Few Word — Development skill for Claude Code
Claude Code plugin that offloads large outputs to filesystem and retrieves when required.
How to install Few Word
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open sheeki03/Few-Word and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Few Word does
Claude Code plugin that offloads large outputs to filesystem and retrieves when required.
Alternatives in Development
- Claude Context Mode — An MCP server that sits between Claude Code and these outputs 5.3k ★
- Flow Parallel — Decompose and execute large changes, migrations, or multi-issue fixes in parallel with quality gates 2.8k ★
- Setup Context — Set up your Skill Memory — a pm-context.md every skill reads so outputs come back tailored to you 1.3k ★
README
FewWord
"Why waste time say lot word when few word do trick? Big output go file. Small word stay. Context happy. Me happy. Everyone go home by seven."
— Kevin Malone
A Claude Code plugin that automatically offloads large command outputs to files, keeping your context clean and retrievable.
[](https://opensource.org/licenses/MIT) [](https://claude.ai/claude-code)
The Problem
AI coding agents hit a wall when:
- Tool outputs bloat your context — One big test run or log dump eats 10k tokens that sit there forever
- Plans get lost — After context summarization, Claude forgets what it was doing
- You're paying for waste — Most of your context is irrelevant to the current step
The Solution
FewWord implements **dynamic context discovery** — patterns from [Manus](https://manus.im/blog/Context-Engineering-for-AI-Agents-Lessons-from-Building-Manus) and [LangChain](https://blog.langchain.com/how-agents-can-use-filesystems-for-context-engineering/) that use the filesystem as infinite, searchable memory.
**Instead of this:**
[26,000 tokens of command outputs sitting in context forever]
**You get this (~35 tokens):**
[fw A1B2C3D4] find e=0 15K 882L | /open A1B2C3D4
For failures, you also get a preview:
[fw E5F6G7H8] pytest e=1 45K 234L | /open E5F6G7H8
FAILED test_auth.py::test_login - AssertionError
FAILED test_api.py::test_endpoint - TimeoutError
2 failed, 48 passed in 12.34s
How It Works
┌─────────────────────────────────────────────────────────────────┐
│ Claude Code Session │
├─────────────────────────────────────────────────────────────────┤
│
Related Skills
Agenfk Plan
Decompose an EPIC into stories (required), or a large STORY into tasks (agent's judgement)
Spark Of The Day
An autonomous agent that wakes up once a day, invents a whimsical 120-word micro-story using Claude on Amazon
Context Arbitration Layer
Context Arbitration Layer (CAL) extends claude-code with persistent, multi-subprocess context management. It o
Pantheon Remember
Store or recall a memory interactively. /pantheon-remember → stores it. /pantheon-remember recall → retrieves
Shortlist
description: Retrieves immutable ranking snapshots, including historical days
Seekstone
The Obsidian MCP server that needs no plugin, no running Obsidian app — and doesn't blow your context window.
Related Agents
Rephraser
Rephrases plain user statements into structured intent JSON. Surfaces a clarifying question only when absolute
Context Engine
Context window management — tracks tool call count, auto-detects when context fills up, triggers state save +
Log Slicer
SRE log analysis specialist. Use proactively during incidents to segment, summarize, and extract signal from l