new-command

new-command is a command for Claude Code from ABO896/obsidian-university-workflow. It costs 28 tokens per session (568 once invoked), scanned A, original, MIT.

A project-aware command generator for Claude Code, a coding assistant that supports slash commands such as /review-config. It uses the Anthropic API to draft a complete command from a name, description, and project files.

In plain words
What is it for?
Use it to create a new Claude Code command based on the project's CLAUDE.md, skills, and existing commands.
Why use it?
It avoids writing and formatting a new slash command by hand while helping it match the project's existing rules and style.

Command for Claude Code

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 commands/abo896/obsidian-university-workflow/new-command
Clone the repo
git clone --depth 1 https://github.com/ABO896/obsidian-university-workflow

Made for: Claude Code.

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 new-command

README.md
[![agentmods](https://agentmods.dev/badge/commands/abo896/obsidian-university-workflow/new-command.svg)](https://agentmods.dev/commands/abo896/obsidian-university-workflow/new-command)
Your own site
<a href="https://agentmods.dev/commands/abo896/obsidian-university-workflow/new-command"><img src="https://agentmods.dev/badge/commands/abo896/obsidian-university-workflow/new-command.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 568 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 $0.00028 $0.00568
Opus 5 $0.00014 $0.00284
Sonnet 5 $0.00006 $0.00114
Haiku 4.5 $0.00003 $0.00057

Measured 5d ago against content hash ae89e84d5021, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

new-command 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 5d 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.

.claude/commands/new-command.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are creating a new Claude Code slash command for this project. Follow every step below in order.


Step 1 — Gather Inputs

If the user provided arguments, parse them as: <command-name> <description>.

If no arguments were provided (or they are incomplete), use the AskUserQuestion tool to ask for:

  1. Command name — the slash command name (lowercase, kebab-case, no leading slash). Example: review-config
  2. Command description — a one-sentence summary of what the command should do when invoked.

Step 2 — Read Project Context

Read the following files to understand the project deeply:

  1. CLAUDE.md — project rules, structure, and conventions
  2. .claude/skills/templater-docs/SKILL.md — Templater docs skill reference
  3. All existing commands in .claude/commands/ — to understand tone, format, and conventions used by existing slash commands in this project

Step 3 — Draft the Command Using the Anthropic API

Use the claude-api skill to call the Anthropic API (Claude) with a prompt that includes:

  • The full contents of CLAUDE.md as project context
  • The command name and description from Step 1
  • A system prompt instructing the model to generate a well-structured Claude Code slash command in markdown format, following the conventions observed in existing commands (phased structure, clear instructions, grounded in project-specific files and patterns)

The API call should ask the model to produce the complete markdown body of the new command file, including:

  • YAML frontmatter with a description field
  • Phased or sectioned instructions that Claude will follow when the command is invoked
  • References to specific project files, scripts, or conventions from CLAUDE.md where relevant
  • Clear, actionable steps — not vague guidance

Step 4 — Save the Command

Write the generated markdown to .claude/commands/<command-name>.md where <command-name> is the name from Step 1.

After writing, read the file back and display it to the user for review.

Read the full file on GitHub · 61 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. 5d ago First seen · 61 lines · 28 tokens per session scan A ae89e84d5021

Subscribe to this mod's changes

new-command is a command published in the GitHub repository ABO896/obsidian-university-workflow (23 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 568 once invoked, about $0.0001 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 2026-08-30.