ZaStoGram_desktop/.grok/commands/continue.md

3.1 KiB

name description
continue Continue a specified batch from the shared ai-tdesktop queue. Use when the user invokes /continue or $continue in Grok Build with a batch specification, or asks to resume the active task and run a specified batch.

Continue AI Work

Read .grok/ai-workflow-adapter.md and .agents/skills/continue/SKILL.md completely. Follow the shared skill with the Grok adapter's delegation, depth, text-handling, UI-driver, and compaction substitutions. The arguments below are the required batch specification. Without one, stop after the read-only queue call, report what the shared skill lists, and ask the user for a specification. Otherwise choose exactly one shared-skill mode and record its frozen task ids: any active task first, then exactly the tasks the specification selects, or the tasks one inbox transaction routes when it asks for the inbox. "All pending tasks" freezes the pending tasks on canonical ai-tdesktop master at startup. Never add unrelated tasks observed later in the run. Append and implement only new follow-up tasks routed from results produced by this invocation, including their transitive discovered follow-ups. Preserve the shared skill's source-project inheritance rule; detaching a follow-up requires its affirmative independence test. Continue until that frozen-and-derived batch reaches the scheduler's normal stop condition or a global hard stop. Do not stop on your own because a compact is approaching.

Apply the shared split-required result and routing phase. A performer publishes that state; this parent launches one fresh blocking split worker that reads the complete shared split reference, creates and publishes the replacements, and retires the source task. Replace the source id in the frozen batch with those replacements. When retained implementation exists, start the checkout-owned carrier first so the helper transfers its sealed source state; do not reset or checkpoint that work.

Apply the shared skill's pending-task consolidation phase too. At each eligible clean AI-slot boundary, recover an older pending_consolidations marker or consolidate newly routed tasks in one fresh blocking spawn_subagent. Give it the effective frozen batch, keep its queue scan and merge reasoning outside this scheduler context, and require it to read the complete shared consolidation reference. Never run consolidation inside the performer or discovery-routing worker, and defer it while the active task owns dirty local phase state.

Every inbox worker, performer, split-routing worker, discovered-task routing worker, and pending-task consolidation worker must be told in its initial prompt to read .grok/ai-workflow-adapter.md completely before the applicable shared skill or reference. Use spawn_subagent with background: false for those workers. A continue-spawned performer is at depth 1 and must run every phase leaf as a same-session checklist. Do not start Grok subprocesses through Bash.

The arguments are the batch specification. They always restrict the batch to the tasks they select; ordering words only order those tasks:

$ARGUMENTS