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.
npx skills add pivoshenko/pivoshenko.ai --skill pivoshenko-brandgit clone --depth 1 https://github.com/pivoshenko/pivoshenko.aiWrote 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.
[](https://agentmods.dev/skills/pivoshenko/pivoshenko.ai/pivoshenko-brand)<a href="https://agentmods.dev/skills/pivoshenko/pivoshenko.ai/pivoshenko-brand"><img src="https://agentmods.dev/badge/skills/pivoshenko/pivoshenko.ai/pivoshenko-brand/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.
<a href="https://agentmods.dev/skills/pivoshenko/pivoshenko.ai/pivoshenko-brand"><img src="https://agentmods.dev/badge/skills/pivoshenko/pivoshenko.ai/pivoshenko-brand.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00144 | $0.03678 |
| Opus 5 | $0.00072 | $0.01839 |
| Sonnet 5 | $0.00029 | $0.00736 |
| Haiku 4.5 | $0.00014 | $0.00368 |
Grade A, and why
pivoshenko-brand 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pivoshenko-brand
What pivoshenko Is
pivoshenko is the practitioner's notebook — a dark, monospaced workshop where an engineer thinks out loud.
Every rule below descends from that sentence. If a future decision doesn't fit it, the decision is out — not the sentence. Read this line as the brand's positioning, not its tagline; it's the test, not the marketing.
The skill is organized in two layers:
- DNA — identity decisions that hold across every substrate (web, print, video, audio, physical). These don't change when you port to a new medium.
- Expression — how DNA gets rendered in this substrate (CSS tokens, hex values, pixel sizes, motion timings). These change per substrate; the DNA above them does not.
When porting to a substrate this skill doesn't enumerate, hold the DNA fixed and re-derive the expression. The Porting to a new substrate section below gives the rubric.
Files
SKILL.md is the entry point. Open references only when the task calls for them — keeps context lean.
One rule for the tree: everything under preview/ is rendered HTML for a human to look at; everything else is for you to read. The component cards are the exception worth reaching for — lift their markup instead of reinventing a component.
colors_and_type.css— drop-in role tokens (CSS vars asR G Btriples) + utility classes + 8type-*recipes. Link or inline for any web prototype.assets/logo-vp.svg— canonicalVPtile (32×32, 4px radius, light fill, dark glyph). The only mark.assets/social/{github,linkedin,rss}.svg— Simple Icons brand marks (footer use only).assets/templates/— drop-in artifact skeletons. Start here for any one-shot output — copy, fill placeholders, don't rebuild from scratch:page.html— generic dark page (header + content + footer). Use for one-pagers, mocks, posters.document.html— print-tuned (A4,@page, page-break hygiene). Render to PDF via headless Chrome.og-card.html— 1200×630 social/OG card. Hex inlined because@vercel/ogand most screenshotters don't resolve CSS variables.
references/voice.md— content fundamentals: rhythm, casing, microcopy, refuse-list, smell test. Read when writing copy (post, README, social, email).references/visual.md— deep rationale for color + typography choices (origin / substitution / extension) and long-form spacing/border/layout rules. Read when extending the palette, porting to a substrate without JetBrains Mono, or auditing a layout.references/iconography.md— Lucide / Simple Icons / VP-mark rules. Read when placing icons, building a logo lockup, or making a favicon / OG mark.references/anti-patterns.md— do/don't pairs per DNA rule. Read when a rule feels ambiguous, or when you've drifted and want to diagnose why.preview/*.html— per-recipe component cards. Lift markup from these; read on demand:colors-*— palette + accent usagetype-*— type recipes + foreground ladderspacing-*— scale, borders, cornerscomponents-*— card, button, tag, alert, code, chrome, menu, search, tabs, status, form-inputs, palette-table
preview/index.html,preview/components.html— the two hub pages that frame the cards above for a human browsing them. Open one for the user when they want to see the system; they carry no rule you can't get from this file.
What ships with it
38 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/logo-vp.svg 384 B
- assets/social/github.svg 839 B
- assets/social/linkedin.svg 564 B
- assets/social/rss.svg 411 B
- assets/templates/document.html 3.3 KB
- assets/templates/og-card.html 2.5 KB
- assets/templates/page.html 2.2 KB
- colors_and_type.css 9.9 KB
- preview/_base.css 924 B
- preview/brand-iconography.html 6.0 KB
- preview/brand-logo.html 1.5 KB
- preview/brand-voice.html 1.5 KB
- preview/colors-accent-in-chrome.html 3.5 KB
- preview/colors-accents.html 2.1 KB
- preview/colors-stone.html 2.6 KB
- preview/colors-surfaces.html 3.4 KB
- preview/components-alerts.html 3.5 KB
- preview/components-buttons.html 5.3 KB
- preview/components-card.html 1.5 KB
- preview/components-chrome.html 3.3 KB
- preview/components-code.html 2.8 KB
- preview/components-form-inputs.html 4.1 KB
- preview/components-menus.html 3.2 KB
- preview/components-palette-table.html 3.6 KB
- preview/components-search.html 6.7 KB
- preview/components-status.html 3.3 KB
- preview/components-tabs.html 2.7 KB
- preview/components-tags.html 1.5 KB
- preview/components.html 15 KB
- preview/index.html 6.4 KB
- preview/spacing-borders-corners.html 2.2 KB
- preview/spacing-scale.html 1.8 KB
- preview/type-foreground-ladder.html 1.8 KB
- preview/type-recipes.html 1.5 KB
- references/anti-patterns.md 7.6 KB
- references/iconography.md 2.6 KB
- references/visual.md 12 KB
- references/voice.md 3.7 KB
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.
- today Changed f0d4c39ec136
- 6d ago Changed · +2 lines 5383025d2da7
- 11d ago First seen · 171 lines · 144 tokens per session scan A 3449a0c97cc6
pivoshenko-brand is a skill published in the GitHub repository pivoshenko/pivoshenko.ai (4 stars, last pushed yesterday), licensed MIT. It adds 144 tokens to every session and 3,678 once invoked, about $0.0007 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.
Other skills, from other repositories
paperclip-capsules
Generate, implement, or review Paperclip capsule visuals. Use for capsule art, agent capsules, heartbeat status capsules, identicons, capsule banks, or brand-usage validation.
80-livekit-agents-majiayu000-claude-skill-registr
Create your LiveKit Agents skill from official documentation, then learn to improve it throughout the chapter.
agent-creation-skill
Procedural guide for creating new agents from templates when project complexity requires delegation.
agent-eyes
Visual context analyzer for AI agents. Provides screenshots, accessibility scans, DOM snapshots, and element descriptions for web pages. Use when you need to see what a web page looks like, analyze accessibility issues, inspect DOM structure, or get detailed element information. Triggers on requests like "take a…
agent-creator
Meta-agent for creating new custom agents, skills, and MCP integrations. Expert in agent design, MCP development, skill architecture, and rapid prototyping. Activate on 'create agent', 'new skill', 'MCP server', 'custom tool', 'agent design'. NOT for using existing agents (invoke them directly), general coding (use…
agent-canvas-setup
Dependency checker and installer for agent-canvas, agent-eyes, and canvas-edit skills. Use BEFORE running any canvas skill for the first time, or when canvas skills fail with import/browser errors. Triggers on "setup agent canvas", "install canvas dependencies", "canvas not working", "playwright not found", or any…