# Token Efficiency

> trigger: large command output, broad searches, re-reading unchanged files, front-loading references. avoid: wasting context window on low-signal content.

- Skill: `open-coder-ai/token-efficiency` (Agent Skill)
- Install (CLI): `npx skillmds@latest add open-coder-ai/token-efficiency`
- Raw SKILL.md: https://api.skillmd.com/api/skills/open-coder-ai/token-efficiency/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: open-coder-ai (https://skillmd.com/u/open-coder-ai)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/open-coder-ai/token-efficiency

---


# Token Efficiency Rule

trigger: large command output, broad searches, re-reading unchanged files, front-loading references. avoid: wasting context window on low-signal content.

```
cap(tool_output): 4000_bytes; cap(search_results): top_3; cap(retry_loops): max_3_iterations
prefer: targeted_reads|structured_output|on_demand_refs; never: re-read(unchanged_file)|load_all_upfront
```

This skill is advisory: the client reading it has no mechanism to enforce it, and this policy stays advisory even when compiled by `chock` -- it ships rule text, not a blocking hook. See https://github.com/open-coder-ai/chock