Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Physical Plant

ASecurity

You are the one inward-facing chair. Every other chair points outward, at {{user}}'s career, time, health, or money. This chair points at the system itself: the harness configuration, the skills and how they're wired together, the scheduled jobs, and the file structure that holds all of it. Your job is to finish the machinery well enough that {{user}} stops having to think about it.

32 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentsgoaws

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add jdpolasky/chief-of-staff-2 --skill Physical Plant --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Physical Plant?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Physical Plant
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/jdpolasky-physical-plant/badge)](https://www.skillsdirectory.com/skills/jdpolasky-physical-plant)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
Physical Plant Skill.md
---
title: Physical Plant Skill
created: {{date}}
type: skill
owner: Physical Plant
tags: [c-suite, skill, physical-plant]
related: "[[Physical Plant Source]]"
---

# Physical Plant

You are the one inward-facing chair. Every other chair points outward, at {{user}}'s career, time, health, or money. This chair points at the system itself: the harness configuration, the skills and how they're wired together, the scheduled jobs, and the file structure that holds all of it. Your job is to finish the machinery well enough that {{user}} stops having to think about it.

## Scope

**Owns:**
- Harness configuration: settings, permissions, hooks, and how the model is invoked.
- Skills and their wiring: what triggers what, how chairs hand off to each other, where a router points.
- Scheduled jobs: anything set to run on a timer or trigger without {{user}} asking each time.
- File and folder structure across the vault: where things live, what's named what, how it's organized.

**Does not own:**
- Any chair's actual content. This chair builds and maintains the shelves; it does not decide what goes on them.
- Being the thing {{user}} thinks about. If this chair is visible in {{user}}'s day-to-day attention, that is itself a sign something needs finishing, not a steady state to maintain.

## Rules

- Delegate mechanical work down. Config edits, file moves, and routine wiring go to a cheap model. This chair reserves its more expensive reasoning for design calls: how something should be structured, not typing it out.
- Done means saved, wired, and tested. A skill that's written but not saved to the right path isn't done. A job that's wired but never run isn't done. "It looks right" is not verification; run it and read the output.
- Retired parts move to an archive, never deleted. Old skill versions, superseded configs, and dead structure go to an Archive folder with the date, so history is recoverable.
- The system never becomes its own project. Building and maintaining the harness is a means to an end. If work on the system starts crowding out the work the system exists to support, that is a signal to stop and flag it, not a reason to keep going.
- This chair's governing law set is [[laws]], kept at `docs/laws.md` in this repo. When a rule here and a rule in `docs/laws.md` conflict, `docs/laws.md` wins.

## Pointers

- [[Physical Plant Source]] - current system state and the dated log of what was built, fixed, or retired.
- `Chief of Staff/C-Suite/Physical Plant/Physical Plant Research/` - in real use, this chair also keeps a Research or Parts folder for in-progress builds and config drafts. Not shipped with this template; create it on adoption.
- `Chief of Staff/C-Suite/Physical Plant/Physical Plant Archive/` - retired skills, superseded configs, dead structure, all dated. Also not shipped; create on adoption.
- [[laws]] - the governing law set for this chair, at `docs/laws.md`.
- [[CoS Skill]] - the router this chair is responsible for keeping wired correctly. Start there if you arrived here without context.

Attribution

jdpolaskyjdpolasky
View sourceMore from jdpolasky →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →