docs(plan): implementation plan for subagent-orchestration refactor

Browse Source

Three-round adversarial review incorporated. Covers:
- Architecture: main orchestrator + thin Haiku runner subagent
- File structure: SKILL.md + new references/runner.md
- Retry invariant: 2 codex invocations per round max; runner owns
  full retry budget across all failure types; main treats every
  failure as terminal for the current round
- Session-id lifecycle with two-tier positive content-bind
- Two-channel result protocol (JSON file + RUNNER_RESULT_AT line)
- user_warning channel for §2.4.4 no-op refresh diagnostic
- SKILL_DIR 3-tier resolution (user-scoped / plugin-marketplace / dev)
- Placeholder-substitution contract before prompt-body write
- Step 5 "VERY NEXT MESSAGE" wording reconciled with user_warning
- Task 7 E2E verification with skill-install, plan-mode test, and
  residue-tax measurement

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

...

This commit is contained in:

ddadmin

2026-04-19 17:53:48 +03:00

co-authored by Claude Opus 4.7

parent f41a6cbe87

commit 08e1c2cda6

1 changed files with 1181 additions and 0 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

docs/superpowers/plans/2026-04-19-subagent-orchestration.md

+1181

File diff suppressed because it is too large Load Diff