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/thedecipherist/classmcp/claude-mdgit clone --depth 1 https://github.com/TheDecipherist/classmcpWrote 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/thedecipherist/classmcp/claude-md)<a href="https://agentmods.dev/instructions/thedecipherist/classmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/thedecipherist/classmcp/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 | $0.00720 | $0.00720 |
| Opus 5 | $0.00360 | $0.00360 |
| Sonnet 5 | $0.00144 | $0.00144 |
| Haiku 4.5 | $0.00072 | $0.00072 |
Grade A, and why
classmcp 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 4d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
classmcp is an MCP (Model Context Protocol) server that provides semantic CSS class patterns optimized for AI code generation. It maps short semantic class names (like btn-primary) to full utility class strings, reducing token usage and improving code readability. Supports Tailwind CSS, Bootstrap 5, UnoCSS, and Tachyons.
Git Workflow
IMPORTANT: Always keep CHANGELOG.md in sync before pushing to git.
When making changes that affect functionality:
- Update
CHANGELOG.mdunder the appropriate version section - Use Keep a Changelog format (Added, Changed, Fixed, Removed)
- Then commit and push
Commands
# Build TypeScript to dist/
npm run build
# Watch mode for development
npm run dev
# Run the MCP server
npm start
# Type check without emitting
npm run typecheck
Architecture
Entry Point
src/index.ts - MCP server setup using @modelcontextprotocol/sdk. Defines 8 tools (set_framework, get_class, list_classes, search_classes, generate_css, get_component, get_ssr_info, list_frameworks) and resource handlers. Maintains currentFramework state (defaults to 'tailwind').
Core Modules
Framework System (src/frameworks/)
index.ts- Framework registry with utilities:getPatterns(),getPattern(),resolveClasses(),generateCSS(),isSSRSafe()tailwind.ts,bootstrap.ts,unocss.ts,tachyons.ts- Framework-specific configs and pattern definitions- Each framework exports a
FrameworkConfigand array ofComponentPatternobjects
Type System (src/types.ts)
ComponentPattern- Main pattern type withid,name,classes(string orStateVariant),category,ssrsafety infoStateVariant- Object withbase,hover,focus,active,disabledstate classesMinificationMap- Tracks semantic-to-minified class name mappings
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.
- 4d ago First seen · 69 lines · 720 tokens per session scan A 548682dfa55a
classmcp CLAUDE.md is an instructions file published in the GitHub repository TheDecipherist/classmcp (6 stars, last pushed 7mo ago), licensed MIT. It adds 720 tokens to every session, about $0.0036 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
vibe-driven-dev AGENTS.md
AGENTS.md instructions for Gladisintelligible706/vibe-driven-dev, covering agents.md — vibe driven dev, what vdd is, official source of truth, your job as a coding agent and installation behavior.
vibe-driven-dev AGENTS.md
AGENTS.md instructions for OpenOps-Studio/vibe-driven-dev, covering agents.md — vibe driven dev, what vdd is, official source of truth, your job as a coding agent and installation behavior.
hiveshare CLAUDE.md
Instructions for KB-perByte/hiveshare, covering hiveshare — claude.md, repo layout, build & run, key env vars (server) and naming: hive vs memory.
llm-safe-haven CLAUDE.md
Claude Code instructions for pleasedodisturb/llm-safe-haven, covering llm safe haven, what this is, project structure, tdd — non-negotiable (adopted 2026-08-17) and the contract.
kleosrules AGENTS.md
Instructions for kleosr/kleosrules, a project described as: Cursor harness pack: user rules, skills, Bash hooks, local HANDOFF memory. macOS, Linux, Windows (WSL).
finding-unknowns-skills CLAUDE.md
Claude Code instructions for Neeeophytee/finding-unknowns-skills, covering repo notes, what ships, and the gate that decides, version lives in three manifests — move them together, files that must be edited together and shipped guidance is not this file.