Adds the attack-the-plan step and per-phase review to the development cycle, the fix-pass stop rule, Athanor resume between phases, and the alias-over-pin model rule. Drops the stale 4.6-for-implementation guidance and per-task review convention. Harness notes now point to the implementation skill's spawning reference.
13 lines
778 B
Markdown
13 lines
778 B
Markdown
# Harness notes (moved)
|
|
|
|
The harness mechanics that lived here (task notifications, background grandchildren, `ListAgents`, `TaskStop`, `TaskOutput`, leaf briefs) moved on 2026-10-05 to the implementation skill's reference, together with resume, fork and model-pin behaviour:
|
|
|
|
`plugins/spire/skills/implementation/references/spawning-claude-code.md`
|
|
|
|
The short version for Igor:
|
|
|
|
- A notification reports a turn ending, not a job finishing. Read the `<result>` text; check `ListAgents` before resuming.
|
|
- Background grandchildren notify you, the root. If a child is still writing an output path, do not resume its parent.
|
|
- Resuming via `SendMessage` is safe from you (the root), not from inside a subagent.
|
|
- Leaf briefs say "do this yourself; do not dispatch further agents."
|