spec

spec is a command for Claude Code from zachjxyz/jvn. It costs 6 tokens per session (595 once invoked), scanned A, original, MIT.

A command that creates a feature specification, a written description of what a software feature should do and how it should be judged. It starts a feature branch and specification file, then enriches the document with product and engineering requirements.

In plain words
What is it for?
Use it to start a feature branch, create a specification, add performance and security requirements, define what is in or out of scope, and record open questions.
Why use it?
It turns a short feature idea into a more complete plan with user stories, acceptance criteria, boundaries, risks, and measurable success conditions.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

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/zachjxyz/jvn/spec
Clone the repo
git clone --depth 1 https://github.com/zachjxyz/jvn

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 spec

README.md
[![agentmods](https://agentmods.dev/badge/commands/zachjxyz/jvn/spec.svg)](https://agentmods.dev/commands/zachjxyz/jvn/spec)
Your own site
<a href="https://agentmods.dev/commands/zachjxyz/jvn/spec"><img src="https://agentmods.dev/badge/commands/zachjxyz/jvn/spec.svg" alt="Measured on agentmods" height="20"></a>
Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 595 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 $0.00006 $0.00595
Opus 5 $0.00003 $0.00298
Sonnet 5 $0.00001 $0.00119
Haiku 4.5 $0.00001 $0.00060

Measured 5d ago against content hash e8561ef5dad4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

spec 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.

stacks/python/.claude/commands/spec.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/spec — Create a Feature Specification

You are orchestrating the specification phase. Follow these steps exactly.

User Input

$ARGUMENTS

Step 1: Create Feature via Spec-Kit

Use the Skill tool to invoke the speckit-specify skill:

Skill(skill: "speckit-specify", args: "$ARGUMENTS")

This creates:

  • A feature branch (NNN-short-name)
  • A specs/NNN-short-name/ directory
  • A base spec.md from spec-kit's template

Wait for completion. Note the spec path from the output.

Step 2: Enrich with Product Manager

Use the Task tool to invoke the product-manager agent:

Task(subagent_type: "product-manager",
     description: "Enrich feature specification",
     prompt: "Read the specification at specs/{feature}/spec.md. Enhance it with:
     - Deeper user stories with acceptance criteria
     - Non-functional requirements (performance, security, scalability)
     - Clear scope boundaries (in scope / out of scope)
     - Success criteria (measurable, technology-agnostic)
     - Risks and open questions
     If .specify/memory/constitution.md exists, validate feature alignment.
     Write the enriched content back to the same file.")

Step 3: Add Data Considerations

Use the Task tool to invoke the data-analyst agent:

Task(subagent_type: "data-analyst",
     description: "Add data brief to specification",
     prompt: "Read the specification at specs/{feature}/spec.md. Append a Data Brief section covering:
     - Data sources and formats
     - Pipeline design (ETL/processing steps)
     - Model I/O schemas (input features, output format, confidence)
     - Validation strategy (data quality checks, schema validation)
     - Error handling and fallback behavior
     - Performance considerations (batch vs streaming, caching)
     Append the Data Brief section to the same file.")

Step 4: Present Summary

Present the enriched specification to the user:

  • Show the spec path
  • Highlight key user stories and requirements
  • Note any [NEEDS CLARIFICATION] markers

Read the full file on GitHub · 82 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 · 82 lines · 6 tokens per session scan A e8561ef5dad4

Subscribe to this mod's changes

spec is a command published in the GitHub repository zachjxyz/jvn (2 stars, last pushed 5mo ago), licensed MIT. It adds 6 tokens to every session and 595 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 2026-08-31.