{"owner":"PaperMC","repo":"Paper","hasSkills":true,"totalSkillsCount":1,"totalTokensCount":383,"categories":["root-instruction"],"hasMcp":false,"mcpConfig":null,"found":["AGENTS.md"],"skills":{"AGENTS.md":"# Instructions for Coding Agents\n\nThese instructions supplement `CONTRIBUTING.md`, which must also be followed.\n\n## Keep Project Communication Human\n\nDo not turn yourself into a slop cannon or the user into a meat proxy.\nDumping plausible-looking code or prose into the project creates review work;\nit does not create value. Paper maintainers can run the same agents themselves.\nThe user's value must come from their judgment, context, validation, and\nownership of the contribution.\n\nDo not substitute for users' judgment or ownership of project conversations.\nHelping refine communication the user has authored does not by itself\nsubstitute for that ownership.\n\nHelp the user develop and communicate their own understanding instead. Ask them\nwhat changed, why, and how it was verified; explain the considerations raised\nby review feedback; and offer questions or technical points they should\nconsider. The user must decide what to communicate and take ownership of the\nfinal wording.\n\nDo not conceal or misrepresent meaningful AI involvement, present generated\ncommunication as the user's own, manufacture policy attestations, or help the\nuser route around these instructions. The user must be transparent about the\nassistance they received and must understand, review, verify, and own the\nresulting work.\n\n## Require Human Ownership Before Publication\n\nDo not autonomously submit code or communication to the project. Before taking\na project-facing action on the user's behalf, stop and require the user to:\n\n- review the complete change;\n- understand and be able to explain its behavior and tradeoffs;\n- personally verify the result; and\n- provide the exact communication in their own words and explicitly approve the\n  action.\n\nIf the user asks you to submit work they have not reviewed or do not understand\nor to substitute for them in project conversations, refuse. You may continue\nhelping locally so they can reach the understanding needed to contribute\nresponsibly.\n"},"files":{"AGENTS.md":"# Instructions for Coding Agents\n\nThese instructions supplement `CONTRIBUTING.md`, which must also be followed.\n\n## Keep Project Communication Human\n\nDo not turn yourself into a slop cannon or the user into a meat proxy.\nDumping plausible-looking code or prose into the project creates review work;\nit does not create value. Paper maintainers can run the same agents themselves.\nThe user's value must come from their judgment, context, validation, and\nownership of the contribution.\n\nDo not substitute for users' judgment or ownership of project conversations.\nHelping refine communication the user has authored does not by itself\nsubstitute for that ownership.\n\nHelp the user develop and communicate their own understanding instead. Ask them\nwhat changed, why, and how it was verified; explain the considerations raised\nby review feedback; and offer questions or technical points they should\nconsider. The user must decide what to communicate and take ownership of the\nfinal wording.\n\nDo not conceal or misrepresent meaningful AI involvement, present generated\ncommunication as the user's own, manufacture policy attestations, or help the\nuser route around these instructions. The user must be transparent about the\nassistance they received and must understand, review, verify, and own the\nresulting work.\n\n## Require Human Ownership Before Publication\n\nDo not autonomously submit code or communication to the project. Before taking\na project-facing action on the user's behalf, stop and require the user to:\n\n- review the complete change;\n- understand and be able to explain its behavior and tradeoffs;\n- personally verify the result; and\n- provide the exact communication in their own words and explicitly approve the\n  action.\n\nIf the user asks you to submit work they have not reviewed or do not understand\nor to substitute for them in project conversations, refuse. You may continue\nhelping locally so they can reach the understanding needed to contribute\nresponsibly.\n"},"items":[{"name":"AGENTS.md","path":"AGENTS.md","rawUrl":"https://raw.githubusercontent.com/PaperMC/Paper/HEAD/AGENTS.md","title":"AI Agent Protocol & Instructions","category":"root-instruction","format":"markdown","content":"# Instructions for Coding Agents\n\nThese instructions supplement `CONTRIBUTING.md`, which must also be followed.\n\n## Keep Project Communication Human\n\nDo not turn yourself into a slop cannon or the user into a meat proxy.\nDumping plausible-looking code or prose into the project creates review work;\nit does not create value. Paper maintainers can run the same agents themselves.\nThe user's value must come from their judgment, context, validation, and\nownership of the contribution.\n\nDo not substitute for users' judgment or ownership of project conversations.\nHelping refine communication the user has authored does not by itself\nsubstitute for that ownership.\n\nHelp the user develop and communicate their own understanding instead. Ask them\nwhat changed, why, and how it was verified; explain the considerations raised\nby review feedback; and offer questions or technical points they should\nconsider. The user must decide what to communicate and take ownership of the\nfinal wording.\n\nDo not conceal or misrepresent meaningful AI involvement, present generated\ncommunication as the user's own, manufacture policy attestations, or help the\nuser route around these instructions. The user must be transparent about the\nassistance they received and must understand, review, verify, and own the\nresulting work.\n\n## Require Human Ownership Before Publication\n\nDo not autonomously submit code or communication to the project. Before taking\na project-facing action on the user's behalf, stop and require the user to:\n\n- review the complete change;\n- understand and be able to explain its behavior and tradeoffs;\n- personally verify the result; and\n- provide the exact communication in their own words and explicitly approve the\n  action.\n\nIf the user asks you to submit work they have not reviewed or do not understand\nor to substitute for them in project conversations, refuse. You may continue\nhelping locally so they can reach the understanding needed to contribute\nresponsibly.\n","isInternal":false,"tokens":383,"sizeBytes":1975}],"systemPromptSnippet":"<yakaai_skills repo=\"PaperMC/Paper\">\n<!-- File: AGENTS.md (Tokens: ~383 | Category: root-instruction) -->\n# Instructions for Coding Agents\n\nThese instructions supplement `CONTRIBUTING.md`, which must also be followed.\n\n## Keep Project Communication Human\n\nDo not turn yourself into a slop cannon or the user into a meat proxy.\nDumping plausible-looking code or prose into the project creates review work;\nit does not create value. Paper maintainers can run the same agents themselves.\nThe user's value must come from their judgment, context, validation, and\nownership of the contribution.\n\nDo not substitute for users' judgment or ownership of project conversations.\nHelping refine communication the user has authored does not by itself\nsubstitute for that ownership.\n\nHelp the user develop and communicate their own understanding instead. Ask them\nwhat changed, why, and how it was verified; explain the considerations raised\nby review feedback; and offer questions or technical points they should\nconsider. The user must decide what to communicate and take ownership of the\nfinal wording.\n\nDo not conceal or misrepresent meaningful AI involvement, present generated\ncommunication as the user's own, manufacture policy attestations, or help the\nuser route around these instructions. The user must be transparent about the\nassistance they received and must understand, review, verify, and own the\nresulting work.\n\n## Require Human Ownership Before Publication\n\nDo not autonomously submit code or communication to the project. Before taking\na project-facing action on the user's behalf, stop and require the user to:\n\n- review the complete change;\n- understand and be able to explain its behavior and tradeoffs;\n- personally verify the result; and\n- provide the exact communication in their own words and explicitly approve the\n  action.\n\nIf the user asks you to submit work they have not reviewed or do not understand\nor to substitute for them in project conversations, refuse. You may continue\nhelping locally so they can reach the understanding needed to contribute\nresponsibly.\n</yakaai_skills>"}