llms.txt@site/public git:20260728.f024119A

Immutable. This exact content is served forever at /api/v1/blob/466082403c1b4f5a.

# Chisle

> Chisle is a Claude Code plugin (also usable with Cursor, Windsurf, Cline, Kiro, and GitHub Copilot via generated rule files) that cuts LLM token usage on three axes: (1) a terse senior-dev persona that writes maximum-signal prose and YAGNI-first code, (2) a PostToolUse hook that compresses tool output (ANSI scrub, head+tail elide with error-line salvage, same-session dedup) before it enters the context window, and (3) context-diet rules that teach the model to read less (grep before Read, slice reads, filter at source).

Key measured results (20 live tasks, 4 arms, billed tokens, reproducible via benchmarks/ in the repo):
- Total 20-task bill: Chisle 52% of a bare model; ponytail 68%; caveman 80%.
- Average task: Chisle 69% vs ponytail 91%, caveman 98%.
- Backfires (task costing more than baseline): Chisle 1/20; ponytail 6/20; caveman 8/20 (worst single task 424%).
- Tool output measured as 67.5% of session content across 171 real transcripts; eligible outputs shrink ~46%.

Safety/correctness: the compressor runs behind an allowlist (Bash, Agent, WebFetch, WebSearch, Grep, Glob, mcp__*) and never modifies Read/Edit/Write results, whose exact bytes feed later edits. Deterministic, zero dependencies, zero network calls, zero LLM calls. Kill switches: CHISLE_COMPRESS=0, "stop chisle", npx chisle --uninstall.

Install: `npx chisle` (npm) or `claude plugin marketplace add JayPokale/Chisle` then `claude plugin install chisle@chisle` (Claude Code plugin). Requires Node >= 18. MIT license.

Lineage: descendant of the caveman and ponytail projects (terse-persona axis), both credited in the repository's prior-art table; Chisle adds the tool-output-compression and context-diet axes and publishes live benchmarks against both.

## Links

- [GitHub repository](https://github.com/JayPokale/Chisle): source, benchmarks, raw transcripts
- [npm package](https://www.npmjs.com/package/chisle): installer
- [Benchmarks](https://github.com/JayPokale/Chisle/tree/main/benchmarks): 4-arm live runner + results
- [Changelog](https://github.com/JayPokale/Chisle/blob/main/CHANGELOG.md)

## Author

Jay Pokale (https://github.com/JayPokale), co-engineered with Claude (Anthropic), Codex (OpenAI), and Antigravity (Google).