new-requirement

new-requirement is a command for Claude Code from MadaraUchiha-314/the-loop. It costs 27 tokens per session (800 once invoked), scanned A, original, MIT.

A command that drafts a requirements document for a new piece of work before a ticket exists. It saves the draft in a temporary specification folder and can use an earlier brainstorm document.

In plain words
What is it for?
Use it to define what a proposed change should do, then pass the resulting requirements to the command that creates a ticket.
Why use it?
It turns an idea into written, reviewable requirements before the team creates a ticket.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the the-loop plugin — 2 skills, 16 commands, 2 hooks shipped together

Good fit Use it to define what a proposed change should do, then pass the resulting requirements to the command that creates a ticket.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add MadaraUchiha-314/the-loop
Claude Code
/plugin install the-loop

Made for: Claude Code.

Or install the-loop, the plugin that ships this one along with the rest of its 2 skills, 16 commands, 2 hooks.

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-requirement

README.md
[![agentmods](https://agentmods.dev/badge/commands/madarauchiha-314/the-loop/new-requirement/github.svg)](https://agentmods.dev/commands/madarauchiha-314/the-loop/new-requirement)
Your own site
<a href="https://agentmods.dev/commands/madarauchiha-314/the-loop/new-requirement"><img src="https://agentmods.dev/badge/commands/madarauchiha-314/the-loop/new-requirement/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.

agentmods 80×15 button for new-requirement

Your own site · 80×15
<a href="https://agentmods.dev/commands/madarauchiha-314/the-loop/new-requirement"><img src="https://agentmods.dev/badge/commands/madarauchiha-314/the-loop/new-requirement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 800 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00027 $0.00800
Opus 5 $0.00014 $0.00400
Sonnet 5 $0.00005 $0.00160
Haiku 4.5 $0.00003 $0.00080

Measured 9d ago against content hash 028567f53c18, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

new-requirement 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 9d 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.

commands/new-requirement.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

the-loop: new-requirement $ARGUMENTS

Draft a requirements spec for work that has no ticket yet. Some work starts as an idea; the-loop lets you define the requirements first, then mint the ticket from them (/the-loop:create-ticket). This is a slice of /the-loop:work-on (Phase 1 only) — work-on remains the superset.

If the idea was first explored in a brainstorm.md (the optional Phase 0 root artifact from /the-loop:brainstorm), this command converts that locked brainstorm into requirements rather than starting from a blank page.

Read the the-loop skill and reference/workflow.md first (phases, EARS, reviews).

Steps

  1. Create or reuse the temporary spec folder. Slugify $ARGUMENTS<slug> and use docs/specs/draft-<slug>/ (reuse it if /the-loop:brainstorm already created it). draft-* folders are the-loop's convention for a spec that has no ticket yet; /the-loop:create-ticket renames it to docs/specs/<id>/.

  2. Convert from a brainstorm if present. If a sibling brainstorm.md exists in the folder, read it and derive the requirements from its locked direction — its chosen option becomes the introduction, its working hypothesis + hand-off become the user stories, and its resolved constraints become acceptance criteria. Do not proceed off an unlocked brainstorm (status not approved): lock it first, or say so and stop. Everything the brainstorm considered-and-rejected stays in brainstorm.md (the record); only the carried-forward direction lands in requirements.md.

  3. Write requirements.md from ${CLAUDE_PLUGIN_ROOT}/skills/the-loop/templates/requirements.md (${CLAUDE_PLUGIN_ROOT} = the installed plugin's root; same in Cursor): introduction, user stories, and EARS acceptance criteria (WHEN <event> THEN the system SHALL <response>), plus the Security considerations section (threat-model-lite: untrusted actors, trust boundaries, abuse cases, fail-closed — security.threatModel.required; "no new attack surface" is written and justified, see reference/security.md). Set front-matter phase: requirements-definition, status: draft, workItem: draft-<slug>, and the required collaborators.

Read the full file on GitHub · 58 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. 9d ago First seen · 58 lines · 27 tokens per session scan A 028567f53c18

Subscribe to this mod's changes

new-requirement is a command published in the GitHub repository MadaraUchiha-314/the-loop (4 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 800 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 2026-08-31.