{"data":{"slug":"clawplays-ospec","name":"ospec","tagline":"Spec-driven workflow framework for AI coding agents","github_url":"https://github.com/clawplays/ospec","owner":"clawplays","repo":"ospec","owner_avatar_url":"https://avatars.githubusercontent.com/u/258579063?v=4","primary_language":"JavaScript","stars":488,"forks":24,"topics":["agentic-ai","agentic-coding","ai","ai-agents","ai-coding-assistant","ai-workflow","claude-code","cli","codex","coding-agent","developer-tools","llm","loop-engineering","mcp","model-context-protocol","prompt-engineering","sdd","spec-driven-development"],"archived":false,"github_pushed_at":"2026-08-26T08:12:13+00:00","maintenance_label":"Active","stars_delta_30d":-36,"url":"https://www.graphcanon.com/tools/clawplays-ospec","markdown_url":"https://www.graphcanon.com/tools/clawplays-ospec.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/clawplays-ospec","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=clawplays-ospec","description":"Spec-driven, agentic workflow framework for AI coding agents. Turn a request into a verifiable goal loop — plan, act, verify — with durable specs and evidence in your repo. Works with Claude Code, Codex, Gemini, OpenCode, and plain CLI.","homepage_url":"https://ospec.ai","license":"MIT","open_issues":0,"watchers":12,"ai_summary":"ospec provides an agentic and spec-driven method to manage and verify goals through iterative cycles of plans, actions, verification with evidence tracked in the repository.","readme_excerpt":"## Install With npm\n\n```bash\nnpm install -g @clawplays/ospec-cli\n```\n\nOfficial package: `@clawplays/ospec-cli`  \nCommand: `ospec`  \nVerify install: `ospec --help`\n\n---\n\n## Quick Start\n\nOSpec only takes 3 steps:\n\n1. initialize OSpec in your project directory\n2. create and advance one change for a requirement, document update, or bug fix\n3. archive the accepted change after deployment and validation are complete\n\n---\n\n## License\n\nThis project is licensed under the [MIT License](LICENSE).","github_created_at":"2026-03-31T02:49:55+00:00","created_at":"2026-07-11T11:55:22.196216+00:00","updated_at":"2026-09-20T06:47:15.734848+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"}],"tags":[{"slug":"agentic-ai","name":"agentic-ai"},{"slug":"coding-agents","name":"coding-agents"},{"slug":"llm","name":"llm"},{"slug":"spec-driven-development","name":"spec-driven-development"}],"trust":{"provenance":{"is_fork":false,"github_id":1196768707,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T06:47:13.553Z","maintenance":{"label":"Active","score":82,"methodology":"github_public_v1","releases_90d":30,"days_since_push":24,"last_release_at":"2026-08-26T08:13:30Z","stars_delta_30d":-36,"open_issues_delta_30d":0},"security_summary":{"status":"no_manifest","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:55:23.398Z","medium_count":0,"scan_profile":"mcp_manifest","critical_count":0}},"capability_facts":{"mcp":{"source":"repo_scan","observed_at":"2026-09-20T06:47:14.608Z","server_manifest":false},"scan":{"source":"repo_scan","observed_at":"2026-09-20T06:47:14.608Z"},"has_cli":{"value":true,"source":"package.json:bin|scripts","observed_at":"2026-09-20T06:47:14.608Z"},"languages":{"value":["javascript","typescript"],"source":"github.language+package.json","observed_at":"2026-09-20T06:47:14.608Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-20T06:47:14.608Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["Use ospec when you prefer an agentic method that aligns well with JavaScript environments and want to ensure that your goals are verifiable through clear specifications and evidence.","Select ospec if you are working extensively with Claude Code, Codex, Gemini, OpenCode, or other coding agents and require a structured workflow engine that supports these integrations."],"when_not_to_use":["Avoid using ospec if your project requires integration with non-JavaScript languages or frameworks that are not compatible with its spec-driven development model.","If real-time feedback loops are critical to the success of your AI coding agent, and you need more instantaneous verification processes than what ospec's structured iterations can provide."],"source":"enrich:decision_facts","observed_at":"2026-07-15T09:07:55.259Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"ospec, a spec-driven workflow framework for AI coding agents, employs iterative cycles of plans, actions, verification with evidence logged in the repository."}]}}