (deployed to lazycodex.ai via Cloudflare Workers)
├── .github/workflows/       → web-ci.yml + web-deploy.yml
├── README.md
└── ...

LazyCodex is part of the omo.dev project. omo in Codex, packaged for the lazy.

👷 Maintainer

LazyCodex is maintained by Jobdori, the AI assistant that builds and ships OmO in real-time.

Meet your own Jobdori, Dori. Learn more at sisyphuslabs.ai.

📄 License

MIT

File tree

1454

code-yeongyu/lazycodexView on GitHub

.agents/
  plugins/
    marketplace.json
.github/
  assets/
    lazycodex-logo.png
    omo-icon-light.svg
    omo-logo.png
    sisyphuslabs.png
  REPO_METADATA.md
  workflows/
    npm-ci.yml
    npm-publish.yml
    pr-source-guidance.yml
    web-ci.yml
    web-deploy.yml
.gitignore
.gitmodules
.omo/
  evidence/
    20260809-readme-light-logo/
      qa.md
    design-system-components-v3.md
    design-system-fidelity-v2.md
    v11-consolidation.md
    v11-demo-chip.png
    v11-full-e2e.txt
    v11-heph-loop.png
    v11-lighthouse.txt
    v11-skills-band.png
    v11-slop-report.md
    v12-full-e2e.txt
    v12-lighthouse.txt
    v12-mobile/
    v12-mobile-green.txt
    v12-mobile-red.txt
      after-demo-m375.png
      after-demo-m390.png
      after-demo-t768.png
      demo-m375.png
      demo-t768.png
      docs-m375-full.png
      docs-t768-full.png
      landing-m375-full.png
      landing-t768-full.png
      s0-header.png
      s1.png
      s10.png
      s2.png
      s3.png
      s4.png
      s5.png
      s6.png
      s7.png
      s8.png
      s9.png
      s99-footer.png
  scripts/
    design-system-fidelity/
      capture-and-drive.mjs
  ulw-loop/
    evidence/
      design-system-components-v3/
        capture-report.json
        diffs/
          docs-desktop-1280x800.json
          docs-mobile-390x844.json
          docs-tablet-768x1024.json
          landing-desktop-1280x800.json
          landing-mobile-390x844.json
          landing-tablet-768x1024.json
          summary.json
        screenshots/
          control/
            docs-desktop-1280x800.png
            docs-mobile-390x844.png
            docs-tablet-768x1024.png
            landing-desktop-1280x800.png
            landing-mobile-390x844.png
            landing-tablet-768x1024.png
          current/
            docs-desktop-1280x800.png
            docs-mobile-390x844.png
            docs-tablet-768x1024.png
            landing-desktop-1280x800.png
            landing-mobile-390x844.png
            landing-tablet-768x1024.png
          interactions/
            docs-desktop-search-hash-1280x800.png
            docs-mobile-menu-open-390x844.png
      design-system-fidelity-v2/
        capture-report.json
        diffs/
          docs-desktop-1280x800.json
          docs-mobile-390x844.json
          docs-tablet-768x1024.json
          landing-desktop-1280x800.json
          landing-mobile-390x844.json
          landing-tablet-768x1024.json
          summary.json
        screenshots/
          control/
            docs-desktop-1280x800.png
            docs-mobile-390x844.png
            docs-tablet-768x1024.png
            landing-desktop-1280x800.png
            landing-mobile-390x844.png
            landing-tablet-768x1024.png
          current/
            docs-desktop-1280x800.png
            docs-mobile-390x844.png
            docs-tablet-768x1024.png
            landing-desktop-1280x800.png
            landing-mobile-390x844.png
            landing-tablet-768x1024.png
          interactions/
            docs-desktop-search-hash-1280x800.png
            docs-mobile-menu-open-390x844.png
bin/
  lazycodex-ai.js
LICENSE
package-lock.json
package.json
packages/
  web/
    .gitignore
    .mcp.json
    AGENTS.md
    app/
      api/
        github-stars/
          route.ts
      apple-icon.png
      docs/
        page.tsx
      globals.css
      icon.svg
      layout.tsx
      manifest.ts
      og-brand-mark.tsx
      og-image-theme.ts
      opengraph-image.tsx
      page.tsx
      robots.ts
      sitemap.ts
      styles/
        design-system.css
        docs.css
        landing.css
        ulw-demo-app.css
        ulw-demo-panel.css
        ulw-demo-transcript.css
        ulw-demo.css
      twitter-image.tsx
    biome.json
    components/
      design-system/
        actions.tsx
        brand-mark.tsx
        docs-hero.tsx
        layout.tsx
        surfaces.tsx
        typography.tsx
        utils.ts
      docs/
        docs-prev-next.tsx
        docs-shell.tsx
        docs-sidebar.tsx
        docs-toc.tsx
      site/
        brand-image.tsx
        command-card.tsx
        command-cards.tsx
        copy-button.tsx
        docs-cta.tsx
        feature-workflows-section.tsx
        github-stars-pill.tsx
        hephaestus-section.tsx
        hero.tsx
        install-block.tsx
        site-footer.tsx
        site-header.tsx
        team-mode-section.tsx
        ultrawork-section.tsx
        ulw-demo/
          codex-window.tsx
          ulw-demo-section.tsx
          window-chrome.tsx
          window-icons.tsx
          window-panes.tsx
        ulw-research-section.tsx
    content/
      docs/
        cli.md
        configuration.md
        deploy.md
        discipline-agents.md
        faq.md
        getting-started.md
        git-workflow.md
        hooks-lifecycle.md
        init-deep.md
        installation.md
        manual-qa.md
        model-routing.md
        overview.md
        recommended-environment.md
        skills.md
        start-work.md
        tdd.md
        ultrawork.md
        ulw-loop.md
        ulw-plan.md
    DESIGN.md
    e2e/
      docs.spec.ts
      github-stars.spec.ts
      home.spec.ts
      landing-sections.spec.ts
      landing.spec.ts
      lighthouse.spec.ts
      responsive.spec.ts
      seo.spec.ts
      ulw-demo.spec.ts
    lib/
      commands.ts
      docs-content.generated.ts
      docs-sections.ts
      docs-source.ts
      github-stars-format.ts
      github-stars.ts
      site-config.ts
      ulw-demo-scenes.ts
    next.config.ts
    open-next.config.ts
    package.json
    playwright.config.ts
    pnpm-lock.yaml
    pnpm-workspace.yaml
    postcss.config.mjs
    public/
      img/
        badge-ultrawork.avif
        badge-ultrawork.png
        badge-ultrawork.webp
    scripts/
      generate-docs-content.mjs
      lighthouse-live.mjs
    tsconfig.json
    wrangler.toml
plugins/
  omo/
    .codex-plugin/
      plugin.json
    .mcp.json
    components/
      bootstrap/
        AGENTS.md
        dist/
          cli.js
        hooks/
          hooks.json
        manifests/
          node.json
        package.json
        scripts/
          bootstrap.ps1
          build.mjs
          generate-manifests.mjs
          node-dispatch.ps1
        src/
          cli.ts
          download.ts
          environment.ts
          hook.ts
          provision.ts
          setup.ts
          worker.ts
        test/
          download.test.ts
          environment.test.ts
          provision.test.ts
        tsconfig.json
      codegraph/
        AGENTS.md
        dist/
          cli.js
          serve.js
        LICENSE
        NODE-RUNTIME-LICENSES.md
        NOTICE
        package.json
        src/
          cache-gc.ts
          cli.ts
          hook-input.ts
          hook-sweep.ts
          hook-types.ts
          hook.ts
          mcp-bridge.ts
          mcp-unavailable.ts
          post-tool-use-hook.ts
          serve-invocation.ts
          serve.ts
          session-start-command.ts
          session-start-cooldown.ts
          session-start-hook-runtime.ts
          session-start-lock.ts
          session-start-outcome.ts
          session-start-paths.ts
          session-start-project.ts
          session-start-worker-result.ts
          session-start-worker.ts
          sweep-cli.ts
        test/
          cache-gc.test.ts
          hook-exclusion.test.ts
          hook-registration.test.ts
          hook-session-start-guard.test.ts
          hook-store-upgrade.test.ts
          hook-sweep.test.ts
          hook.test.ts
          mcp-bridge-fixtures.ts
          package-runtime.test.ts
          provisioned-node-guard.test.ts
          serve-built-wrapper.test.ts
          serve-mcp-bridge-lifecycle.test.ts
          serve-mcp-bridge.test.ts
          serve-mcp-facade.test.ts
          serve-node-support.test.ts
          serve-provision.test.ts
          serve-unavailable.test.ts
          serve.test.ts
          session-start-node-support.test.ts
          session-start-project.test.ts
          session-start-state.test.ts
          session-start-trust-boundary.test.ts
          session-start-worker-availability.test.ts
          session-start-worker-cooldown.test.ts
          session-start-worker-flow.test.ts
          sweep-cli.test.ts
        tsconfig.build.json
        tsconfig.json
      comment-checker/
        .gitattributes
        .github/
          branch-ruleset.json
          CODEOWNERS
          dependabot.yml
          ISSUE_TEMPLATE/
            bug.yml
            feature.yml
          pull_request_template.md
          workflows/
            ci.yml
            publish.yml
        AGENTS.md
        biome.json
        CHANGELOG.md
        dist/
          cli.js
        hooks/
          hooks.json
        LICENSE
        NOTICE
        package.json
        README.md
        skills/
          comment-checker/
            SKILL.md
        src/
          apply-patch.ts
          cli.ts
          codex-hook.ts
          core-values.ts
          core.ts
          hook-input.ts
          request-extractor.ts
          runner.ts
          types.ts
        test/
          codex-hook-newline.test.ts
          codex-hook.test.ts
          core.test.ts
          fixtures/
            apply-patch-mixed-requests.ts
            post-tool-use.json
          package-smoke.test.ts
          runner.test.ts
        tsconfig.build.json
        tsconfig.json
        vitest.config.ts
      git-bash/
      git-bash-mcp/
        dist/
          cli.js
        AGENTS.md
        dist/
          cli.d.ts
          cli.js
... 1386 more

More Flows by @code-yeongyu.

VerifiedPlugin

Development

oh-my-openagent

36 skills

@code-yeongyu

View Plugin

VerifiedPlugin

Development

lazyclaudecode

The lazy way to run omo inside Claude Code. A native Claude Code plugin marketplace by Sisyphus Labs. What it is · Install · Components · MCP · Telemetry · omo

18 skills

@code-yeongyu

View Plugin

FAQ

What is lazycodex?: The one and only agent harness for complex codebases. Project memory, planning, execution, and verified completion inside Codex.
How do I install lazycodex?: Run these in Claude Code: npx -y skills add code-yeongyu/lazycodex --agent claude-code. Then prompt normally.
Does lazycodex auto-invoke its skills?: Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
Is lazycodex free?: Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.

lazycodex

Skills

Agents

MCP

README

🚀 Install

Install from the Codex marketplace (experimental)

Verify it worked

Uninstall

⚡ Commands

Use the built-in workflows

1. $init-deep creates project memory

2. The three command pillars stay up front

3. Skills cover specialized work

4. Sub-agent roles ride Codex's native multi-agent tools

💤 What is this?

🧩 What you get

🧠 Why different GPT models appear

🏗️ Architecture

👷 Maintainer

📄 License

File tree

More Flows by @code-yeongyu.

oh-my-openagent

lazyclaudecode

lazycodex

Skills

Agents

MCP

README

🚀 Install

Install from the Codex marketplace (experimental)

Verify it worked

Uninstall

⚡ Commands

Use the built-in workflows

1. $init-deep creates project memory

2. The three command pillars stay up front

3. Skills cover specialized work

4. Sub-agent roles ride Codex's native multi-agent tools

💤 What is this?

🧩 What you get

🧠 Why different GPT models appear

🏗️ Architecture

👷 Maintainer

📄 License

File tree

More Flows by @code-yeongyu.

oh-my-openagent

lazyclaudecode

1. `$init-deep` creates project memory

1. `$init-deep` creates project memory