consult

Automatic capability selection

Resolve select-capabilities.js from the checkout scripts/forgeflow, a host-supplied plugin root, or the installed ForgeFlow runtime for this host. Run node <helper-dir>/select-capabilities.js --guide and follow the shared selection procedure with phase consult and the current objective, criteria and affected scope. Reuse the same result across alias handoffs and pass it through existing context construction; do not reset reassessment limits. Missing runtime support is an explicit limitation, not a reason to invent selection results. Preserve current workflow read-only and isolation boundaries. Planned capabilities are not executable and selection grants no new authority.

At workflow entry, run node <helper-dir>/open-session-dashboard.js --root <project-root> --workflow consult when available. Resolve <helper-dir> from the checkout's scripts/forgeflow first, then ${CODEX_HOME:-$HOME/.codex}/forgeflow/scripts/forgeflow. The helper starts or reuses agent-chat and reports known workflow phases on each entry; it uses CODEX_THREAD_ID, CLAUDE_SESSION_ID, or FORGEFLOW_SESSION_ID to open the local dashboard once per session. If the host supplies a session id separately, pass --session <host-session-id>; never invent a new id per invocation. Headless runs and FORGEFLOW_DASHBOARD_AUTO_OPEN=off skip the launch. A missing helper or unavailable browser must not block the workflow. Report actual phase transitions, significant progress, waiting, and the final result with node <runtime-root>/services/agent-chat/client.js activity <state> "<short label>" (<runtime-root> is the checkout or installed forgeflow directory). Use complete only when work and required checks have finished; report failed for failures, and never invent progress to keep Ember moving.

Delegate to the forgeflow-consult workflow.

Use this skill when the user wants Forgeflow consultation before implementation.

Resolve helpers before running them: set FORGEFLOW_HELPER_DIR to scripts/forgeflow when that directory exists, otherwise to ${CODEX_HOME:-$HOME/.codex}/forgeflow/scripts/forgeflow. If neither exists, report a missing Codex runtime installation.

Before other work, run:

"$FORGEFLOW_HELPER_DIR/ensure-forgeflow-state.sh"

Workflow:

1. Read the canonical consultation skill and follow its complete workflow, including consultation routing. If the canonical skill is unavailable, report the missing instructions instead of inventing a separate route.
2. Use its smallest relevant specialist set, risk/uncertainty escalation, and Architect synthesis. This alias does not require all four consultants or skip independent validation and final review.

If both this alias and forgeflow-consult are available, treat them as equivalent.

Task evidence continuity

Use the shared task workflow for a bounded change with an accepted objective or brief. Resolve task.js from the same runtime helper directory used above. Run list --root <project-root> and reuse only the task explicitly selected by the user or matching the current objective and scope. Do not attach an unrelated task based only on recency. If this is a new accepted change, create a task using its objective and behavioral acceptance criteria; the task workflow describes the JSON contract.

Keep the same task id across consult, implement, review and ship. Use check for actual validation commands and saved evidence for observed manual/reviewer results. Record a checkpoint at each completed phase and before interruption, including the actual host/session identity when available. A saved plan, successful build, or reviewer verdict alone must not mark every criterion verified. Waivers require explicit user intent and a reason.

Before reporting completion or preparing a shipping handoff, read status --root <project-root> --task <id>. Stale/missing/failed criteria and pending actions remain visible. Reconcile interrupted actions from actual evidence, then use resume; never silently replay unknown work. Legacy work without task records stays supported but has no source-bound task completion claim. All remote authorization rules above still apply.