Is the FewWord skill free?

Yes. The skill itself is free from sheeki03/Few-Word. SkillProof publishes the install command and an independent test verdict at no cost.

What is the FewWord SkillProof Score?

7.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 2/5.

How do I install FewWord?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use FewWord with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

FewWord

Auto-offloads big command output to files, returns a compact pointer

by sheeki03 · sheeki03/Few-Word

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 7.6/10
Tested: Jul 17, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 274338f

Executed the offload hook live: a 600-line, 20KB command was rewritten to capture output to .fewword and returned a single ~10-token pointer to the model instead of the full dump, a real and measured context saving over the baseline. But that automation lives in the plugin's PreToolUse hooks, not in the SKILL.md, so installing it as a plain skill delivers only the manual filesystem-memory patterns. The advertised 'secret redaction ON by default' is not wired into the offload path: an AWS key in the output was written to disk verbatim 600 times, and the Redactor class is imported but never called. The session-start update check also pings GitHub on every launch (a public GET with no user data and an opt-out env var). Strong mechanism, but it needs the plugin/hooks install and its redaction claim is currently false.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 7/10
Docs & honesty 2/5

What FewWord does

A context-engineering plugin that intercepts Bash commands via hooks, captures large stdout/stderr to files under .fewword/, and returns the model a short pointer plus preview instead of the full dump, with a filesystem-memory workflow for plans and sub-agent state. Triggers when tool outputs exceed a few thousand tokens or the user mentions offloading context, scratch pads, filesystem memory, or reducing context bloat.

How to install FewWord

git clone https://github.com/sheeki03/Few-Word.git
mkdir -p ~/.claude/skills
cd Few-Word && cp -r plugins/fewword/skills/fewword ~/.claude/skills/fewword

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger FewWord

/fewword Auto-offloads big command output to files, returns a compact pointer

It also activates on plain-language prompts like these:

this command's output is huge, can you offload it to a file
set up a scratch pad so tool output stops bloating our context
reduce the context bloat coming from these massive build logs

Frequently asked questions

Is the FewWord skill free?: Yes. The skill itself is free from sheeki03/Few-Word. SkillProof publishes the install command and an independent test verdict at no cost.
Does FewWord work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 17, 2026. Verdict: Works with setup. Executed the offload hook live: a 600-line, 20KB command was rewritten to capture output to .fewword and returned a single ~10-token pointer to the model instead of the full dump, a real and measured context saving over the baseline. But that automation lives in the plugin's PreToolUse hooks, not in the SKILL.md, so installing it as a plain skill delivers only the manual filesystem-memory patterns. The advertised 'secret redaction ON by default' is not wired into the offload path: an AWS key in the output was written to disk verbatim 600 times, and the Redactor class is imported but never called. The session-start update check also pings GitHub on every launch (a public GET with no user data and an opt-out env var). Strong mechanism, but it needs the plugin/hooks install and its redaction claim is currently false.
What is the FewWord SkillProof Score?: 7.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 2/5.
How do I install FewWord?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use FewWord with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.