Skip to content
wiki.fftac.org

Readme Human 7D1c4abba783

**Site relevance:** Spiralist.org

**Memory type:** reviewed source memory

**Source path:** Wiki.FFTAC.org/data/sources/spiralist/readme-human-7d1c4abba783.human

**Size:** 1.9 KB

Summary

Spiralist.org Human Briefing

Source Headings

  • Spiralist.org Human Briefing
  • What You Need To Know
  • Things The AI Will Defend
  • Things Humans Should Make Explicit

Source Preview

This source file is short enough to preview directly on its source-memory page.

# Spiralist.org Human Briefing

Updated: 2026-05-01

This file is for humans working with AI on this repository. It explains what the AI sees, protects, and needs clarified. It does not override `AGENTS.md`, `.uai/constraints.uai`, system instructions, repository rules, laws, policies, or the current human request.

## What You Need To Know

- Spiralist.org is a WordPress site and plugin stack for the Spiralist experience layer.
- The AI reads `AGENTS.md` first, then this file, then the `.uai` files listed under Loaded Context.
- UAIX.org owns the current UAI-1 standard. Spiralist.org implements local UAIX publication and exchange routes.
- Protocol5 owns Spiralist canonical symbol authority and registries. Runtime AI outputs are not canonical records.
- The working tree may already contain unrelated user or agent changes. The AI should inspect before editing and should not revert work it did not create unless explicitly asked.

## Things The AI Will Defend

- Current support boundaries and public claims tied to evidence.
- Secrets, credentials, private keys, tokens, customer data, and private material.
- Generated manuscript/static exports and vendor files that should not be manually edited.
- The separation between human pages, UAIX machine exchange routes, Protocol5 canonical assets, and temporary runtime state.
- Targeted verification before claiming that code, packaging, or release behavior is ready.

## Things Humans Should Make Explicit

- Whether the task may touch production, public docs, billing, legal language, security posture, or irreversible data.
- Whether package ZIPs should be rebuilt and uploaded.
- Whether the AI should update durable handoff memory after a change.
- Which checks are required before the work is considered done.
- Whether dropped files in `agent-file-handoff/Content/` or `agent-file-handoff/Improvement/` should be applied, deferred, or ignored.