agentmods.dev

tell-proof: Skill for Cursor

.cursor/skills/agency-quality-site/SKILL.md

agency-quality-site is a skill for Cursor from ashishpatill/tell-proof. It costs 50 tokens per session (827 once invoked), scanned A, original, MIT.

A phased process for building agency-quality marketing websites, from gathering references and planning through typography, spacing, motion, mobile layouts, and launch.

In plain words
What is it for?
Use it to run a full marketing-site pipeline or complete one design phase at a time, with status checks and automatic learning.
Why use it?
It breaks a large website build into reviewable stages and records lessons from completed work.

Skill for Cursor

Written for Cursor: installed under .cursor/.

This is ashishpatill/tell-proof's own configuration. It tells Cursor how to work on tell-proof itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything tell-proof configures →

not rated 2repo 22d ago A scan 50 tokens original MIT
View source ↗ ashishpatill/tell-proof tell-proof.vercel.app
Reuse

Borrowing it

Nothing to install: this file belongs to ashishpatill/tell-proof. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ashishpatill/tell-proof/master/.cursor/skills/agency-quality-site/SKILL.md
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 agency-quality-site

README.md
[![agentmods](https://agentmods.dev/badge/skills/ashishpatill/tell-proof/agency-quality-site/github.svg)](https://agentmods.dev/skills/ashishpatill/tell-proof/agency-quality-site)
Your own site
<a href="https://agentmods.dev/skills/ashishpatill/tell-proof/agency-quality-site"><img src="https://agentmods.dev/badge/skills/ashishpatill/tell-proof/agency-quality-site/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 agency-quality-site

Your own site · 80×15
<a href="https://agentmods.dev/skills/ashishpatill/tell-proof/agency-quality-site"><img src="https://agentmods.dev/badge/skills/ashishpatill/tell-proof/agency-quality-site.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 827 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 $0.00050 $0.00827
Opus 5.5 $0.00020 $0.00331
Sonnet 5.5 $0.00010 $0.00165
Haiku 4.5 $0.00005 $0.00083

Measured 1mo ago against content hash 822d5c08a227, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agency-quality-site 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 1mo 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/skills/agency-quality-site/SKILL.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agency-quality-site

Full playbook: agent-skills/web-design/premium-content-custom-web/agency-quality-site/SKILL.md
Copy/paste prompts: …/agency-quality-site/PROMPTS.md
Design rigor: …/agency-quality-site/DESIGN_RIGOR.md
Learn (automatic): .cursor/skills/agency-run-learn · research/design-data.README.md

Quick contract

  1. Autonomous: pnpm agency:run -- --query "…" --fresh — ends with automatic agency:learn + media:site (WebP)
  2. Manual craft: one phase per cycle — Goal → run → eye → Loop ≤3 → --mark-pass → next (4-ship mark-pass also auto-learns and runs media:site)
  3. Phases: 1-refs → 2-build → 3a-typography → 3b-spacing → 3c-motion → 3d-mobile → 4-ship
  4. Each phase starts from current.html of the last passed phase.
  5. Phase 0 reads DESIGN_RIGOR.md — lane + craft nodes (auto-filled by agency:run; craftNodes land on the brief and merge into engine routedSkills).
  6. Never combine axes. Never craft --all.
  7. Status: pnpm agency:pipeline -- --brief <brief> --status
  8. Learn is automatic on agency runs (agency-run-learn) — developer corpus only when design-data pointer is set.
  9. User sessions learn separately in the browser (tell-user-session-learn) — never via design-data checkout.
  10. Personal corpus (dev): TELL_DESIGN_DATA + TELL_DEV_CORPUS=1 or research/design-data.local.json.
  11. Media performance is automatic — responsive-performance is always routed; pnpm media:site runs at end of agency:run and on agency:pipeline --mark-pass 4-ship. Specimen UIs use SiteImg.
  12. Research gate is automatic on every template — designFromFeatures attaches researchPlan (LoadPrior → gap → sport-site-research when sport → IA → training) and merges followOnCraft into routedSkills.
  13. Skill wiring is a hard gate — assertSkillWiring (via assertBasics) + agency 2-build artifacts RESEARCH_GATE.md / SKILL_WIRING.json. Phase fails if research/craft/optim wiring is red.

Read the full file on GitHub · 52 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. 1mo ago First seen · 52 lines · 50 tokens per session scan A 822d5c08a227

Subscribe to this mod's changes

agency-quality-site is a skill published in the GitHub repository ashishpatill/tell-proof (2 stars, last pushed 22d ago), licensed MIT. It adds 50 tokens to every session and 827 once invoked, about $0.0002 per session on Opus 5.5. 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.

FrontendMarketing and SEOPlanningaicursordesign-systemsdeveloper-toolshackathon
Related

Other skills, from other repositories

vfx-text-cursor

Cursor light trail, chromatic rays, and directional flares for word-by-word quote reveals in video intros.

nexu-io/open-design · 28 tokens

animate-text

Curated text animation catalog with exact JSON specs for headings, labels, counters, and text swaps. Use when an agent needs to pick or translate named effects like soft blur in, typewriter, shared axis, line reveal, stagger, crossfade, or kinetic builds into WAAPI, Motion, Framer Motion, GSAP, CSS, Lottie, Rive, or…

marvkr/better-design · 81 tokens

better-design

Build, improve, and review production interfaces with the Better Design MCP. Use for frontend design, UI, UX, interactions, flows, forms, navigation, components, styling, design systems, accessibility, responsive layouts, motion, React Native, Expo, Shopify, Three.js, and product video work, especially when creating…

marvkr/better-design · 77 tokens

orchestrate

START HERE for HackerRank Orchestrate. Master plan for the 24-hour challenge - scoring targets, the phase order, which orchestrate- skill to run next, what to do when a step fails, and the transcript discipline that applies all day. Use at the start of the challenge, whenever you are unsure what to do next, or when…

NITISH-R-G/hackerrank-orchestrate-skills · 77 tokens

orchestrate-score

Estimate the Orchestrate score the way HackerRank weights it - four signals (Code ZIP 30%, Output CSV 30%, AI Interview 30%, Chat Transcript 10%) with the published sub-weights. Uses the kit's scoring module as a heuristic and clearly separates measured facts from estimates. Use before submission, after each…

NITISH-R-G/hackerrank-orchestrate-skills · 82 tokens

orchestrate-build

Orchestrate phases 1 and 2 - turn the problem statement into a written design (DESIGN.md) and then build the agent so it runs end to end on the sample with validation, failure handling and secrets handled. Use after reading the problem statement and sample data, and until the pipeline writes a valid CSV for the whole…

NITISH-R-G/hackerrank-orchestrate-skills · 74 tokens