graph
01Command
Inspect and drive the-loop's process graph — the PDLC as an executable graph of nodes with entry and exit hooks, rather than a set of labels somebody remembers to move.
52 tagged loop, measured the same way as everything else here.
Browse within: agentic-coding 35claude-plugin 35ai-assistant 12ai-loops 12loop-engineering 12OpenSpec 5ccg 5enginerring 5gsd 5gstack 5workflow 5
Command
Inspect and drive the-loop's process graph — the PDLC as an executable graph of nodes with entry and exit hooks, rather than a set of labels somebody remembers to move.
Command
The work-item ↔ harness-session registry, the five execution-control commands, and the reset that forgets a work item entirely.
Command
The sessions the-loop keeps for itself — declared in the CLI config, brought up by the-loop start, and addressed by name rather than by work item.
Command
Open a URL in the desktop browser panel for the current session. With no argument it opens the workspace's static entry point, falling back to this session's existing preview target when no entry point exists. A local file can be opened by its absolute file:// URL. Use maestro preview clear to empty the panel.
Command
Manage projects: register repos, inspect, configure per-project settings, and remove.
Command
Manage agent sessions: list, inspect, rename, kill, restore, clean up, and claim PRs.
Command
Run a CCG adversarial quality gate on the current stage's output — deterministic quality gates (security/quality/change/module) + multi-model adversarial review (codex+gemini); auto-optimizes and re-checks on findings, raising the quality of loop outputs.
Command
Trigger a Loop Engineering iteration loop — milestone archive → retro → lessons extraction → intent audit → gap analysis → generate next-round seed; reinforces the macro loop.
Command
Advance the Loop Engineering engineering loop — detects the current Phase and auto-routes to the next tool (gstack for looking, OpenSpec for writing, GSD for doing), with optional --auto chained self-invocation.