tommy29tmar

Hewn — Development skill for Claude Code

Development community

Claude Code CLI wrapper: routes every turn to a compact answer shape (IR, prose+code, findings, polished, caveman) via system-prompt + per-turn drift-fix hook.

How to install Hewn

This entry records only its repository, not the path inside it, so there is no exact command to give. Open tommy29tmar/flint and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Hewn does

Claude Code CLI wrapper: routes every turn to a compact answer shape (IR, prose+code, findings, polished, caveman) via system-prompt + per-turn drift-fix hook.

Alternatives in Development

Research Codebase — You are tasked with conducting comprehensive research across the codebase to answer user questions by spawning 10k ★
Cavemem — Frozen — cross-agent persistent memory for coding assistants 674 ★
Caveman Claude Skill — Ultra-compressed communication mode for Claude 396 ★

README

Hewn

[![CI](https://img.shields.io/github/actions/workflow/status/tommy29tmar/hewn/ci.yml?branch=main&label=CI&style=flat-square&v=091)](https://github.com/tommy29tmar/hewn/actions/workflows/ci.yml) [![License: MIT](https://img.shields.io/github/license/tommy29tmar/hewn?style=flat-square&v=091)](LICENSE) [![Latest release](https://img.shields.io/github/v/release/tommy29tmar/hewn?style=flat-square&v=091)](https://github.com/tommy29tmar/hewn/releases) [![Made for Claude Code](https://img.shields.io/badge/made%20for-Claude%20Code-84cc16?style=flat-square)](https://claude.com/claude-code)

**Make Claude Code go longer before limits hit.**

*Less output burn. Less drift. Faster long sessions.*

Claude Code users tend to stay in one long session — it's the practical path: no lost context, no re-loading files, no re-doing setup. But that's also where the cost hits hardest: repeated context, long answers, and output burn exactly when the budget starts to matter.

Hewn is built for that failure mode. It keeps Claude Code tighter over long sessions by routing each turn into a compact answer shape and then re-asserting that route every turn, so the model spends less output on restating context and more on the actual work.

Caveman already showed that compressed prompting helps. Hewn is tuned for a different bottleneck: long-session efficiency when Claude Code limits get tight.

Simple rule: if you want the most aggressive compression on one giant prompt, use Caveman. If you spend hours inside one Claude Code session and the limits are the pain, use Hewn.

No proxy. No telemetry. Default `claude` untouched.

![Long Claude Code sessions — less burn, less drift, more room to work](assets/hero_benchmark.png)

This is the proof asset: the multi-turn benchmark where Hewn is strongest.

5-turn workflow, Claude Opus 4.7, same model and prompts across all four arms. Concept retention measured by transcript-aware LLM-as-judge.

Full methodology, raw snapshots, and