feat(rules): add subagents.md — when, how, and when not to delegate

Cross-cutting rule covering subagent hygiene:

- Decision table: parallel-safe (read-only investigation, independent
  test failures, multi-domain research) vs sequential-with-review
  (plan execution, coupled edits) vs never-parallel (concurrent writes)
  vs don't-subagent-at-all (target known, work fits in ~10 tool calls).
- Prompt contract: scope / pasted context / explicit 'do NOT' list /
  required output format. Missing any field yields shallow work.
- Context-pollution rule: subagents absorb noise the main thread
  shouldn't carry. When one fails, dispatch a fix-agent with the
  failure report — do not retry in the orchestrator.
- Review-gate cadence: after each sequential task, or every ~3 in
  parallel batches.
- Anti-patterns including parallel implementation on overlapping
  files, broad 'fix all the tests' prompts, timeout-tuning to mask
  flakes, and letting the agent decide scope.

Added one-line cross-references to subagents.md from debug/,
review-code/, and finish-branch/ SKILL.md — the skills that most
rely on delegation.

Clean-room synthesis from NeoLabHQ/context-engineering-kit's
subagent-driven-development pattern (MIT).

1 files changed, 2 insertions, 0 deletions

diff --git a/finish-branch/SKILL.md b/finish-branch/SKILL.md
index 5cb02ef..0903010 100644
--- a/finish-branch/SKILL.md
+++ b/finish-branch/SKILL.md
@@ -40,6 +40,8 @@ Commands vary by stack. Use what the project's Makefile, `package.json` scripts,
 
 **If verification passes:** continue to Phase 2.
 
+If any verification step fails and triggers sub-investigations, follow `subagents.md` — dispatch a fresh fix-agent per failure with pasted error context rather than retrying in the orchestrator.
+
 ## Phase 2 — Determine Base Branch
 
 The four outcomes need to know what the branch is being integrated into. Find the base: