dungeon-buddy

Development formatting hooks (Go, Shell, Proto, OpenAPI), TDD agents, grill-with-docs, pi-implementer (a local model implements Tickets through pi + pi-vcc under Claude Code's supervision), and second-opinion (Muse Code reviews Diffs and Plans read-only; Claude verifies and rebuts), consensus-review (security, cleanup and bug reviewers, then a blind Verifier per Finding; only medium+ Findings the Verifier confirms reach you), plus mods: Crawler Points HUD, Dispatch Board, Podman Guard, Branch Guard, TDD Band, Floor Boss, Sponsor Mail (PR watch), Beast Watch (GPU box health + Beast Guard) and the System's voice (its Cues are heard by dungeon-buddy)

5 skills · 7 agents · 1 MCP server · hooks · LSP

Security default for organizations: seated outermost, it keeps the organization's classic hooks, prompt content, settings, tool policy and pinned environment out of reach of the plugins a person installs, and adds no policy of its own; one managed option, allowManagedModsOnly, limits mods to the organization's.

Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data

9 skills · 9 commands · 11 agents · 1 MCP server

Claude Code mod: watch Headroom snip tokens off every request, with an animated band, a /headroom log and a running total.

Onboard a Code-with-Claude Makers Cardputer with one /maker-setup command — clones the build-with-claude repo, flashes UIFlow firmware, and installs the Claude Buddy app bundle.

2 skills · 1 command

Optional mods companion for claude-seo (needs Claude Code 2.1.287+). A spend guard that holds paid SEO API calls against the claude-seo budget, and zero-token /seo-spend and /seo-doctor commands.

Optional local Claude Ads workbench for runs, evidence, inputs, comparison and report receipts. Enabled separately.