new-requirement

new-requirement is a skill for Claude Code from HirogaKatageri/hirokata. It costs 144 tokens per session (8,727 once invoked), scanned A, original, MIT.

A guided process for adding a new feature or work item to a Guild project. It interviews you about the need, then creates the requirement, implementation plan, and related tasks.

In plain words
What is it for?
Use it to queue a feature, define acceptance criteria, plan its implementation, and create developer, test-planning, and review tasks.
Why use it?
It turns an idea into organized development work with agreed requirements and planned responsibilities.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: reads .claude/ paths; mentions subagents; names the AskUserQuestion tool.

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 guild plugin — 21 skills, 15 agents shipped together

Good fit Use it to queue a feature, define acceptance criteria, plan its implementation, and create developer, test-planning, and review tasks.

Compare 6 skills 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 HirogaKatageri/hirokata
Claude Code
/plugin install guild

Made for: Claude Code.

Or install guild, the plugin that ships this one along with the rest of its 21 skills, 15 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-requirement

README.md
[![agentmods](https://agentmods.dev/badge/skills/hirogakatageri/hirokata/new-requirement/github.svg)](https://agentmods.dev/skills/hirogakatageri/hirokata/new-requirement)
Your own site
<a href="https://agentmods.dev/skills/hirogakatageri/hirokata/new-requirement"><img src="https://agentmods.dev/badge/skills/hirogakatageri/hirokata/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/skills/hirogakatageri/hirokata/new-requirement"><img src="https://agentmods.dev/badge/skills/hirogakatageri/hirokata/new-requirement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 144 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,727 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 $0.00144 $0.08727
Opus 5 $0.00072 $0.04364
Sonnet 5 $0.00029 $0.01745
Haiku 4.5 $0.00014 $0.00873

Measured 2d ago against content hash c674fdc78725, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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 2d 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.

plugins/guild/skills/new-requirement/SKILL.md · 646 lines

How it starts

The opening of the file, as written. The whole thing — 646 lines — stays where its author put it; the contents beside it link to each section on GitHub.

New Requirement — Add Work to the Guild

Run the project-manager and strategist through a live interview with the user, then hand the board a fully-planned requirement: the requirement itself, an implementation plan, every ticket needed to build it, and the execution graph that says what runs when. Unlike the rest of the guild's pipeline, none of this is ticket-dispatched — you (the orchestrator) spawn both agents directly and moderate the conversation until the user says it's done.

Load guild:warehouse first. There is no guild CLI: tursodb is the tool and every write below is SQL. The canonical statements — creating a requirement, a plan, a ticket with its capabilities, instantiating a graph — are in references/queries.md; copy from there rather than improvising.

Where this skill stops: gate-plan

This skill plans. It does not build. It ends by presenting the plan at gate-plan — the first of the guild's two gates, and the whole point of the gate model:

The plan is the cheapest place to change your mind. Approving it costs one decision and redirects everything downstream. After that, the guild runs to completion without stopping, and the problems it finds are collected and judged together at gate-repairs.

So the last thing you do here is put the plan in front of the guild master and record their answer (Step 7). Nothing is dispatched, nothing is implemented, no ticket leaves todo until that approval exists. If they approve, /guild:check-in runs the first batch. If they don't, the requirement sits with a pending gate and the board is unchanged — which is exactly what a plan gate is for.

Only you can ask. Subagents cannot call AskUserQuestion, which is why a gate can never live inside a dispatched workflow and why this skill — the orchestrator session — is where it happens.

Arguments

Argument Description
title Short title for the requirement (e.g., "User Authentication")
description Brief description of what's needed

Read the full file on GitHub · 646 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. 2d ago Changed c674fdc78725
  2. 3d ago Changed · +5 lines d4959230dc25
  3. 7d ago Changed · +426 lines · +35 tokens per session b153a0aef104
  4. 11d ago First seen · 215 lines · 109 tokens per session scan A 8d9677a76432

Subscribe to this mod's changes

new-requirement is a skill published in the GitHub repository HirogaKatageri/hirokata (5 stars, last pushed 3d ago), licensed MIT. It adds 144 tokens to every session and 8,727 once invoked, about $0.0007 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.