{
  "id": "page:docs-harness-features-backlog-gaps-prompt-engineering-gap-prompt-011",
  "_kind": "Page",
  "_file": "wiki/docs/harness-features-backlog/gaps/prompt-engineering/gap-prompt-011.md",
  "_cluster": "wiki",
  "attributes": {
    "nodeKind": "Page",
    "sourcePath": "docs/harness-features-backlog/gaps/prompt-engineering/GAP-PROMPT-011.md",
    "sourceKind": "repo-docs",
    "title": "GAP-PROMPT-011: Output Efficiency Rules",
    "displayName": "GAP-PROMPT-011: Output Efficiency Rules",
    "slug": "docs/harness-features-backlog/gaps/prompt-engineering/gap-prompt-011",
    "articlePath": "wiki/docs/harness-features-backlog/gaps/prompt-engineering/GAP-PROMPT-011.md",
    "article": "\n# GAP-PROMPT-011: Output Efficiency Rules\n\n| Field | Value |\n|-------|-------|\n| Category | prompt-engineering |\n| Priority | Medium |\n| Effort | S |\n| Status | Missing |\n\nLast refreshed: 2026-04-25\n\n## Description\nInclude output efficiency guidelines in orchestration prompts to reduce token consumption from verbose delegated agent output. Long-running orchestrations accumulate context quickly; concise output from each iteration preserves token budget for actual work.\n\n## Current State\nIteration prompts generated by `session:iteration-message` do not include output efficiency guidelines. Delegated agents often produce verbose explanations, repeat user instructions, and include unnecessary preamble. This wastes token budget, especially in multi-iteration orchestrations where context accumulates.\n\n## Target State\nAn `outputEfficiency` prompt section injected into iteration prompts and task prompts. Content: lead with action not reasoning, skip filler and preamble, do not restate instructions, focus on decisions needing input / status updates / errors, one sentence over three when possible. Adapted from CC's output efficiency rules. Configurable verbosity level per process definition (verbose for debugging, concise for production).\n\n## Dependencies\n- [GAP-PROMPT-001](../prompt-engineering/GAP-PROMPT-001.md) -- strata model for section placement\n- [GAP-PERF-002](../performance/GAP-PERF-002.md) -- session compaction for token management\n\n## Key Files\n| Component | Path |\n|-----------|------|\n| Prompts module | `packages/sdk/src/prompts/` |\n| Session management | `packages/sdk/src/session/` |\n| CC prompt phrasing analysis | [`11-prompt-phrasing-analysis.md`](../../11-prompt-phrasing-analysis.md) -- Section 5 (Output Efficiency Rules) has exact CC phrasing |\n\n## Recommendation\nPhase 2 implementation. Small effort -- extract efficiency rules, inject into iteration prompt template. Measurable impact on token usage in multi-iteration runs.\n",
    "documents": []
  },
  "outgoingEdges": [],
  "incomingEdges": [
    {
      "from": "page:docs-harness-features-backlog",
      "to": "page:docs-harness-features-backlog-gaps-prompt-engineering-gap-prompt-011",
      "kind": "contains_page"
    }
  ]
}