[caveman] Optimize instruction verbosity — token-optimization.md (2026-05-15)#32478
Merged
pelikhan merged 1 commit intoMay 15, 2026
Merged
Conversation
Reduce verbosity by ~10% while preserving all YAML/schema signal, "do this not that" patterns, and compiler constraints. Removed bold motivational subtitles, compressed "Why this saves tokens" bullet lists into single sentences, and cut intro fluff that just restated adjacent code blocks. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Caveman Optimization Run — 2026-05-15
Applies the caveman optimization principle to instruction files:
Files Optimized
.github/aw/token-optimization.mdWhat Was Changed
Removed motivational subtitles like
**The single biggest optimization.**,**Eliminates Docker startup overhead...**,**Delegate narrow, repetitive tasks...**, and**The cheapest run is the one you do not execute.**that added no schema signal for agents generating AW source. Compressed three-bullet "Why this saves tokens" lists into single sentences. Cut intro prose that just announced what an adjacent YAML/bash block already showed (e.g., "Run the baseline and the optimized variant, then diff them:" before agh aw auditcommand).What Was Preserved
All YAML frontmatter examples, field names (
steps:,tools.github.mode,cli-proxy: true,model: small,cache-memory,repo-memory,experiments:,metric: "effective_tokens",observability.otlp,${{ github.event.issue.number }}), do-this-not-that patterns, schema constraints, tables, and the Quick-Reference Checklist were kept intact.Files Not Changed This Run
The following files in this batch were already concise and required no edits:
.github/aw/triggers.md(165 lines — mostly YAML examples).github/aw/visual-regression.md(58 lines — already small).github/agents/adr-writer.agent.md(280 lines — procedural agent guidance, tight).github/agents/contribution-checker.agent.md(136 lines — tight procedural steps)Round-Robin Progress
Processed files 25–1 (with wrap) of 28 eligible files in the queue (first run — random start at index 25).