refactor(pressure-test): main context is the main brain; subagents are scoped instruments - #31
Merged
Merged
Conversation
Humans describe what they saw on the screen, not what happened; follow the evidence to the failing layer before fixing where it was reported. Added to CLAUDE.md, fanned out to all rule mirrors, mirrored in README, and condensed into the always-injected hook text (with the hook comment updated to state its admission bar). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
pressure-test now fans grounding out to parallel subagents — one per pillar and per load-bearing claim, each gathering its own evidence in a fresh context immune to session anchoring — then synthesizes one recommendation. No token-thrift: invoking the command is the signal the stakes warrant the fleet. New §1 rule "Map the usage surface": a feature is more than the flow in the prompt — enumerate entry points and usage variations, build what was asked, and name the usages left out.
…e scoped instruments Replaces the per-pillar fan-out: the main context runs the test and owns the ruling, with most of the thinking and token spend staying there. Subagents are spawned only for small scoped checks that benefit from being outside the session — challenging a belief the conversation already holds, or online research / docs verification — never the test wholesale: an agent that only orchestrates stops being the main brain.
…-from-a # Conflicts: # README.md # commands/pressure-test.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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Replaces the per-pillar subagent fan-out: the main context runs the test and owns the ruling, with most of the thinking and token spend staying there. Subagents are spawned only for small scoped checks that benefit from being outside the session — challenging a belief the conversation already holds, or online research / docs verification — never the test wholesale: an agent that only orchestrates stops being the main brain.