qingye-lab

qingye-lab/rootloom

Instructions file CodexOpenCode

Instructions for qingye-lab/rootloom, a project described as: Inspectable engineering workflows for OpenAI Codex.

qingye-lab/rootloom

Skill Claude CodeCodex

Initialize, retrieve, and explicitly update the separate Rootloom Memory plugin's repository-owned architecture, risk, decision, and failure lessons. Use only when explicitly requested. Memory is experimental, advisory, and outside Rootloom Core.

qingye-lab/rootloom

Hook

Runs when a session starts on startup, resume and clear, executing run_component_hook.py via python3. From qingye-lab/rootloom.

qingye-lab/rootloom

Skill Claude CodeCodex

Review code, diffs, pull requests, migrations, or architecture without modifying files. Lead with severity-ranked evidence-backed findings, challenge root-cause claims, and disclose cleared and unreviewed scope.

qingye-lab/rootloom

Skill Claude CodeCodex

The single Rootloom entry for code changes. Route Direct, Scoped, Governed, Evidence, and external-action work; repair owning invariants, preserve unrelated work, and report only verification that ran.

qingye-lab/rootloom

Skill Claude CodeCodex

Seed, refresh, refine, or validate concise evidence-backed AGENTS.md guidance. Deterministic scripts own the managed block; model judgment may add only durable repository-specific invariants outside it.

qingye-lab/rootloom

Skill Claude CodeCodex

Plan, install, inspect, update, or roll back Rootloom Personal Core in a user's Codex home. Supports Skills-only, guidance, and the recommended personal preset. Use when the user explicitly asks for a Rootloom setup plan, installation, configuration, bootstrap, repair, audit, status, update, reduction, rollback, or…