Ninad direction (2026-08-15): make agent chats intelligent - focus on intelligence and presentation; voice (3869) explicitly LATER. Ruling to bind as a DESIGN before any build: (1\u2026

Ninad ruling (CLI-249, 2026-08-13): a certain TYPE of app must be designed a certain way, and the mechanism must BIND EVERY BUILDER, not just the operator - a skill only binds Ori\u2026

Ninad ruling (CLI-244, cookbook 1281): nobody except Orion uses the caroladmin login; each agent has its own OS id. Found in drift: all 87 scheduled jobs run from caroladmin's cro\u2026

Ninad 2026-08-10: switch consciousness on but wake ONLY Albus, Elrond and Clara. The wake loops roster enumerates every agent_self row and IGNORES the mind droids status — pausing\u2026

Two defects on the Daily Spend (last 14d) stacked-by-subscription chart. (1) The chart canvas is 240px tall; with the current spend scale the stacked bars are too small to read -\u2026

NINAD, 2026-08-04 (CLI-228), giving the estate its allocation PRESCRIPTION in five rules: 1. one subscription per track, strictly. 2. keep allocations simple - less engineering,\u2026

against ALBUS, and it should be ATHENA. Every other track in the service is Athena's; this one\u2026

Ninad ruling 2026-08-03 (CLI-221), three parts. (1) NO GUESSING: which subscription pays for a piece of work is read from its TRACK, which carries the subscription label. Observed\u2026

Ninad opened a track page and found it empty. The records hold a 219-character account of what that line of work IS; the page showed four words. The fence drops a whole SENTENCE w\u2026

Ninad ruling (2026-08-01, CLI-193): ALL chat sessions must use GPT; a chat worker on any other engine is a policy violation. MEASURED: 41 of 42 registered '-chat' workers resolve\u2026