token-efficiency
Minimize token waste in all bash, file, and data processing operations
Open source Open in the app JSON README (API)
About
Minimize token waste in all bash, file, and data processing operations
Details
- Kind
- Plugins
- Topic
- No topic detected
- Publisher
- undefdev
- Origin
- gemini
- Category
- ferramentas
- Version
- 1.0.0
- Stars
- 29
- Forks
- 3
- Last push
- 2026-07-04T15:58:56Z
- Repository state
- ativo
- Language
- Shell
- License
- MIT
- Added
- 2026-08-30 14:13:39
- Updated
- 2026-08-30 14:13:39
- Origin id
undefdev/token-efficiency
README
# Token Efficiency A skill that teaches coding agents to minimize token waste in all tool use, file reading, and data processing operations. Every byte of tool output is money and context window spent. This skill instills the habit of filtering, projecting, and truncating at the source — not dumping raw output and hoping for the best. > **Sunset notice:** This skill exists because current coding agents haven't yet internalized efficient tool use. As models improve and these practices become default behavior, this skill will be discontinued. ## What it covers - Structured query tools (`jq`, `yq`, `awk`) over dump-and-read - Precision search (`ast-grep`, `rg`) over broad text search - Git summary-first workflows (`--stat`, `--name-only`) - Output noise suppression (quiet flags, `NO_COLOR`, selective reads) - Hash-based change detection over re-reading files - Coreutils over Python for simple transforms ## Installation ### Claude Code First, add the marketplace: ``` /plugin marketplace add undefdev/token-efficiency ``` Then install: ``` /plugin install token-efficiency@undefdev-token-efficiency ``` ### Cursor Not yet available on the Cursor Marketplace. For now, clone the repo and add the skill content to your project's rules manually. ### Gemini CLI ```bash gemini extensions install https://github.com/undefdev/token-efficiency ``` ### Codex See [.codex/INSTALL.md](.codex/INSTALL.md) ### OpenCode See [.opencode/INSTALL.md](.opencode/INSTALL.md)