casual
01Command
Skip adhoc methodical-mode for the next single turn (auto-reverts after one prompt).
Claude Code plugin marketplace — forge, foundry, and verification tooling
Command
Skip adhoc methodical-mode for the next single turn (auto-reverts after one prompt).
Command
Disable the adhoc Stop hook citation verifier.
Command
Enable the adhoc Stop hook citation verifier (default mode).
Command
Show the adhoc plugin commands and how the methodical-mode hook works.
Command
Disable adhoc methodical-mode injection for the rest of this session.
Command
Re-enable adhoc methodical-mode injection.
Command
Show the current adhoc methodical-mode and citation-verifier state.
Command
Disable the adhoc Stop hook strict gates (grounding audit + critic-agent gate).
Command
Enable the adhoc Stop hook strict gates (grounding audit + critic-agent gate).
Command
One-shot bypass of adhoc strict gates (grounding + critic) for the next single turn.
Command
Disable the adhoc Stop hook uncertainty-tell scanner.
Command
Enable the adhoc Stop hook uncertainty-tell scanner (default mode).
Command
Cancel an active crew run.
Command
Throw an AI dev at a problem and have it own the outcome — investigate, plan, execute, verify.
Command
Set a completion condition and let crew work unattended until critic and fresh-eyes both pass.
Command
Command "list" from alphabravo-oss/guild, covering crew list, behavior and rules.
Command
Resume an interrupted crew run from .crew/runs/ /.
Command
Build a structured spec with the mini-foundry engine: decompose into disjoint units, approve the split once, then CAST → INSPECT → GRIND → ASSAY. Refuses a dirty tree.
Command
Print a copy-pasteable anti-AI-slop design ruleset (tailored to the detected stack) for you to adjust and drop into CLAUDE.md or memory.
Command
Scan a running UI for AI-slop tells: Playwright captures screenshots + CSS facts per route, a Workflow engine judges them with 9 blind self-rating lenses, and renders a ranked change list. --apply commits HIGH-confidence low-risk fixes.
Command
Run the Playwright suite, read trace.zip per failure, triage by root cause.
Command
Discover every route in the app and generate one smoke spec per route.
Command
Install Playwright + register Playwright MCP + scaffold tests/ in the current project.
Command
Generate routes × roles coverage suite with reused storageState (login once per role).