Operational route

Cost and review control

Choose how much planning, model capacity, context, and independent challenge the task deserves, then record the decision.

Page evidence

Operational mapScore the lane. Resolve the host model. Freeze the choice.
Stable tier keys
  1. cheaproutine, low-risk work
  2. midmulti-file reasoning
  3. powerfulhigh ambiguity or risk
Per-run resolution
  1. lane scoretask signals
  2. host model idconfigured mapping
  3. resolved settingsfrozen evidence

Tier keys stay portable. Exact model ids belong to host configuration.

/guild:guild "Task" --rigor=balanced --review=cross

Route comparison

Same job. A visible operating record.

Without a route record

Cost and review strength drift across prompts, while operators cannot tell which posture produced the result.

With Guild Stack

Guild Stack resolves a portable tier and review mode from explicit settings and flags, then freezes them with the run.

Route stops

Request to verified result.

  1. 01

    Choose rigor

    Set the planning and verification posture for the risk of the task.

  2. 02

    Resolve the tier

    Use deterministic task signals and host-configured model mappings.

  3. 03

    Set review strength

    Choose local, cross-host, or off with the resulting independence recorded.

  4. 04

    Freeze and inspect

    Keep effective settings and review evidence beside the run.

Receipts

What the route leaves behind.

  1. 01
    Path resolved-settings.json
    Role

    Per-key effective configuration and source map.

  2. 02
    Path run.yaml
    Role

    Selected rigor, review posture, and lifecycle state.

  3. 03
    Path review/<gate>/
    Role

    Packet, result, trail, and independence label.

  4. 04
    Path handoffs/*.md
    Role

    Lane tier and escalation evidence.

Next

Open the Control route

The demo traces one bounded task through approvals, specialist lanes, review, verification, and the final run record.