Sidecar is a terminal-based workspace for running AI coding agents alongside file trees, task issues, Git diffs, and Jira or GitHub resources in split panes. Developers use it to monitor agent sessions, inspect files and changes, manage workspaces, and handle tasks without leaving one shell. The catalogue entries extend or guide coding-agent workflows used with Sidecar.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/marcus/sidecarnpx agentmods add skills/marcus/sidecar/sidecar-websiteWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/marcus/sidecar/sidecar-website)<a href="https://agentmods.dev/skills/marcus/sidecar/sidecar-website"><img src="https://agentmods.dev/badge/skills/marcus/sidecar/sidecar-website/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/marcus/sidecar/sidecar-website"><img src="https://agentmods.dev/badge/skills/marcus/sidecar/sidecar-website.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00060 | $0.01683 |
| Opus 5.5 | $0.00024 | $0.00673 |
| Sonnet 5.5 | $0.00012 | $0.00337 |
| Haiku 4.5 | $0.00006 | $0.00168 |
Grade A, and why
sidecar-website scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docusaurus Documentation Site
The documentation site lives in website/. It uses Docusaurus with Node.js >= 20.
Quick Start
cd website
npm install # First time only
npm start # Dev server at http://localhost:3000
Project Structure
website/
├── docs/ # Markdown documentation pages
├── blog/ # Blog posts (date-prefixed markdown)
│ ├── authors.yml # Blog author definitions
│ └── tags.yml # Blog tag definitions
├── src/
│ ├── pages/ # Custom React pages (non-docs)
│ │ ├── index.js # Front page (/)
│ │ └── index.module.css
│ ├── components/ # Reusable React components
│ └── css/
│ └── custom.css # Global style overrides
├── static/ # Static assets (copied as-is to build)
│ └── img/ # Images
├── docusaurus.config.js # Main site configuration
├── sidebars.js # Docs sidebar structure
└── package.json
Writing Documentation
Principles
- User-first: Answer "what can I do?" before "how does it work?"
- Scannable: Use headers, code blocks, tables for keyboard shortcuts
- Progressive disclosure: Quick overview -> detailed usage -> full reference
- Working examples: Every feature needs runnable code, not
...placeholders
Creating a New Doc
Add a Markdown file in website/docs/ with YAML frontmatter:
---
sidebar_position: 2
title: My New Page
---
# My New Page
Content here. Supports **Markdown** and MDX.
Frontmatter options:
sidebar_position: Order in sidebar (lower = higher)sidebar_label: Override sidebar texttitle: Page titledescription: Meta description for SEOslug: Custom URL path
Plugin Documentation Pattern
# Plugin Name
One-line description.
## Overview
Brief explanation of UI layout and core purpose.
## Feature Section
Description with keyboard shortcut table:
| Key | Action |
|-----|--------|
| `s` | Stage file |
| `d` | View diff |
## Navigation
How to move around.
## Command Reference
Complete shortcut list by context.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 267 lines · 60 tokens per session scan A ca2259a0f976
sidecar-website is a skill published in the GitHub repository marcus/sidecar (1,091 stars, last pushed 11d ago), licensed MIT. It adds 60 tokens to every session and 1,683 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
revise-roadmap
Revise an implementation roadmap based on critic feedback.
build-knowledge-base
Build or update a persistent repo knowledge base graph.
research-codebase
Document codebase as-is through comprehensive research.
validate-phase-plan-structural
Per-phase plan structural validation gate - evaluates conformance to the concise vertical-slice phase-plan format.
implement
Execute an approved phase plan with TDD, dependency-aware task fan-out, required evidence, and a strict iteration handoff.
review-comments
Execute a feature-level review-comments cycle — aggregate unaddressed PR comments across every Feature.Repos PR, address or dismiss each one, and emit the standard handoff.