fewword

FewWord - Filesystem-Based Context Engineering

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "fewword" with this command: npx skills add sheeki03/few-word/sheeki03-few-word-fewword

FewWord - Filesystem-Based Context Engineering

The filesystem provides a single interface for storing, retrieving, and updating effectively unlimited context. This addresses the fundamental constraint that context windows are limited while tasks often require more information.

Core insight: Files enable dynamic context discovery—pull relevant context on demand rather than carrying everything in the context window.

v1 Feature: Bash commands are automatically intercepted and their output is offloaded to files when large. You will see a pointer and preview instead of full output.

Directory Structure

project/ └── .fewword/ # All plugin data in one namespace ├── scratch/ # Ephemeral (auto-cleaned hourly) │ ├── tool_outputs/ # Offloaded command outputs │ └── subagents/ # Agent workspace files ├── memory/ # Persistent (survives cleanup) │ ├── plans/ # Archived completed plans │ ├── history/ # Archived sessions │ ├── patterns/ # Discovered patterns │ └── preferences.yaml # User preferences ├── index/ # Metadata tracking │ ├── current_plan.yaml # THE canonical active plan │ ├── tool_log.jsonl # Tool execution log │ └── mcp_metadata.jsonl # MCP tool metadata └── DISABLE_OFFLOAD # Create to disable auto-offloading

Escape Hatch

If automatic offloading causes issues:

  • Create file: touch .fewword/DISABLE_OFFLOAD

  • Or set env: export FEWWORD_DISABLE=1

Automatic Behaviors (v1)

Bash Output Offloading

When you run a Bash command, the plugin automatically:

  • Captures stdout+stderr to a file

  • After completion, measures output size

  • If small (<8KB): shows full output normally, deletes temp file

  • If large: shows pointer + preview (first/last 10 lines)

  • Preserves the original exit code

What you see for large output:

=== [FewWord: Output offloaded] === File: .fewword/scratch/tool_outputs/pytest_20250107_143022_a1b2c3d4.txt Size: 45678 bytes, 1234 lines Exit: 0

=== First 10 lines === ...preview...

=== Last 10 lines === ...preview...

=== Retrieval commands === Full: cat .fewword/scratch/tool_outputs/pytest_20250107_143022_a1b2c3d4.txt Grep: grep 'pattern' .fewword/scratch/tool_outputs/pytest_20250107_143022_a1b2c3d4.txt

Skipped commands (v1 conservatively skips):

  • Interactive: ssh, vim, less, top, watch, python, node, psql, etc.

  • Already redirecting: commands with > , 2> , | tee , | less

  • Heredocs: commands containing <<

  • Pipelines: commands containing |

  • Trivial: very short commands

MCP Tool Handling

  • All MCP tool calls are logged to .fewword/index/mcp_metadata.jsonl

  • Write-like operations (create, update, delete, commit, push) are gated

  • Pagination parameters are automatically clamped to prevent excessive results

Manual Patterns

Pattern 1: Plan Persistence

For long-horizon tasks, use the canonical active plan:

.fewword/index/current_plan.yaml

objective: "Refactor authentication module" status: in_progress steps:

  • id: 1 description: "Audit current auth endpoints" status: completed

  • id: 2 description: "Design new token validation" status: in_progress

  • id: 3 description: "Implement and test" status: pending

  • Plan survives context summarization

  • Re-read at turn start or when losing track

  • When completed, automatically archived to memory/plans/

Pattern 2: Sub-Agent File Workspaces

Sub-agents write findings directly to filesystem instead of message passing:

.fewword/scratch/subagents/ ├── research_agent/ │ ├── findings.md │ └── sources.jsonl ├── code_agent/ │ ├── changes.md │ └── test_results.txt └── synthesis.md

Pattern 3: Chat History as File Reference

When context window fills:

  • Write full history to .fewword/memory/history/session_{id}.txt

  • Generate summary for new context window

  • Include reference: "Full history in .fewword/memory/history/session_{id}.txt"

  • Use grep to recover details lost in summarization

Search Techniques

Tool Use Case Example

ls / find

Discover structure find .fewword -name "*.txt" -mmin -30

grep

Content search grep -rn "error" .fewword/scratch/

head /tail

Boundary reads tail -100 .fewword/scratch/tool_outputs/log.txt

sed -n

Line ranges sed -n '50,100p' file.txt

References

For detailed implementation patterns, see:

  • references/implementation-patterns.md

  • Code examples for each pattern

  • references/cleanup-strategies.md

  • Scratch file lifecycle management

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

test_skill

import json import tkinter as tk from tkinter import messagebox, simpledialog

Archived SourceRecently Updated
General

magister.net

Fetch schedule, grades, and infractions from https://magister.net 🇳🇱 portal

Registry SourceRecently Updated
1400ghuron
General

Official Doc

公文写作助手。通知、报告、请示、批复、会议纪要、工作总结、格式检查、语气检查、模板库。Official document writer for notices, reports, requests, meeting minutes with format check, tone check, template l...

Registry SourceRecently Updated
2392ckchzh
General

Douyin Creator

抖音内容创作与运营助手。抖音运营、抖音涨粉、短视频创作、抖音标题、抖音标签、抖音SEO、抖音账号运营、抖音数据分析、抖音选题、抖音脚本、抖音文案、抖音评论区运营、抖音人设定位、抖音发布时间、DOU+投放、抖音流量、短视频运营、视频创意、直播脚本、话题标签策略、合拍翻拍创意、抖音变现、带货星图、Douyin con...

Registry SourceRecently Updated