From glean-pack
Optimizes Glean costs by filtering irrelevant content, pruning stale documents, using incremental indexing, and consolidating datasources.
How this skill is triggered — by the user, by Claude, or both
Slash command
/glean-pack:glean-cost-tuningThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Glean pricing scales with indexed content volume and user count. Reduce costs by indexing only relevant content, pruning stale data, and using incremental indexing.
Glean pricing scales with indexed content volume and user count. Reduce costs by indexing only relevant content, pruning stale data, and using incremental indexing.
| Strategy | Savings | Implementation |
|---|---|---|
| Filter irrelevant content | 20-40% | Skip drafts, templates, archived pages |
| Prune stale documents | 10-20% | Delete docs not updated in 12+ months |
| Use incremental indexing | Compute savings | Index only changed docs, not full corpus |
| Consolidate datasources | Admin savings | Fewer connectors to maintain |
| Set content size limits | Storage savings | Truncate body to ~50KB per doc |
function shouldIndex(doc: SourceDocument): boolean {
if (doc.status === 'draft' || doc.status === 'archived') return false;
if (doc.updatedAt < oneYearAgo) return false;
if (doc.title.startsWith('[Template]')) return false;
if (doc.content.length < 50) return false; // Skip near-empty pages
return true;
}
const filtered = allDocs.filter(shouldIndex);
// Typically reduces corpus by 30-50%
npx claudepluginhub ia23a-lachnita/claude-code-plugins-plus-fix-skills --plugin glean-pack2plugins reuse this skill
First indexed Jul 17, 2026
Optimize Glean costs by managing indexed content volume, datasource efficiency, and connector resource usage. Trigger: "glean costs", "glean optimization", "reduce glean indexing".
Guides collaborative design exploration before implementation: explores context, asks clarifying questions, proposes approaches, and writes a design doc for user approval.
Creates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.