design

design is a command for coding agents from koolamusic/claudefiles. It costs 57 tokens per session (3,163 once invoked), scanned A, original, MIT.

A guided command for designing Warden acceptance plans, which are checks that verify a project's required behavior. It gathers a specification from existing planning material or from questions asked during the session.

In plain words
What is it for?
Use it to create plans for supported Node.js or Go backends, authentication, PostgreSQL database checks, and browser-based UI checks. It can start from free text, a GitHub issue, or an existing plan.
Why use it?
It turns an incomplete idea or existing issue into a clear, testable plan. It also creates the initial `.warden/` setup when the project has not been bootstrapped.

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 warden plugin — 5 commands 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/koolamusic/claudefiles/design
Clone the repo
git clone --depth 1 https://github.com/koolamusic/claudefiles

Or install warden, the plugin that ships this one along with the rest of its 5 commands.

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 design

README.md
[![agentmods](https://agentmods.dev/badge/commands/koolamusic/claudefiles/design.svg)](https://agentmods.dev/commands/koolamusic/claudefiles/design)
Your own site
<a href="https://agentmods.dev/commands/koolamusic/claudefiles/design"><img src="https://agentmods.dev/badge/commands/koolamusic/claudefiles/design.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,163 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00057 $0.03163
Opus 5 $0.00028 $0.01581
Sonnet 5 $0.00011 $0.00633
Haiku 4.5 $0.00006 $0.00316

Measured 4d ago against content hash a0c0e34abd66, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

design scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| HTTP endpoint contract (status, headers, JSON shape) | `hurl` when fixture-heavy, else `bash` + curl via `lib/api.sh` |
plugins/warden/commands/design.md · 234 lines

How it starts

The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design a warden acceptance plan for the current project. The command's job is to converge on a clear, testable spec, then write a plan that verifies it. Spec gathering is the load-bearing step; do not skip past it.

Supported scope. Node.js and Go backends with cookie-session (better-auth shape) or JWT bearer auth; Postgres for database assertions; agent-browser for UI; macOS and Linux dev machines. Other stacks may work via the custom auth strategy and skipping unused libs, but are not first-class.

Parse the input

$ARGUMENTS:

  • A free-text spec describing what to verify. Used as a starting point for the converge loop.
  • --issue N: pull the spec from GitHub issue N (gh issue view N --json title,body). Counts as a planning artifact.
  • --from-plan <path>: model the new plan on an existing one. Counts as a planning artifact.
  • --source auto: skip the source-picker and use whichever planning artifact ranks first (see "Detect planning artifacts" below).
  • --source interactive: skip the source-picker and force interactive Q&A.

Empty $ARGUMENTS is fine. Spec gathering will proceed from interactive Q&A.

Mode: detect

WARDEN_DIR=".warden"
if [ -d "$WARDEN_DIR" ]; then MODE=plan; else MODE=first-run; fi

Stage 1: bootstrap (first-run only)

.warden/ does not exist. Run the bootstrap once. The first plan is written in Stage 3 below.

1.1 Detect tech stack and auth strategy

Inspect (use Read for known paths, Glob/Grep tight scope; no whole-file reads):

  • package.json deps (better-auth, next-auth, lucia, passport, jose, jsonwebtoken, @clerk/, @auth0/)
  • pyproject.toml, requirements.txt, Pipfile
  • Cargo.toml, go.mod
  • .env, .env.example, backend/.env, backend/.env.example, <service>/.env* for any workspace package
  • openapi.json / openapi.yaml securitySchemes

Grep targets:

  • Set-Cookie, cookies.set, res.cookie → cookie-session
  • Authorization: Bearer, verify_jwt, jwt.sign → jwt-bearer
  • X-API-Key, process.env.API_KEY → api-key
  • @UseGuards, @requires_auth, [Authorize] → role-based; multi-identity is likely needed
  • Auth-shaped env vars: BETTER_AUTH_SECRET, NEXTAUTH_SECRET, JWT_SECRET, JWT_PRIVATE_KEY, SESSION_SECRET, COOKIE_DOMAIN, AUTH_API_KEY

Read the full file on GitHub · 234 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 · 234 lines · 57 tokens per session scan A a0c0e34abd66

Subscribe to this mod's changes

design is a command published in the GitHub repository koolamusic/claudefiles (132 stars, last pushed 5d ago), licensed MIT. It adds 57 tokens to every session and 3,163 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.