{"id":50528095,"url":"https://github.com/dadwadw233/claude-code-philosophy","last_synced_at":"2026-06-03T10:01:25.558Z","repository":{"id":349335105,"uuid":"1197590939","full_name":"dadwadw233/claude-code-philosophy","owner":"dadwadw233","description":"Vendor-neutral agent design skill inspired by Claude Code-class systems.","archived":false,"fork":false,"pushed_at":"2026-04-05T11:25:43.000Z","size":22,"stargazers_count":5,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-04-05T13:14:33.034Z","etag":null,"topics":["agent-design","agents","ai-tools","claude-code","codex","skill"],"latest_commit_sha":null,"homepage":null,"language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/dadwadw233.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":null,"dco":null,"cla":null}},"created_at":"2026-03-31T17:52:23.000Z","updated_at":"2026-04-05T11:18:59.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/dadwadw233/claude-code-philosophy","commit_stats":null,"previous_names":["dadwadw233/claude-code-philosophy"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/dadwadw233/claude-code-philosophy","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dadwadw233%2Fclaude-code-philosophy","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dadwadw233%2Fclaude-code-philosophy/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dadwadw233%2Fclaude-code-philosophy/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dadwadw233%2Fclaude-code-philosophy/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dadwadw233","download_url":"https://codeload.github.com/dadwadw233/claude-code-philosophy/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dadwadw233%2Fclaude-code-philosophy/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33858578,"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":"2026-06-03T02:00:06.370Z","response_time":59,"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-design","agents","ai-tools","claude-code","codex","skill"],"created_at":"2026-06-03T10:01:24.726Z","updated_at":"2026-06-03T10:01:25.553Z","avatar_url":"https://github.com/dadwadw233.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# Claude Code Philosophy\n\n[![Featured in awesome-agent-skills](https://img.shields.io/badge/featured%20in-awesome--agent--skills-2563eb?style=flat-square)](https://github.com/heilcheng/awesome-agent-skills)\n\nDesign better agents.\n\n`claude-code-philosophy` is a public skill and plugin package for developers who want to build agentic systems that are actually useful: controllable, legible, recoverable, and grounded in real product constraints.\n\nIt is inspired by the design philosophy behind Claude Code-class agent systems, but written as **vendor-neutral guidance** that can help builders working with Codex, Claude Code, or their own custom agent runtimes.\n\nThis project is unofficial. It is not affiliated with Anthropic.\n\n## Why this exists\n\nA lot of agent projects are still too shallow:\n\n- great demo, weak product\n- many tools, no capability model\n- “memory” with no boundaries\n- autonomy with no control surface\n- impressive output, fragile runtime\n\nThis project exists to push in the other direction.\n\nThe core belief is simple: the difference between a toy agent and a useful one is usually **the harness**, not just the model or the prompt.\n\n## What you get\n\nThis repository currently ships one installable skill:\n\n- `agent-design-coach`\n\nIt helps developers:\n\n- turn fuzzy agent ideas into concrete system designs\n- review an existing agent for harness, tool, memory, safety, and UX gaps\n- decide whether a workflow needs a real agent or a simpler tool\n- make vibe-coded AI projects more disciplined and useful\n\n## What the skill teaches\n\nThe skill is built around a few strong principles:\n\n- harness-first design\n- explicit tool and permission boundaries\n- layered memory instead of one giant blob\n- recovery and durability as first-class features\n- human control as part of the product\n- practical usefulness over fake autonomy\n\n## Quick install\n\n### Codex: install the skill directly\n\nInside Codex, run:\n\n```text\n$skill-installer install https://github.com/dadwadw233/claude-code-philosophy/tree/main/skills/agent-design-coach\n```\n\nThen restart Codex.\n\n### Claude Code: install through the repository marketplace\n\nInside Claude Code, run:\n\n```text\n/plugin marketplace add dadwadw233/claude-code-philosophy\n/plugin install claude-code-philosophy@claude-code-philosophy\n```\n\nThen invoke the installed skill with:\n\n```text\n/claude-code-philosophy:agent-design-coach\n```\n\n### Manual install\n\n- Codex: copy this repo to `~/.codex/plugins/claude-code-philosophy` and register it in `~/.agents/plugins/marketplace.json`\n- Claude Code: copy `skills/agent-design-coach` to `~/.claude/skills/agent-design-coach`\n\nDetailed examples are below.\n\n## Installation details\n\n### Codex: direct skill install\n\nThis is the simplest path if you only want the skill itself.\n\n```text\n$skill-installer install https://github.com/dadwadw233/claude-code-philosophy/tree/main/skills/agent-design-coach\n```\n\nAfter installation, restart Codex.\n\n### Codex: local plugin install\n\nClone the repo:\n\n```bash\ngit clone git@github.com:dadwadw233/claude-code-philosophy.git\n```\n\nCopy it into your local plugin area:\n\n```bash\nmkdir -p ~/.codex/plugins\ncp -R /absolute/path/to/claude-code-philosophy ~/.codex/plugins/claude-code-philosophy\n```\n\nCreate or update `~/.agents/plugins/marketplace.json`:\n\n```json\n{\n  \"name\": \"personal-plugins\",\n  \"interface\": {\n    \"displayName\": \"Personal Plugins\"\n  },\n  \"plugins\": [\n    {\n      \"name\": \"claude-code-philosophy\",\n      \"source\": {\n        \"source\": \"local\",\n        \"path\": \"./.codex/plugins/claude-code-philosophy\"\n      },\n      \"policy\": {\n        \"installation\": \"AVAILABLE\",\n        \"authentication\": \"ON_INSTALL\"\n      },\n      \"category\": \"Productivity\"\n    }\n  ]\n}\n```\n\nRestart Codex. The plugin should appear in the plugin directory.\n\n### Claude Code: marketplace install\n\nThis repository includes a Claude Code marketplace manifest at `.claude-plugin/marketplace.json`.\n\nRegister the marketplace:\n\n```text\n/plugin marketplace add dadwadw233/claude-code-philosophy\n```\n\nInstall the plugin:\n\n```text\n/plugin install claude-code-philosophy@claude-code-philosophy\n```\n\nAfter installation, the explicit slash command is:\n\n```text\n/claude-code-philosophy:agent-design-coach\n```\n\n### Claude Code: manual skill install\n\nCopy the skill directory:\n\n```bash\nmkdir -p ~/.claude/skills\ncp -R skills/agent-design-coach ~/.claude/skills/agent-design-coach\n```\n\nFor a manually installed standalone skill, invoke:\n\n```text\n/agent-design-coach\n```\n\n## How to use it\n\n### Codex\n\n- `Use $agent-design-coach to turn this coding-agent idea into a real system architecture.`\n- `Use $agent-design-coach to review this repo's agent design for harness, memory, permissions, and UX gaps.`\n\n### Claude Code plugin install\n\n- `/claude-code-philosophy:agent-design-coach`\n- `/claude-code-philosophy:agent-design-coach Review this coding agent and tell me what is weak in its harness design.`\n\n### Claude Code standalone skill install\n\n- `/agent-design-coach`\n- `/agent-design-coach Turn this vibe-coded AI product into a disciplined agent design.`\n\n## What a good output should look like\n\nWhen the skill is working well, it should produce guidance that includes:\n\n- user value and task framing\n- recommended system shape\n- harness and execution loop\n- tool and permission boundaries\n- memory and context strategy\n- human control and UX surfaces\n- failure modes and evaluation criteria\n- immediate implementation next steps\n\n## Repository structure\n\n```text\n.\n├── .claude-plugin/\n│   ├── marketplace.json\n│   └── plugin.json\n├── .codex-plugin/\n│   └── plugin.json\n├── .agents/plugins/\n│   └── marketplace.json\n└── skills/\n    └── agent-design-coach/\n        ├── SKILL.md\n        ├── LICENSE.txt\n        ├── agents/\n        │   └── openai.yaml\n        └── references/\n            ├── design-principles.md\n            ├── review-rubric.md\n            └── system-patterns.md\n```\n\n## Design notes\n\nThe repository is intentionally layered:\n\n- `SKILL.md` stays procedural and activation-focused\n- `references/` contains the heavier philosophy and review material\n- `.codex-plugin/` packages the project for Codex\n- `.claude-plugin/` packages the project for Claude Code\n\nThis keeps the skill lean while still preserving enough depth to be genuinely useful.\n\n## Inspiration\n\nThis project draws from:\n\n- Claude Code as an example of a strong agent runtime and product\n- official OpenAI/Codex skill and plugin conventions\n- Anthropic's public skills and skills marketplace patterns\n- the broader Agent Skills ecosystem\n\n## Non-goals\n\nThis project is not trying to:\n\n- replicate Claude Code\n- provide a universal agent framework\n- replace actual engineering judgment\n- encourage maximal autonomy by default\n\nIt is trying to help developers make better design decisions.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdadwadw233%2Fclaude-code-philosophy","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdadwadw233%2Fclaude-code-philosophy","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdadwadw233%2Fclaude-code-philosophy/lists"}