The orchestrator no longer monitors a running planner; it confirms startup
and exits. The planner is the only full CLI agent and delegates implementer,
reviewer, fixer, and merger roles to native Pi subagents instead of Herdr- or
CLI-launched agents. Update dispatcher, run-loop, state, and agent interface
copy to match.
Rewrote the skill so the invoking session only discovers an existing
run or launches a fresh planner, then monitors via Herdr read-only
commands. Workers keep state in .orchestrate/<slug>/ with run.json and
events.jsonl; the tracker holds all handoffs and decisions. Re-invoking
the same command recovers monitoring after an orchestrator outage, and
an in-progress label plus atomic launch claims prevent duplicate
planners.
Add an explicitly invoked Pi orchestration skill that drives a plan from the
current conversation or an @file through a published spec, linked dependency-aware
tickets, and one-at-a-time isolated implementation to a merged PR, using Herdr
and Pi agents with no Bun CLI or orchestration runtime.
- orchestrate-herdr (SKILL.md + dispatcher/run-loop/state references): worker-node
selection and Herdr discovery/validation, plan-and-publish, one-at-a-time task
loop (claim, isolate, implement, verify, four-axis review, scoped fix rounds max
three, transient retries max two, reconcile uncertain side effects, escalate),
PR/merge/close gates, authoritative worker-node state, cross-system recovery,
and owned-only cleanup that preserves dirty worktrees and retained state.
- dual-review: self-contained correctness/security + maintainability review axis
(four-axis review with code-review).
- to-spec and to-tickets: drop disable-model-invocation so the orchestration
workflow can invoke them.
- READMEs: list the two new skills.
gitadmin