create-prompt

create-prompt is a skill for Claude Code, Codex from marcus/sidecar. It costs 55 tokens per session (1,053 once invoked), scanned A, original, MIT.

A guide for creating reusable prompt templates in Sidecar workspace configuration files. It explains the fields, template variables, and how project settings override global settings.

In plain words
What is it for?
Use it to create or edit prompts for tasks such as code reviews, bug fixes, and feature work.
Why use it?
It removes the need to remember the configuration format and where each prompt should be stored.

Skill for Claude CodeCodex

About the project

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.

marcus/sidecar · 1,055 stars · on GitHub

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/marcus/sidecar/create-prompt
Any agent
npx skills add marcus/sidecar --skill create-prompt
Clone the repo
git clone --depth 1 https://github.com/marcus/sidecar

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for create-prompt

README.md
[![agentmods](https://agentmods.dev/badge/skills/marcus/sidecar/create-prompt.svg)](https://agentmods.dev/skills/marcus/sidecar/create-prompt)
Your own site
<a href="https://agentmods.dev/skills/marcus/sidecar/create-prompt"><img src="https://agentmods.dev/badge/skills/marcus/sidecar/create-prompt.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,053 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00055 $0.01053
Opus 5 $0.00028 $0.00526
Sonnet 5 $0.00011 $0.00211
Haiku 4.5 $0.00006 $0.00105

Measured today against content hash 241e4fc3b88e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

create-prompt 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 today.

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.

.claude/skills/create-prompt/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Creating Prompts

Prompts are reusable templates that configure the initial context for agents when creating workspaces. They help standardize common workflows like code reviews, bug fixes, or feature implementation.

Config File Locations

Scope Path Override Priority
Global ~/.config/sidecar/config.json Lower
Project .sidecar/config.json (in project) Higher

Project prompts override global prompts with the same name (case-sensitive match).

Config Format

{
  "prompts": [
    {
      "name": "Code Review",
      "ticketMode": "optional",
      "body": "Do a detailed code review of {{ticket || 'open reviews'}}.\nFocus on correctness, edge cases, and test coverage."
    }
  ]
}

Prompt Fields

name (required)

Display name shown in the prompt picker. Keep it concise.

ticketMode (optional)

Controls how the ticket/task field behaves:

Mode Behavior
optional Task field shown, can be empty (default)
required Task must be selected before creating
none Task field is hidden, prompt stands alone

body (required)

The prompt text sent to the agent. Supports template variables. Use \n for newlines.

Template Variables

{{ticket}}

Expands to the selected task ID. Returns empty string if no task selected.

"body": "Fix issue {{ticket}}."
// With task td-abc123: "Fix issue td-abc123."
// Without task: "Fix issue ."

{{ticket || 'fallback'}}

Expands to task ID, or the fallback text if no task selected.

"body": "Review {{ticket || 'all open items'}}."
// With task td-abc123: "Review td-abc123."
// Without task: "Review all open items."

Only single quotes work for fallback text:

  • {{ticket || 'default'}} -- works
  • {{ticket || "default"}} -- does NOT work

Read the full file on GitHub · 137 lines

Changes

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.

  1. today First seen · 137 lines · 55 tokens per session scan A 241e4fc3b88e

Subscribe to this mod's changes

create-prompt is a skill published in the GitHub repository marcus/sidecar (1,055 stars, last pushed 2d ago), licensed MIT. It adds 55 tokens to every session and 1,053 once invoked, about $0.0003 per session on Opus 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 2026-09-05.