fixture-smith

fixture-smith is an agent for Cursor from ashishpatill/tell-proof. It costs 38 tokens per session (343 once invoked), scanned A, original, MIT.

An instruction for building a deliberately generic demo website in a small Next.js app. It is designed to expose common visual problems that a design-checking tool can detect.

In plain words
What is it for?
Use it to create the fixtures/generic-app demo, run it with pnpm dev:fixture, and include an intentionally different brutalist page for comparison.
Why use it?
It provides a controlled example for testing whether those detectors identify repetitive fonts, colors, spacing, buttons, and layouts.

Agent for Cursor

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 agents/ashishpatill/tell-proof/fixture-smith
Clone the repo
git clone --depth 1 https://github.com/ashishpatill/tell-proof

Made for: Cursor.

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 fixture-smith

README.md
[![agentmods](https://agentmods.dev/badge/agents/ashishpatill/tell-proof/fixture-smith.svg)](https://agentmods.dev/agents/ashishpatill/tell-proof/fixture-smith)
Your own site
<a href="https://agentmods.dev/agents/ashishpatill/tell-proof/fixture-smith"><img src="https://agentmods.dev/badge/agents/ashishpatill/tell-proof/fixture-smith.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 343 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 $0.00038 $0.00343
Opus 5 $0.00019 $0.00171
Sonnet 5 $0.00008 $0.00069
Haiku 4.5 $0.00004 $0.00034

Measured 3d ago against content hash 80f602e268b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fixture-smith 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 3d 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.

.cursor/agents/fixture-smith.md · 34 lines

What it actually says

You build Ashish's embarrassing landing page — the demo "before."

Scope

  • fixtures/generic-app — small Next.js app, port 3001

Must trigger (BUILD.md §7)

  1. Inter/system-ui everywhere → SystemFontTell
  2. Violet→pink hero gradient → GradientCrutchTell
  3. shadow-lg on every card → ShadowEverywhereTell
  4. 8px radius everywhere → RadiusMonotoneTell
  5. #8B5CF6 on #0F0F0F → AcidAccentTell
  6. Emoji in nav/buttons (🚀 ✨ 📊) → EmojiChromeTell
  7. text-align center on all sections → CenteredEverythingTell
  8. Six near-identical grays → GrayMushTell
  9. Near-duplicate bg colors → NearDuplicateValues
  10. Half buttons missing focus ring → FocusRingInconsistency
  11. Random font sizes → TypeScaleDrift
  12. Off-grid padding → SpacingChaos
  13. /brutalist route with intentional mono → taste returns intentional

Label

Add banner: "Demo input — deliberately generic. Not Tell's UI."

DoD

  • Runs on pnpm dev:fixture
  • Looks embarrassingly like every AI-built SaaS (that's the point)
  • CONTRIBUTIONS.md lists this as demo input, not original work
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. 3d ago First seen · 34 lines · 38 tokens per session scan A 80f602e268b6

Subscribe to this mod's changes

fixture-smith is an agent published in the GitHub repository ashishpatill/tell-proof (1 stars, last pushed 8d ago), licensed MIT. It adds 38 tokens to every session and 343 once invoked, about $0.0002 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.