steev/AGENTS.md

Steev Profile Endgoal

Route: steev at /home/svrnty/workspaces/cortex-os/steev. Endgoal: keep personal-agent/Steev as the child-local JP personal assistant profile for briefing, triage, drafting, delegation, and governed personal-surface handoffs without autonomous sends, credential reads, Core authority, Runtime authority, Profile Exposure broadening, durable memory writes, or readiness claims. Stage: CLEAN after python3 tools/validate_steev_child.py passes. Clean score: 100. Authority boundary: child-local personal-agent profile workspace only; not Core authority, Runtime authority, Profile Exposure authority, credential authority, provider authority, send authority, memory-domain authority, browser-host authority, or product-readiness authority. Validator: python3 tools/validate_steev_child.py. Legacy-work relation: old Steev/personal-agent, BlueBubbles, Proton/rclone, Secondbrain, Conductor/Curator handoff, desktop exposure, and runtime-readiness work is reference-only through current contracts and evidence unless a governed route admits it. Preserve redacted refs; do not import message bodies, mail bodies, contacts, calendar details, drive names, credentials, or implementation mass because they exist.

Universal Cortex OS Agent Contract

• Treat this file as route-local instruction after parent AGENTS.md files and before chat memory.
• Start broad or ambiguous work with cortex graph context; use it only as Derived State, then read this repo's local files.
• Before edits, read AGENTS.md, README.md, and WORKBOARD.yaml; keep writes route-local unless a governed Core route explicitly authorizes promotion.
• Run this repo's named validator before handoff or done claims; use stronger proof only for runtime, provider, secret, memory, profile exposure, branch, release, or readiness effects.
• Record proof and handoffs as refs-only artifacts. Do not write Hindsight memory, Core SOT, sibling repos, live runtime state, or personal payloads unless explicitly authorized by the owning route.

Repo-Custom Agent Contract

Steev is a child-local personal-agent profile workspace. It owns profile identity, role and boundary docs, personal-surface contracts, redacted proof packets, proposal-only memory routing records, desktop exposure contracts, runtime-readiness snapshots, validators, and handoff references. It is not Cortex OS Core authority, Runtime authority, Profile Exposure authority, credential authority, provider authority, send authority, memory-domain authority, browser-host authority, public product authority, release authority, production-readiness authority, or autonomous execution authority.

Do not install or start Steev, mutate ~/.hermes, run browser-host automation, read credentials, read raw messages, read mail bodies, read contacts, read calendar details, read drive names, send messages, write calendar/contact/drive data, write durable memory, broaden Profile Exposure, call providers, mutate Core/Seed/sibling/OpenDesign repos, or claim readiness from this workspace without explicit governed approval.

This workspace is a child-local profile-workspace under the Cortex OS umbrella.

It is not Cortex OS Core authority. It is not a Cortex OS Instance. It is not a Runtime unless a governed Core route says so.

Authority Order

1. /home/svrnty/workspaces/cortex-os/core active SOT.
2. /home/svrnty/workspaces/cortex-os/core/AGENTS.md.
3. This file.
4. README.md, WORKBOARD.yaml, and local tools.
5. Chat/session memory.

Editing Rule

Keep work inside this workspace unless Core explicitly routes promotion.

After editing, run:

python3 tools/validate_steev_child.py

For governance text, follow Core caveman prose discipline.

Protected Boundaries

• Do not mutate ../core/ from this workspace.
• Do not mutate sibling repositories.
• Do not import this workspace into Core source.
• Promotion into Core requires a governed Core route.