[caveman] Optimize instruction verbosity — token-optimization.md (2026-05-26)#35057
Merged
pelikhan merged 1 commit intoMay 26, 2026
Merged
Conversation
Remove prose duplicating adjacent tables/headings: - Intro restating the heading - Two "Or via MCP tool" subsections folded to one-liners - Mode prose duplicating the summary table - "What to minimize" paraphrase of caveman principles - Wordy OTLP and AgenticOps descriptions Net: -36 lines (408 → 371), no schema/example/constraint signal removed. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
github-actions
Bot
added
automation
documentation
pelikhan
approved these changes
May 26, 2026
pelikhan
deleted the
caveman/token-optimization-2026-05-26-a13395e36434f1e4
branch
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Trim token-optimization.md redundancy
Summary
Editorial pass on
.github/aw/token-optimization.mdto reduce verbosity without removing any semantic content. The guide covers the same techniques; it is simply more concise.What changed
.github/aw/token-optimization.mdDetail
Removals / condensations applied across the file:
audittool calls (single-run and multi-run) collapsed to inline code:Equivalent via MCP: \audit` tool with `run_id: (run-id)``gh-proxyparagraph — condensed from 3 lines to 1.schedule:yaml block — block + surrounding prose collapsed into a single sentence.Why
The previous prose repeated context the reader already has, added navigation overhead, and made the guide longer to scan during high-token workflows — the exact situation the guide is meant to address. No technique, recommendation, or link was dropped.
Testing
Documentation-only change; no code or schema affected.
Commits
f6e50a9fc