reference

A command for finding real website examples that match a design brief. It searches A1 Gallery, a collection of website designs, for full sites or specific sections such as heroes and pricing tables.

In plain words
What is it for?
Finding five or six suitable website references, their live URLs, and the specific design detail each one matches.
Why use it?
It turns a vague visual request into gallery search terms and returns concrete references that can guide the design work.

Command

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/bryntay/a1-mcp/reference
Clone the repo
git clone --depth 1 https://github.com/bryntay/a1-mcp
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 169 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 $0.00010 $0.00169
Opus 5 $0.00005 $0.00084
Sonnet 5 $0.00002 $0.00034
Haiku 4.5 $0.00001 $0.00017

Measured yesterday against content hash caa4ca6ef446, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reference 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 yesterday.

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/reference.md · 19 lines

What it actually says

Find reference in A1 Gallery for: $ARGUMENTS

Run the search, then report back:

  1. Rephrase the brief in the gallery's taxonomy terms and call search_websites. If the brief names a section rather than a whole site — a hero, a pricing table — use search_sections instead.
  2. Return five or six matches. For each, give the site name, its live URL, and the one thing that makes it a match for this brief. Not a list of its tags.
  3. If the response carries broadenedSearch, say which terms were dropped and that the matches are looser than asked for.

Skip the preamble. Lead with the matches.

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. yesterday First seen · 19 lines · 10 tokens per session scan A caa4ca6ef446

Subscribe to this mod's changes

reference is a command published in the GitHub repository bryntay/a1-mcp (1 stars, last pushed 5d ago), licensed MIT. It adds 10 tokens to every session and 169 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.