agentmods.dev

create-design

create-design is a command for coding agents from MadaraUchiha-314/the-loop. It costs 21 tokens per session (745 once invoked), scanned A, original, MIT.

A command that creates a technical design document from approved requirements for a work item.

In plain words
What is it for?
Use it to document architecture, map requirements to components, describe data models and boundaries, and specify how the change should be tested.
Why use it?
It turns agreed needs into a concrete implementation plan before coding begins, including components, interfaces, data, errors, security, and testing strategy.

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 the-loop plugin — 2 skills, 37 commands, 2 hooks shipped together

not rated 4 today A scan 21 tokens original MIT
View the source file MadaraUchiha-314/the-loop
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/madarauchiha-314/the-loop/create-design
Clone the repo
git clone --depth 1 https://github.com/MadaraUchiha-314/the-loop

Or install the-loop, the plugin that ships this one along with the rest of its 2 skills, 37 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 create-design

README.md
[![agentmods](https://agentmods.dev/badge/commands/madarauchiha-314/the-loop/create-design.svg)](https://agentmods.dev/commands/madarauchiha-314/the-loop/create-design)
Your own site
<a href="https://agentmods.dev/commands/madarauchiha-314/the-loop/create-design"><img src="https://agentmods.dev/badge/commands/madarauchiha-314/the-loop/create-design.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 745 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 $0.00021 $0.00745
Opus 5 $0.00010 $0.00373
Sonnet 5 $0.00004 $0.00149
Haiku 4.5 $0.00002 $0.00075

Measured 4d ago against content hash 70ec8f4f9f56, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-design 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 4d 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/create-design.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

the-loop: create-design $ARGUMENTS

Produce the design for a work item from its approved requirements — Phase 2 of the spec chain. A slice of /the-loop:work-on; work-on remains the superset.

Read the the-loop skill and reference/workflow.md first. Load .the-loop/harness-config.yaml.

Steps

  1. Locate the spec. Resolve $ARGUMENTS to docs/specs/<id>/ and read requirements.md. It should be approved; if not, say so and stop (do not design ahead of approved requirements).

  2. Write design.md from ${CLAUDE_PLUGIN_ROOT}/skills/the-loop/templates/design.md (${CLAUDE_PLUGIN_ROOT} = the installed plugin's root; same in Cursor), derived from the requirements: overview, architecture, components/interfaces, data models, error handling, the testing strategy (a paragraph; the executable detail belongs to testing-plan.md), plus the Security design section — how each trust boundary from the requirements' Security considerations is enforced (security.design.required; a boundary left unenforced fails the gate, see reference/security.md). Map each requirement to a component. RULE: all diagrams are mermaid (config.userInteraction).

  3. Produce UI/UX design artifacts — if the work item has a user-facing surface. design.md (markdown + mermaid) captures architecture/HLD/LLD; visual UI/UX design is tracked as first-class artifacts under docs/specs/<id>/design/ (design.uiArtifacts.dir): self-contained HTML+CSS+JS prototypes (design.uiArtifacts.format: html, Claude-artifact style — inline CSS/JS, no external deps) and/or a linked Figma file. Fill in the UI/UX design inventory in design.md. Iterate each visual artifact with the designer persona until the designer is satisfied — review the rendered output, feedback as ticket comments, capture screenshots as evidence. (design.md itself is locked at the design-approval gate, never by the session — issue-281.) Skip this step (write N/A) for backend/CLI/infra work with no UI. Read reference/design-artifacts.md for the full pattern.

Read the full file on GitHub · 53 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. 4d ago First seen · 53 lines · 21 tokens per session scan A 70ec8f4f9f56

Subscribe to this mod's changes

create-design is a command published in the GitHub repository MadaraUchiha-314/the-loop (4 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 745 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.

Planningagentic-codingclaude-codeclaude-pluginclaude-skillscursorloop
Related

Other commands, from other repositories

gaai-audit

Show workspace audit log with filters and optional JSON export.

digipulse-engineering/GAAI-framework · 10 tokens

brainstorm

已弃用 - 请改用 superpowers:brainstorming 技能.

Leodorareluctant259/superpowers-zh · 15 tokens

execute-plan

已弃用 - 请改用 superpowers:executing-plans 技能.

Leodorareluctant259/superpowers-zh · 16 tokens

gaai-ask

Search workspace memory — ranked entries with 1-hop graph context (cognitive guarantee).

digipulse-engineering/GAAI-framework · 17 tokens

gaai-status

Show backlog, memory state & delivery readiness.

digipulse-engineering/GAAI-framework · 8 tokens

gaai-update

Update the GAAI framework or switch AI tool adapter.

digipulse-engineering/GAAI-framework · 11 tokens