davidorex

Complete reference for the factory CLI — all commands, arguments, options, and usage. Use when an agent needs to invoke factory commands, check correct syntax, or understand available options.

When and how to write a human-action-needed entry to memory/{agent}/needs.md. Agents write these entries when they hit blockers that only a human can resolve.

When you encounter a failure, correction, or new pattern, write a learning and optionally propose a skill.

How the factory workspace is organized and what each directory means.

What to examine during a reflection pass and how to write observations to memory/{agent}/needs.md.

When and how to write scenario holdouts for factory verification.

How to integrate scenario evaluation into verification reports.

How to review proposed skills, curate shared memory, and detect patterns.

Build coordination wrapper for VCV Rack modules using Makefile

Load module context from handoff files to resume work

Multi-agent parallel investigation for complex VCV Rack problems

Validate panel ↔ creative brief consistency, catch design drift

Adaptive brainstorming for VCV Rack module concepts and improvements

Version management, bug fixes, feature additions for VCV Rack modules

Manage complete module lifecycle - install, uninstall, reset, destroy

Interactive research and planning (Stages 0-1) for VCV Rack module development

Schema-driven project state management with typed JSON blocks, schema validation, substrate config, lens views, closure-table relations, and cross-block referential integrity. Use when managing substrate blocks, scaffolding project structure, installing block kinds from the packaged samples catalog, validating project state, rendering lens views, or adding work items.

Orchestrates multi-step agent workflows defined in YAML with DAG-based execution, typed data flow, checkpoint/resume, and output validation. Use when running workflows, authoring workflow specs, debugging step failures, or inspecting agent configurations.

Sibling Pi extension that registers in-pi agent-as-tool dispatch, capability composition, real-check execution, attested commits, and the bounded north-star work-order loop. Use when authoring agent specs, granting tool capabilities, running deterministic checks, committing with writer attestation, loading config-declared composite operations, or driving end-to-end work-orders through their bounded retry loop.

Meta-package re-exporting pi-context (schema-driven project state), pi-workflows (workflow orchestration), and pi-behavior-monitors (autonomous behavior monitoring). Install once to get all three extensions.

Audit the active pi-context substrate for currency — stored-vs-derived status divergence, fired stale-conditions, lagging feature/gap buckets, stale filing text — and enact user-granted corrections. Use when asked to confirm substrate currency or accuracy, run a currency audit, check for stale statuses, or reconcile substrate state with shipped reality.

Cut a release of the pi-project-workflows monorepo — lockstep version bump, CHANGELOG roll, tag, operator promote, credentialed verification, and the publish/push handoff. Use when asked to release, cut a version, bump and tag the monorepo, or prepare a publish.

Build, run, and drive pi-project-workflows. Use when asked to run the pi-context CLI, start or smoke-test the monorepo, exercise the pi extensions via tool dispatch, verify a build end-to-end, or check that the substrate tooling works on this machine.

Run, launch, build, smoke-test, or verify the prompt-workshop — the 14-spec LLM plan-generation pipeline (run_workflow.mjs / render_from_substrate / check_draft / verify-render-parity) that drives the school-improvement-plan prompt corpus against the dev DB. Use to run the workshop sequence, render a spec, smoke-test the pipeline, or check render-parity.

Replaces built-in compaction with YAML-driven structured extraction and budget-aware reassembly. Use when configuring compaction specs, switching work modes, understanding extraction strategies, authoring custom extracts, or debugging compaction budget and artifact growth.

Behavior monitors that watch agent activity and steer corrections when issues are detected. Monitors are JSON files (.monitor.json) in .pi/monitors/ with classify, patterns, actions, and scope blocks. Patterns and instructions are JSON arrays. Use when creating, editing, debugging, or understanding behavior monitors.