Herdr runtime

Before following the original instructions below, read the sibling pstack-herdr skill and its required mapping. Resolve relative references from this installed skill directory. Use a named sibling skill by reading ../<name>/SKILL.md, because explicit-only siblings are not in the harness skill list. The mapping translates original repository paths to bundled resources; no separate upstream checkout is needed. The Herdr mapping overrides upstream delegation tools, model defaults, setup files, and Cursor-specific capabilities. Delegate only through horch, using workers.toml. Keep workflow coordination in the controller. A bounded worker assignment remains bounded: do not start nested workers. User and project instructions take precedence. Check required capabilities before acting; keep unavailable steps unresolved. For setup-pstack, use the adapter's role setup instead of the original Cursor rule-writing procedure.

Swarm

Start

Open a todolist with one entry per phase before launching anything.

1. Frame
2. Fan out
3. Aggregate
4. Report

Phase A: Frame

1. State the done predicate and the artifact or report the swarm must return.
2. Choose the shape. Partition into slices, race N workers on identical briefs, or mix both. For a race or mixed shape, declare first pass, rank all, or best-of before spawning.
3. Pick the worker model from the swarm workers line in ~/.cursor/rules/pstack-models.mdc. If the rule or that line is missing, use grok-4.7-xhigh-fast. For auto or inherit-parent, omit model so the workers run on the parent model. If the Task tool rejects a slug, use the default and say so. If it rejects the default, use the closest valid slug of the same family from its error message. For a model race, name each arm's model up front. Pick each subagent's reasoning level and fast or standard speed for the job, per the Subagents section of the poteto-mode skill.
4. Give each worker its own writable output when it writes. When workers verify or measure commits, each brief names the exact SHAs. A measurement brief also names the method (sample count, what one sample is, order). The worker records both in its result.

Phase B: Fan out

Spawn all N workers in one message with subagent_type: generalPurpose, environment: "cloud", run_in_background: true, and the step 4 model, left unset for auto or inherit-parent. Use environment: "local" only when the worker needs access to something on the user's computer.

When a worker must start from a non-default pushed branch, pass cloud_base_branch.

Every brief stands alone. Include the goal, scope, exact slice or race arm, how to verify, and what to report. Reports use PASS, ISSUES, or BLOCKED with evidence. A worker that can prove a defect reports ISSUES and lists every issue it can prove, not only the first.

If a worker drops out, proceed with N-1 and note it.

Phase C: Aggregate

Read the terminal results. Drop a result that does not record the SHAs and method its brief names, and respawn that worker once. After a second miss, record a gap. A gap does not count as a pass. For coverage, every required slice needs a result. For a race, apply the selection rule declared up front. Use first pass, rank all, or best-of. Do not paste raw worker dumps.

Phase D: Report

Return one consolidated in-chat report with the table, issue one-liners, gaps or dropouts, and the race rule when used.