Skip to content

[caveman] Optimize instruction verbosity — token-optimization.md (2026-05-15)#32478

Merged
pelikhan merged 1 commit into
mainfrom
caveman/token-optimization-trim-20260515-9abd8a5a48c0ebbd
May 15, 2026
Merged

[caveman] Optimize instruction verbosity — token-optimization.md (2026-05-15)#32478
pelikhan merged 1 commit into
mainfrom
caveman/token-optimization-trim-20260515-9abd8a5a48c0ebbd

Conversation

@github-actions
Copy link
Copy Markdown
Contributor

Caveman Optimization Run — 2026-05-15

Applies the caveman optimization principle to instruction files:

"Why use many token when few do trick."

Files Optimized

File Before After Removed
.github/aw/token-optimization.md 452 lines / 16,925 chars 407 lines / 15,179 chars Motivational bold subtitles, redundant "Why this saves tokens" bullet lists, and intro prose that restated adjacent code blocks (10.3% chars / 10.0% lines)

What 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 a gh aw audit command).

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).

Generated by ⚡ Daily Caveman Optimizer · ● 21.3M ·

  • expires on May 18, 2026, 9:10 PM UTC

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>
@github-actions github-actions Bot added automation documentation Improvements or additions to documentation prompt-quality labels May 15, 2026
@pelikhan pelikhan merged commit ea0ba92 into main May 15, 2026
@pelikhan pelikhan deleted the caveman/token-optimization-trim-20260515-9abd8a5a48c0ebbd branch May 15, 2026 21:35
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

automation documentation Improvements or additions to documentation prompt-quality

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant