new

new is a command for coding agents from tzachbon/smart-ralph. It costs 7 tokens per session (2,150 once invoked), scanned A, original, MIT.

A command that creates a new software specification and starts its research phase. A specification is a written plan describing a proposed change and its supporting decisions.

In plain words
What is it for?
Use it to create a named specification, record an optional goal, choose an allowed specs directory, and begin or skip research.
Why use it?
It gives a new idea a defined place in the project and starts the work needed to understand it before requirements are written. Research can also be skipped when appropriate.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the ralph-specum plugin — 3 skills, 11 commands, 7 agents shipped together

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/tzachbon/smart-ralph/new
Clone the repo
git clone --depth 1 https://github.com/tzachbon/smart-ralph

Or install ralph-specum, the plugin that ships this one along with the rest of its 3 skills, 11 commands, 7 agents.

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/tzachbon/smart-ralph/new.svg)](https://agentmods.dev/commands/tzachbon/smart-ralph/new)
Your own site
<a href="https://agentmods.dev/commands/tzachbon/smart-ralph/new"><img src="https://agentmods.dev/badge/commands/tzachbon/smart-ralph/new.svg" alt="Measured on agentmods" height="20"></a>
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,150 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 $0.00007 $0.02150
Opus 5 $0.00003 $0.01075
Sonnet 5 $0.00001 $0.00430
Haiku 4.5 $0.00001 $0.00215

Measured yesterday against content hash ec9558b5ce81, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

new 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 yesterday.

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.

plugins/ralph-specum/commands/new.md · 276 lines

How it starts

The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create New Spec

You are creating a new specification and starting the research phase.

Parse Arguments

From $ARGUMENTS, extract:

  • name: The spec name (required, must be kebab-case, first argument)
  • goal: Everything after the name except flags (optional)
  • --skip-research: If present, skip research and start with requirements
  • --specs-dir : Create spec in specified directory (must be in configured specs_dirs array)

Examples:

  • /ralph-specum:new user-auth -> name="user-auth", goal=none
  • /ralph-specum:new user-auth Add OAuth2 login -> name="user-auth", goal="Add OAuth2 login"
  • /ralph-specum:new user-auth --skip-research -> name="user-auth", goal=none, skip research
  • /ralph-specum:new api-auth --specs-dir ./packages/api/specs -> create in specified dir

Multi-Directory Resolution

This command uses the path resolver for multi-directory support:

# Source path resolver (conceptually - commands don't execute bash directly)
# These functions are available via the path-resolver.sh helper:

ralph_get_specs_dirs()    # Returns all configured spec directories
ralph_get_default_dir()   # Returns first specs_dir (default for new specs)
ralph_find_spec(name)     # Find spec by name, returns full path
ralph_list_specs()        # List all specs as "name|path" pairs
ralph_resolve_current()   # Resolve .current-spec to full path

--specs-dir Validation

When --specs-dir is provided:

  1. Call ralph_get_specs_dirs() to get configured directories
  2. Check if provided path matches one of the configured directories
  3. If NOT in configured list: Error "Invalid --specs-dir: '$path' is not in configured specs_dirs"
  4. If valid: Use this path as the spec root instead of default
--specs-dir Validation Logic:

1. Extract --specs-dir value from $ARGUMENTS
2. Get configured dirs: dirs = ralph_get_specs_dirs()
3. Normalize paths (remove trailing slashes)
4. Check: specsDir in dirs?
   - YES: Use specsDir for spec creation
   - NO: Error "Invalid --specs-dir: '$specsDir' is not in configured specs_dirs. Configured: $dirs"

Read the full file on GitHub · 276 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. yesterday First seen · 276 lines · 7 tokens per session scan A ec9558b5ce81

Subscribe to this mod's changes

new is a command published in the GitHub repository tzachbon/smart-ralph (533 stars, last pushed 2d ago), licensed MIT. It adds 7 tokens to every session and 2,150 once invoked, about $0.0000 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 2026-09-03.