From daplug
Orchestrates multi-prompt execution in sequential/parallel phases with auto-dependency inference, validation, model-tiered planning, and tmux-monitored runs via /run-at-prompt.
npx claudepluginhub cruzanstx/daplug --plugin daplugThis skill is limited to using the following tools:
Run existing prompts using agent-team orchestration.
Mandates invoking relevant skills via tools before any response in coding sessions. Covers access, priorities, and adaptations for Claude Code, Copilot CLI, Gemini CLI.
Share bugs, ideas, or general feedback.
Run existing prompts using agent-team orchestration.
Use this skill when the user invokes /run-at-prompt.
-> separates sequential phases., separates prompts inside the same phase (parallel).Examples:
220,221 -> 222,223 -> 224220 -> 221,222,223 -> 224220Reference parse output:
[
{"phase": 1, "prompts": [220, 221], "strategy": "parallel"},
{"phase": 2, "prompts": [222, 223], "strategy": "parallel"},
{"phase": 3, "prompts": [224], "strategy": "parallel"}
]
PLUGIN_ROOT=$(jq -r '.plugins."daplug@cruzanstx"[0].installPath' ~/.claude/plugins/installed_plugins.json)
AT_RUNNER="$PLUGIN_ROOT/skills/at-prompt-runner/scripts/at_runner.py"
PROMPT_MANAGER="$PLUGIN_ROOT/skills/prompt-manager/scripts/manager.py"
python3 "$AT_RUNNER" parse "220,221 -> 222,223 -> 224"
python3 "$AT_RUNNER" parse "220 221 222" --auto-deps
python3 "$AT_RUNNER" validate "220,221 -> 222"
python3 "$AT_RUNNER" plan "220,221 -> 222" --model codex --worktree --json
--auto-deps, infer group order.Run:
python3 "$AT_RUNNER" validate "$GROUPS" [--auto-deps]
If validation fails, stop and report missing prompt IDs.
--auto-deps)When --auto-deps is set:
at-planner (model: sonnet) to review inferred dependencies./run-prompt command until confirmation is explicit.Planner output should include:
Run:
python3 "$AT_RUNNER" plan "$GROUPS" --model "$MODEL" [--worktree] [--loop] [--validate] [--json]
If --dry-run is set:
/run-prompt commands only.For each phase:
at-monitor task per prompt (model: haiku, run_in_background: true)./run-prompt ... through tmux and produces an Execution Report.TaskOutput() and triage in orchestrator.Decision rules:
OK -> continue to next phase.ESCALATE -> inspect evidence and resolve before proceeding.at-fixer (model: opus).at-merger (model: sonnet).--validate)Spawn at-validator (model: sonnet) after all phases complete.
Validator decides:
at-fixer with explicit log line referencesat-monitor: haikuat-planner: sonnetat-validator: sonnetat-merger: sonnetat-fixer: opus (only on escalation)Do not assign sonnet/opus to monitor role.
Monitor agents are mechanical watchers. They do not debug or choose strategy.
Each report must include:
Report format requirement:
ESCALATE|OK: {description} (see log lines N-N if applicable)
--model <model>: default model for delegated /run-prompt commands--auto-deps: infer phase ordering from prompt contents--validate: append final validator phase--worktree: run each prompt in isolated worktree--loop: enable verification loop per prompt--dry-run: show plan onlyUse explicit role-based Task calls:
Task(subagent_type: "at-monitor", model: "haiku", run_in_background: true, prompt: "...phase command...")
Task(subagent_type: "at-validator", model: "sonnet", prompt: "...review reports...")
Task(subagent_type: "at-merger", model: "sonnet", prompt: "...resolve overlap...")
Task(subagent_type: "at-fixer", model: "opus", prompt: "...complex failure details...")
Always pass log path + line ranges when escalating.