# AI Influencer OS - Agent Guide

OpenClaw AI creator system with configurable persona, memory, life continuity, Wavespeed images, social drafts, QA, and approval-gated Instagram posting automation.

## Agent instruction

Do not scrape the human UI. Use this agent guide, the package manifest, and raw Buildprint files.

1. Fetch package manifest: `/buildprints/ai-influencer-os/package.json`
2. Read order: `BUILDPRINT.md`.
3. Do not scrape human cards. Use this manifest, agent.md, and raw files. BUILDPRINT.md is the canonical start file and owns the required read order, phase gates, and acceptance gates. Structured control files are machine-readable mirrors only.
4. Follow the Buildprint's alignment/question rules before implementation.
5. Run required validation and write requested validation evidence plus the final chat handover.

## Metadata

- slug: `ai-influencer-os`
- category: `Product OS`
- tier: `agent-grade`
- status: `validated`
- runtime: OpenClaw
- stack: OpenClaw, Persona memory, Wavespeed, Social publishing, Docker

## Entrypoints

- Human page: /buildprints/ai-influencer-os/
- Manifest JSON: /buildprints/ai-influencer-os/package.json
- Prompt: /buildprints/ai-influencer-os/prompt.txt
- GitHub: https://github.com/DomEscobar/agent-buildprint/tree/main/buildprints/ai-influencer-os
- Raw base: https://agent-buildprint.com/buildprints/ai-influencer-os/files

## Files

- `BUILDPRINT.md` - compatibility bootstrap or package contract (required)
- `checks/acceptance.md` - acceptance checklist (required)
- `CONTRACTS.md` - legacy interface/data contracts, when present (required)
- `DEFAULT_PRESET.md` - Buildprint package file (required)
- `PLAN.md` - legacy execution index, when present (required)
- `plans/00-alignment.md` - phase rail (required)
- `plans/01-openclaw-runtime-shape.md` - phase rail (required)
- `plans/02-persona-runtime.md` - phase rail (required)
- `plans/03-memory-life-state.md` - phase rail (required)
- `plans/04-wavespeed-image.md` - phase rail (required)
- `plans/05-social-planner.md` - phase rail (required)
- `plans/06-publisher-handoff.md` - phase rail (required)
- `plans/07-manager-audit.md` - phase rail (required)
- `plans/08-tests-validation.md` - phase rail (required)
- `policies/media.md` - policy artifact (optional)
- `policies/safety.md` - policy artifact (optional)
- `publication.json` - machine-readable mirror (required)
- `questions.md` - configuration interview (required)
- `README.md` - human overview, non-authoritative (required)
- `schemas/buildprint.meta.json` - schema artifact (optional)
- `SPEC.md` - legacy behavior requirements, when present (required)
- `TEST_MATRIX.md` - legacy risk-to-test alignment, when present (required)
- `VALIDATION_TEMPLATE.md` - legacy completion report template, when present (required)

## Copyable implementation prompt

```txt
Use the AI Influencer OS Buildprint. First bootstrap exact snapshots: agb start https://agent-buildprint.com/buildprints/ai-influencer-os/package.json . If agb is not installed, clone https://github.com/DomEscobar/agent-buildprint and run node agent-buildprint/bin/agb.js start https://agent-buildprint.com/buildprints/ai-influencer-os/package.json . Then read .buildprint/next-agent.md and continue. Do not write Buildprint snapshots manually. Focus on the approval-gated influencer workflow; do not auto-publish by default.
```