Review a declared code change or code scope with evidence-backed findings and five independent quality scores. Use for pull requests, diffs, commits, patches, file sets, modules, bug fixes, refactors, and implementation-review requests.
Diagnose and recover a CCB agent whose provider context is corrupted, stale, overloaded, or semantically off-track when the user wants more than a plain clear: clear the agent only after safety checks, reconstruct the active task context from CCB…
Diagnose and recover CCB communication and reply delivery stalls. Use when a user reports a missing CCB_REPLY, stuck ask, agent stuck busy/delivering, queued work behind an active job, cancelled/incomplete reply, empty artifact, chain not continuing, rejected…
Private built-in CCB configuration skill for agentroles.ccb_self. Design, edit, validate, and prepare reloads for .ccb/ccb.config, role bindings, providers, windows, workspaces, tool windows, sidebar, and provider startup inputs. Use only inside ccb_self;…
Answer CCB architecture, source-location, command, config, communication, release, test-evidence, manual, and "where is this implemented" questions with source-backed evidence. Use when a user asks how CCB works, how to use a CCB feature, whether a CCB…
Diagnose and safely maintain the CCB Mobile host service, LAN/tailnet/Cloudflare Tunnel/Relay routes, pairing and devices, Relay invitation or host activation, multi-project terminals, and capability-negotiated Provider controls. Use when Mobile cannot…
Internal CCB lineage repair for retry/resubmit/ack decisions when a job/message/attempt/reply/inbound-event/artifact id is already in hand. Prefer ccb-comm-reply-recover for user-visible "reply did not arrive", stuck busy/delivering, queued-behind-active,…
Diagnose CCB runtime, mounted daemon graph, tmux namespace and panes, provider context, queue/inbox/trace, replies/artifacts, config drift, and storage boundaries. Use when the user asks what is broken, which agent is stuck, whether CCB is mounted, why a…