{"id":51280200,"url":"https://github.com/rblalock/omakaseagent","last_synced_at":"2026-06-30T01:03:12.786Z","repository":{"id":364067826,"uuid":"1256663301","full_name":"rblalock/omakaseagent","owner":"rblalock","description":"The chef's standard for AI agent work: twelve rules, a critique gate, and project memory. One skill. Craftsman's taste. Zero AI slop.","archived":false,"fork":false,"pushed_at":"2026-06-20T14:50:15.000Z","size":1203,"stargazers_count":7,"open_issues_count":0,"forks_count":1,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-06-20T16:24:44.608Z","etag":null,"topics":["agent-skills","ai-agents","anti-slop","claude","claude-code","code-quality","codex","cursor","developer-tools","llm"],"latest_commit_sha":null,"homepage":"https://omakaseagent.com","language":"JavaScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/rblalock.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null}},"created_at":"2026-06-02T01:38:05.000Z","updated_at":"2026-06-20T14:50:19.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/rblalock/omakaseagent","commit_stats":null,"previous_names":["rblalock/omakaseagent"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/rblalock/omakaseagent","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rblalock%2Fomakaseagent","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rblalock%2Fomakaseagent/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rblalock%2Fomakaseagent/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rblalock%2Fomakaseagent/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/rblalock","download_url":"https://codeload.github.com/rblalock/omakaseagent/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rblalock%2Fomakaseagent/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34948227,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-29T02:00:05.398Z","response_time":58,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agent-skills","ai-agents","anti-slop","claude","claude-code","code-quality","codex","cursor","developer-tools","llm"],"created_at":"2026-06-30T01:03:12.195Z","updated_at":"2026-06-30T01:03:12.775Z","avatar_url":"https://github.com/rblalock.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n\n\u003ca href=\"https://omakaseagent.com\"\u003e\u003cimg src=\"https://omakaseagent.com/og.png\" alt=\"Omakase Agent: the chef's standard for AI agent work\" width=\"720\"\u003e\u003c/a\u003e\n\n**The chef's standard.** One skill. Craftsman's taste. Zero AI slop.\n\n[omakaseagent.com](https://omakaseagent.com)\n\n[![npm](https://img.shields.io/npm/v/omakaseagent?color=d93a1f\u0026label=npm)](https://www.npmjs.com/package/omakaseagent)\n[![license](https://img.shields.io/badge/license-Apache--2.0-2a221b)](LICENSE)\n[![skills.sh](https://skills.sh/b/rblalock/omakaseagent)](https://skills.sh/rblalock/omakaseagent)\n\n\u003c/div\u003e\n\nTrust the chef — state the goal. Omakase applies the bar, remembers taste, and critiques before anything significant ships.\n\n## What it is\n\nOmakase is a **portable quality standard** for agent work: twelve rules, a critique rubric, and project memory (`.omakaseagent/taste.md`, `decisions.md`). Not a bag of prompts.\n\nGeneric, hedging, over-engineered output fails. Non-trivial work explains *why* this approach.\n\n## Quick start\n\nPaste this into your agent (Claude Code, Cursor, wherever it lives) — the setup is agentic, not a script:\n\n```text\nRun `npx omakaseagent init` in this repo. Then read the AGENTS.md and Omakase\nskill it installs, and adopt the twelve rules and the critique gate for all\nwork here from now on. Next, run `npx omakaseagent learn` and fill in\n.omakaseagent/factory.md with this repo's real build, test, and verify\ncommands. When you're done, tell me what standard you're now working under\nand how I should hand you tasks.\n```\n\nPrefer the terminal? `npx omakaseagent init` then `npx omakaseagent learn` — but the agent should be the one reading and adopting what gets installed.\n\nReload your harness, then talk to a **lead** (not a menu of skills):\n\n| Harness | Example |\n|---------|---------|\n| Cursor / Claude Code | `@omakase-engineer add rate limiting with backoff` |\n| OpenCode | `opencode run --agent omakase-engineer \"add rate limiting…\"` |\n| Grok | `grok --agent omakase-engineer \"…\"` |\n| Claude CLI | `claude -p --agent omakase-critic \"review the auth module\"` |\n\n**Leads:** `@omakase-engineer` · `@omakase-critic` · `@omakase-archivist` — specialists stay internal; leads delegate.\n\n**Router skill** (`omakase-router`) is only for plan, taste, handoff, and init when you are not using a native lead:\n\n```\n/omakase-router plan \u003cgoal\u003e\n/omakase-router critique \u003ctarget\u003e\n```\n\nHarness quirks, Codex names, and troubleshooting: [docs/NATIVE-SUBAGENTS.md](docs/NATIVE-SUBAGENTS.md).\n\n## The standard (always loaded)\n\n| File | Role |\n|------|------|\n| [OMAKASE-RULES.md](OMAKASE-RULES.md) | Twelve non-negotiable rules |\n| [OMAKASE-CRITIQUE.md](OMAKASE-CRITIQUE.md) | Rubric for major output |\n| [OMAKASE-PRINCIPLES.md](OMAKASE-PRINCIPLES.md) | Why this is a standard, not a prompt pack |\n\nMemory lives in `.omakaseagent/` after `init`.\n\n## Install\n\n**New project:**\n\n```bash\nnpx omakaseagent init\n```\n\n**Skill + agents only** (harness already configured):\n\n```bash\nnpx omakaseagent skills install          # auto-detect harness\nnpx omakaseagent skills install cursor   # or: claude | agents | grok | codex\n```\n\nAlso on the skills ecosystem: `npx skills add rblalock/omakaseagent` ([skills.sh](https://skills.sh/rblalock/omakaseagent)).\n\nUse `npx omakaseagent skills install --no-native-agents` for skill-only. Verify artifacts: `npm run verify:native-agents`.\n\n## Developing this repo\n\nSource: `skill/`. Shipped bundles: `dist/` (committed — do not edit by hand).\n\n```bash\nnpm link              # local CLI\nnpm run build\nnpm run verify:native-agents\nnpx omakaseagent init      # dogfood in this clone\nnpx omakaseagent learn     # factory layout for this repo\n```\n\n## License\n\nApache 2.0","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frblalock%2Fomakaseagent","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frblalock%2Fomakaseagent","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frblalock%2Fomakaseagent/lists"}