Description
The Schema Consistency Checker consumed 8.1M tokens in a single run across 138 turns (Apr 20–27 weekly window) — the highest per-run token cost in the entire repository. Its cache efficiency is only ~14.9%, meaning most context is being re-read rather than cached. This represents a compounding cost as the workflow runs.
Evidence: Weekly Workflow Analysis #28687, Agentic Observability Report #28682 — both flag this as the primary cost optimization target.
Recommended approach:
- Add a deterministic pre-step that fetches/diffs schema files and writes results to
/tmp/gh-aw/agent/schema-diff.json before the agent starts — eliminates bulk data-gathering turns (~40–60 turns)
- Split the workflow into smaller batch jobs (e.g., one per schema area) rather than one monolithic run
- Add
max-turns: 60 cap to prevent runaway (current 138 turns = no guard)
- Increase cache hit rate by structuring prompts to reuse static context
Expected Impact
Target: reduce from 8.1M → ≤ 3M tokens/run. With weekly cadence: ~5M tokens/week reduction.
Suggested Agent
Agentic Optimization Kit
Estimated Effort
Medium (1–4 hours)
Data Source
DeepReport Intelligence Briefing — April 27, 2026 (run §25003521428); Weekly Workflow Analysis #28687; Observability Report #28682
Generated by DeepReport - Intelligence Gathering Agent · ● 473.9K · ◷
Description
The Schema Consistency Checker consumed 8.1M tokens in a single run across 138 turns (Apr 20–27 weekly window) — the highest per-run token cost in the entire repository. Its cache efficiency is only ~14.9%, meaning most context is being re-read rather than cached. This represents a compounding cost as the workflow runs.
Evidence: Weekly Workflow Analysis #28687, Agentic Observability Report #28682 — both flag this as the primary cost optimization target.
Recommended approach:
/tmp/gh-aw/agent/schema-diff.jsonbefore the agent starts — eliminates bulk data-gathering turns (~40–60 turns)max-turns: 60cap to prevent runaway (current 138 turns = no guard)Expected Impact
Target: reduce from 8.1M → ≤ 3M tokens/run. With weekly cadence: ~5M tokens/week reduction.
Suggested Agent
Agentic Optimization Kit
Estimated Effort
Medium (1–4 hours)
Data Source
DeepReport Intelligence Briefing — April 27, 2026 (run §25003521428); Weekly Workflow Analysis #28687; Observability Report #28682