Extend investigation-depth rule to subagent delegation - #316
Merged
Conversation
The 調査の深さはタスクに比例 bullet only governed the assistant own investigation; retrospective #274 found an over-scoped Explore delegation (5 items, no cutoff conditions) for a lookup answerable from already-loaded context in about 3 commands. Rewrite the bullet in place so delegation prompts carry the same depth cap as explicit cutoff conditions, and items answerable from loaded context are checked directly instead of delegated. Finding 1 of #274 (unverified Explore-defaults-to-Haiku claim in subagent-model.md) was already resolved by #302. Closes #274 Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_0156RhYyZmXJn2YdA1rHZztf
ikuwow
marked this pull request as ready for review
July 27, 2026 03:30
# Conflicts: # AIRULES.md
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Changes
Background
Retrospective #274 recorded an Explore delegation with 5 items and no cutoff conditions for a lookup the parent later answered in about 3 commands from loaded context, costing the user 3 interventions over 8 minutes. The existing depth rule only governed the assistant's own investigation, so it is rewritten in place rather than adding a parallel rule, per the rule-editing conventions
Finding 1 of #274 (unverified "Explore defaults to Haiku" claim in subagent-model.md) was already resolved by #302, which dropped the parenthetical; only finding 2 remained
Issue: #274
Verification