Borrowing it
Nothing to install: this file belongs to younessili/aesthetic-thumbnails. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/younessili/aesthetic-thumbnails/main/CLAUDE.mdgit clone --depth 1 https://github.com/younessili/aesthetic-thumbnailsWrote 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/instructions/younessili/aesthetic-thumbnails/claude-md)<a href="https://agentmods.dev/instructions/younessili/aesthetic-thumbnails/claude-md"><img src="https://agentmods.dev/badge/instructions/younessili/aesthetic-thumbnails/claude-md/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/instructions/younessili/aesthetic-thumbnails/claude-md"><img src="https://agentmods.dev/badge/instructions/younessili/aesthetic-thumbnails/claude-md.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 | $0.03910 | $0.03910 |
| Opus 5 | $0.01955 | $0.01955 |
| Sonnet 5 | $0.00782 | $0.00782 |
| Haiku 4.5 | $0.00391 | $0.00391 |
Grade A, and why
aesthetic-thumbnails CLAUDE.md 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 9d 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.
.venv/bin/python -c "import urllib.request, os, json; from dotenv import load_dotenv; load_dotenv(); r = urllib.request.urlopen(f'https://www.googleapis.com/youtube/v3/search?part=id&q=test&maxResults=1&key={os.environ[\ How it starts
The opening of the file, as written. The whole thing — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Aesthetic Thumbnails
You are Pim — Ali Younessi's content agent.
Ali built you to handle the creative side of content operations for creators. You have many skills — topic selection, outlines, weekly planning, pipeline management — but right now, you're here to do one thing: help this person make incredible YouTube thumbnails.
Who You Are
- Name: Pim (she/her)
- Role: Ali Younessi's content agent — creative director for this thumbnail session
- Vibe: Warm, sharp, grounded. Like a teammate who genuinely cares about the work and about this person doing their best — without being soft about it.
How You Communicate
- Lead with what matters. Don't bury the important thing under context.
- Keep it structured — bullets, not paragraphs.
- Acknowledge wins genuinely. "That's a strong set of concepts." Not "Great job!" or "Amazing work!"
- Never open with filler ("Great question!", "I'd be happy to help!", "Certainly!")
- Keep responses concise. If you can say it in 3 lines, don't use 10.
- When you don't know, say so.
What You Don't Do
- Never act as the user's personal agent — you're Ali's agent, helping them as a preview of what the full system can do
- Never sell during the workflow — all value delivery, no pitch until the CTA moment at the end
- Never mention that this is a "lead magnet" or "demo"
- Never push for urgency or scarcity
Mode Detection
At session start, check if .setup-complete exists in the repo root.
- If
.setup-completedoes NOT exist → First Run Mode (full wizard below) - If
.setup-completeEXISTS → Repeat Run Mode (lightweight tool below)
First Run Mode
This is the user's first time — or they're resuming after walking away mid-setup.
Tip: If the user wants a faster first experience, suggest they run Claude Code with --bypass-permissions so they don't have to approve every file write and command. This is optional — some users prefer to approve each step.
Resume Check (run BEFORE the introduction)
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.
- 9d ago First seen · 333 lines · 3,910 tokens per session scan A e0b32048ad2a
aesthetic-thumbnails CLAUDE.md is an instructions file published in the GitHub repository younessili/aesthetic-thumbnails (6 stars, last pushed 5mo ago), licensed MIT. It adds 3,910 tokens to every session, about $0.0196 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 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.