---
title: "builder"
description: "Agent Plugin for Builders"
canonical: https://agentpluginsdirectory.com/plugins/builder
last-updated: 2026-10-21
---

# builder
Agent Plugin for Builders
- Slug: builder
- Publisher: thimslugga
- Repository: https://github.com/thimslugga/agent-plugins
- Manifest: plugins/builder/plugin.json
- Version: 1.0.0
- License: MIT
- Category (editorial): agent-tooling
- Skills: 35 (adr, asd-ste100, ast-grep-outline, ast-grep, autoresearch, caveman, diagram-design, economist-style, gauntlet-loop, golang-pro, grill-me, handoff, herdr, humanizer, i-have-adhd, impeccable, intent, karpathy-guidelines, linus-review, mermaid-architecture-diagrams, mermaid-diagrams, no-ai-slop, onboarding, playwright-skill, poka-yoke, ponytail, python-code-pro, research, rfc, s3-files, sem, shell-script-pro, simple-english, taste-interviewer, unslop-ui)
- MCP servers: 4 (aws-knowledge, context7, exa, github)
- Stars: 0
- Repository created: 2026-08-29
- Repository last pushed: 2026-10-14
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/builder
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## Skills

- adr
- asd-ste100: Use when English text must be parsed without a human to resolve ambiguity, tool descriptions, error messages, inter-agent instructions, system prompts, status reports, and misreading has a real cost, or when text reads as dense, hedged, or easy to misparse. Triggers: disambiguate, STE100 rewrite,…
- ast-grep-outline
- ast-grep
- autoresearch: 'Autonomous iterative experimentation loop for any programming task. Guides the user through defining goals, measurable metrics, and scope constraints, then runs an autonomous loop of code changes, testing, measuring, and keeping/discarding results. Inspired by Karpathy''s autoresearch. USE FOR: au…
- caveman: Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra, off. Use when user invokes /caveman, $caveman, user says "caveman mode", "talk like caveman", "be brief" or "less tokens"; stays on until user says "stop caveman" or "normal mode…
- diagram-design
- economist-style: Apply The Economist style guide to written content. Detects weasel words, fillers, passive voice, and style issues. Use when editing markdown, HTML, documentation, or any written text that needs professional editing for clarity, precision, and brevity.
- gauntlet-loop: Create a short, paste-ready agent prompt that turns a concrete goal and a real reference into an iterative builder-critic loop. Use when user invokes /gauntlet-loop or $gauntlet-loop, says "gauntlet loop" or "gauntlet this", requests a gauntlet prompt, or asks to keep improving work until it beats…
- golang-pro
- grill-me: Structured questioning to reach shared understanding before action. Walks the decision tree one branch at a time, checks memory for already-answered questions, saves every answer as a lesson. Use when user wants to think through a plan, align on approach, poke holes in a design, or figure out decis…
- handoff: Compacts the current conversation into a handoff document so a fresh agent can continue the work in a new session. Use when user invokes /handoff, $handoff, or user says "handoff document", "create handoff document".
- herdr: Control Herdr, a terminal multiplexer for coding agents. Use only when the user explicitly mentions Herdr or asks to use Herdr to inspect or control panes, tabs, workspaces, commands, or another agent. Do not use merely because a task could benefit from a background terminal, delegation, or paralle…
- humanizer: Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analys…
- i-have-adhd: Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Use when user invokes /i-have-adhd, $i-have-adhd, user says "adhd mode"; stays on until user says "stop adhd mode".
- impeccable
- intent
- karpathy-guidelines: Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
- linus-review
- mermaid-architecture-diagrams
- mermaid-diagrams
- no-ai-slop
- onboarding
- playwright-skill
- poka-yoke
- ponytail
- python-code-pro
- research
- rfc
- s3-files
- sem
- shell-script-pro
- simple-english
- taste-interviewer
- unslop-ui

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.

## MCP servers

- aws-knowledge: transport: streamable-http; url: https://knowledge-mcp.global.api.aws
- context7: transport: streamable-http; url: https://mcp.context7.com/mcp
- exa: transport: streamable-http; url: https://mcp.exa.ai/mcp
- github: transport: streamable-http; url: https://api.githubcopilot.com/mcp/

Read from the plugin's own mcp.json. Environment variable names only, never values.