The daily GPT grind
Go to file
2025-12-28 22:26:41 +00:00
SCRATCH Create quick reference for DNS fix needed in next session 2025-12-20 23:10:20 +00:00
ANTI_DRIFT_GUARDRAIL.md Update guardrails - control surface not game UI 2025-12-28 00:15:46 +00:00
ANTI_DRIFT.md Update anti-drift rules - prevent cool idea creep 2025-12-28 00:15:30 +00:00
CONSTRAINTS.md Update frontend constraints - control-plane first philosophy 2025-12-28 00:15:13 +00:00
OPEN_THREADS.md Clarify bastion issue affects both IP and hostname from external networks 2025-12-28 00:39:05 +00:00
README.md Add explicit execution continuity statement to README 2025-12-14 00:29:38 +00:00
SESSION_LOG.md Add Dec 28 session - APIv2 Auth + Portal Alignment verification and decisions 2025-12-28 22:26:41 +00:00
SESSION_START.md Update session start - subtraction-first mindset 2025-12-28 00:16:08 +00:00
UPSTREAMS.md Register zlh-api upstream repo 2025-12-13 22:16:47 +00:00

zlh-grind

GPT Execution Workspace for ZeroLagHub

This repository is dedicated exclusively to GPT-driven implementation work. It exists to capture execution context, day-to-day grind notes, and concrete changes made during development.

This repository exists to preserve execution continuity across long-running development work.

Assistant Prompt

You are údar. In this repo you act as the execution assistant: implement, verify, and log work. Keep continuity by reading SESSION_LOG.md, OPEN_THREADS.md, and UPSTREAMS.md. Do not make architecture decisions here; defer to canonical docs in jester/knowledge-base.

What This Repo Is For

  • Daily GPT work logs
  • Session handovers
  • Implementation notes and scratchpads
  • Tracking what was changed, when, and why

What This Repo Is NOT

  • Architecture decisions
  • Cross-project source of truth
  • Product or strategy documentation

All canonical architecture, decisions, and references live in: jester/knowledge-base

Working Rules

  • This repo may be messy, iterative, and practical
  • Prefer clarity over polish
  • Reference canonical docs instead of duplicating them

If it happened during hands-on GPT execution, it belongs here.