PaperClipAI/packages/shared/src/external-agent-guidance.ts

/** Tool-use guidance for external-agent onboarding and durable connection instructions. */
export const EXTERNAL_AGENT_TOOL_GUIDANCE = `When you receive a Paperclip assignment or message, use your own available tools, apps, plugins, skills, and capabilities to complete the requested work, then return the result to Paperclip. For example, use your existing Slack connection when the task calls for Slack. Paperclip's app catalog describes what this connection exposes; it is not a list of everything you can use in your own runtime. A missing Paperclip app connection does not make your own connection unavailable. Respect each tool's existing permissions, approvals, and the user's current instructions. Keep Paperclip data and actions within this connection's authorized company, agent, and task. Never use another Paperclip connection or identity to bypass a denial. Setup or test restrictions apply only to their stated scope; do not carry them into later requests unless the user explicitly says they continue.`;

/** The assignment catalog constrains the Paperclip bridge, not the external runtime. */
export const DOT_AGENT_TOOL_GUIDANCE = `${EXTERNAL_AGENT_TOOL_GUIDANCE}\n\nUse the assignment catalog through paperclip_dot_tool for Paperclip operations. Use your native tools directly for the rest of the work; they do not need to appear in that catalog. Record useful results and deliverables on the task and follow the Paperclip completion instructions.`;

export const GROK_BOT_AGENT_TOOL_GUIDANCE = `${EXTERNAL_AGENT_TOOL_GUIDANCE}\n\nUse the current assignment catalog through paperclip_grok_tool for first-party Paperclip operations. Grok Bot retains its own connected apps and persistent memory. Retrieve current task context and instructions for each Paperclip work session; do not assume provider memory is isolated or reset. Acknowledge routine wakes using paperclip_grok_ack_wake. Accept admitted assignments before task operations and keep request IDs stable across retries. If an operation is pending, poll paperclip_grok_operation_status with the same assignmentId and requestId for its durable outcome before dependent work. Completed or rejected receipts are terminal; an unknown outcome needs reconciliation. Do not repeat it under a new ID. A tool result does not start another routine. At safe boundaries and before finishing, drain paperclip_grok_inbox and read current task history to incorporate queued feedback. Report progress, questions and deliverables in Paperclip, then follow its canonical completion instructions. Routine acceptance, Paperclip session completion and remote process termination are distinct. Grok usage and spending are not reported.`;