deep-execution

# Agent-Enhanced Council Execution Use parallel Claude subagents for deeper analysis. Each subagent queries its provider, evaluates response quality, can ask follow-up questions, and returns structured insights. ## Step 1: Determine Provider Details For each selected provider, gather: - Provider name and script path: `${CLAUDE_PLUGIN_ROOT}/scripts/providers/{name}.sh` - Model name: run `bash ${CLAUDE_PLUGIN_ROOT}/scripts/query-council.sh --list-available` or read the provider script defaults ## Step 2: Spawn Provider Agents in Parallel Launch ALL provider agents in a **single message** (multiple Agent tool calls) for parallel execution. Use `run_in_background: true` and `subagent_type: "general-purpose"` for each. **Agent prompt template**: See [agent-prompt-template.md](agent-prompt-template.md) for the full template. Read it and fill in `{PROVIDER}`, `{SCRIPT_PATH}`, and `{QUESTION}` for each agent. **CRITICAL**: If a role was assigned to a provider (via --roles), build the role-injected question with the same helper the standard flow uses — source `scripts/lib/prompts.sh` and `scripts/lib/roles.sh`, then `build_prompt_with_role "<question>" "<role>"` — and pass its output as the agent's `{QUESTION}`. The role format itself is defined in `${CLAUDE_PLUGIN_ROOT}/prompts/role-injection.md`. **CRITICAL**: If file context was gathered (via --file or auto-context), include it in the question passed to each agent. ## Step 3: Collect and Validate Results As each backgroun...