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 agentmods add instructions/wyverncw/monich/claude-mdgit clone --depth 1 https://github.com/WyvernCW/MonichWrote 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/wyverncw/monich/claude-md)<a href="https://agentmods.dev/instructions/wyverncw/monich/claude-md"><img src="https://agentmods.dev/badge/instructions/wyverncw/monich/claude-md.svg" alt="Measured on agentmods" 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 | $0.00618 | $0.00618 |
| Opus 5 | $0.00309 | $0.00309 |
| Sonnet 5 | $0.00124 | $0.00124 |
| Haiku 4.5 | $0.00062 | $0.00062 |
Grade A, and why
Monich CLAUDE.md 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Project Memory
This repository contains a reusable portable skill named monich.
At the start of any task involving scroll websites, sticky product stories, parallax pages, pinned reveals, Raycast-like app pages, Apple-like product showcases, NVIDIA-like technical reveals, GPU showcases, AI browser landing pages, or premium animated SaaS pages, read:
skills/monich/SKILL.md
Use progressive disclosure, but always read and recursively scan the available templates/ folder before choosing references. Do not stop at top-level README files or jump directly into one starter template.
Template Selection
- Default to React for generated websites unless the user asks for another stack.
- Start by recursively scanning
templates/so the available template families are known. - If present, scan every folder and file inside
templates/web-template/design-templates/,templates/web-template/horizontal-craft/, andtemplates/web-template/design-systems/. - Read actual source/reference files inside every template/reference folder, including
.html,.css,.js,.jsx,.tsx,.md,.json, and design-token files. Do not rely only onSKILL.md,README.md,info.md, or folder names. - Build an inventory of template names, metadata, visual style, page type, layout pattern, motion pattern, component language, color system, typography, and stack.
- For broad or style-sensitive requests, show the user 2-4 closest template references with a short rationale before implementation.
- Choose the closest matching template or reference set only after that scan.
- For Next.js requests or existing Next.js projects, adapt discovered template patterns into the app-router or pages-router structure already in the project.
- For Astro, SvelteKit, Vue, Nuxt, or other stacks, preserve the Monich scroll architecture and translate the component patterns into the requested framework.
Working Rules
- Generate runnable code, not advice-only responses.
- Do not invent missing image assets.
- Do not copy brand assets, names, logos, screenshots, exact layouts, or marketing text.
- Prefer CSS mockups when no assets are provided.
- Learn and adapt from templates; do not copy-paste template code line-by-line into the generated project.
- Use templates to extract layout strategy, visual rhythm, motion timing, spacing, and interaction intent, then write fresh code for the target stack.
- Do not default back to starter-template visuals after reading
web-templatereferences. - When generating React or Next.js, translate the chosen
web-templatestyle into React/Next.js components instead of recreating the starter-template UI. - Animate transform and opacity.
- Include responsive CSS and a reduced-motion fallback.
- Match visible copy to the language the user spoke. The web-template pack contains Chinese-first examples, but generated pages should not stay Chinese unless the user requests Chinese.
- Set
<html lang>or framework metadata to the generated content language. - Verify imports, package dependencies, and build commands before claiming completion.
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.
- 6d ago First seen · 38 lines · 618 tokens per session scan A fa859edfdaaf
Monich CLAUDE.md is an instructions file published in the GitHub repository WyvernCW/Monich (3 stars, last pushed 2mo ago), licensed MIT. It adds 618 tokens to every session, about $0.0031 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 instructions, from other repositories
aeon CLAUDE.md
Claude Code instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
cognirepo CLAUDE.md
Claude Code instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).
wayland-core copilot-instructions.md
Copilot instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.
mcp-structured-memory CLAUDE.md
Claude Code instructions for nmeierpolys/mcp-structured-memory, a project described as: Structured Memory MCP Server.
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
RNR-Enhanced-Cognee AGENTS.md
AGENTS.md instructions for vincentspereira/RNR-Enhanced-Cognee, covering rnr enhanced cognee implementation for codex, critical requirements, 1. ascii-only output (no unicode encoding), 2. dynamic categories (no hardcoded categories) and 3. standard memory mcp interface.