with one click
with one click
Design, edit, or migrate CCB project teams by updating .ccb/ccb.config. Use when the user wants to add, rename, remove, or reorganize CCB agents; choose providers, worktree isolation, models, API shortcuts, single-window or multi-window layout; migrate an old ccb.config to the current windows topology; handle optional skill inheritance or injection requests for agents; or turn a natural-language team/workflow description into a valid CCB config. Only update shared or per-agent memory when the user explicitly asks for workflow memory design.
Clear CCB managed agent conversation context with `ccb clear`. Use when the user writes `$ccb-clear`, `$ccb_clear`, or asks to clear/reset one or more CCB agent contexts without restarting or deleting project state.
Maintain a structured planning document tree made of roadmap/status files, implementation status or handoff TODO files, topic notes, decision records, open questions, ideas/inspiration pools, and repository/file-structure hygiene plans. Use when Codex needs to create, reorganize, audit, or update a multi-file plan, design-doc folder, roadmap tree, active implementation-status file, repo cleanup/filesystem plan, ADR/decision log, ideas inbox, or linked planning knowledge base; reconcile Done/In Progress/Next state; resume work from TODO/handoff state; move resolved questions into decisions; promote ideas into formal plan artifacts; or keep plan documents and file-structure planning internally consistent without making this project-specific.
Send a request to a CCB agent with `ask`.
Send a request to a CCB agent with `ask`.
Maintain this CCB project's GitHub-facing release surface. Use when preparing, publishing, auditing, or fixing CCB releases; updating README.md, README_zh.md, CHANGELOG.md, VERSION, GitHub release notes/assets, repository description/topics, or GitHub Actions release/test status.
| name | ask |
| description | Send a request to a CCB agent with `ask`. |
| metadata | {"short-description":"Ask agent"} |
Use this only for /ask <target> <message...>.
TARGET = first token; MESSAGE = raw remainder sent as the task body.ask may append reply guidance unless the message already contains explicit output requirements.TARGET=all broadcasts.ask injects concise-reply guidance while still delivering the full reply body.--compact when the caller wants an actively distilled answer, such as review findings, status, risks, blockers, or next actions.--silence when success does not need a body; failures, blockers, or required next actions should still surface.--callback only from inside an active CCB task when this agent needs the target's result before finishing the original task. The current turn must end after submit; CCB will route the target result back as a new continuation task.ask from an active CCB task is rejected; choose --callback for needed results or --silence for independent no-result-needed work.ask injects reply guidance.ask get, pend, watch, and ping are diagnostics-only commands for explicit debugging requests, not normal ask workflow tools.Always send MESSAGE through the <<'EOF' ... EOF heredoc below. No other form is allowed.
command ask "$TARGET" <<'EOF'
$MESSAGE
EOF
command ask --compact "$TARGET" <<'EOF'
$MESSAGE
EOF
command ask --silence "$TARGET" <<'EOF'
$MESSAGE
EOF
command ask --callback "$TARGET" <<'EOF'
$MESSAGE
EOF
After the command returns, immediately end the turn. Do not wait for a reply, do not run ask get / pend / ping / watch, do not poll, do not add commentary. For --callback, report only that delegation was submitted; the final result belongs in the later continuation task.