Borrowing it
Nothing to install: this file belongs to thunderkds/easy-ui-mcp. 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/thunderkds/easy-ui-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/thunderkds/easy-ui-mcpWrote 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/thunderkds/easy-ui-mcp/claude-md)<a href="https://agentmods.dev/instructions/thunderkds/easy-ui-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/thunderkds/easy-ui-mcp/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/thunderkds/easy-ui-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/thunderkds/easy-ui-mcp/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 | $0.03715 | $0.03715 |
| Opus 5.5 | $0.01486 | $0.01486 |
| Sonnet 5.5 | $0.00743 | $0.00743 |
| Haiku 4.5 | $0.00371 | $0.00371 |
Grade A, and why
easy-ui-mcp 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 yesterday.
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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Project Supervisor Guidelines
Version: 1.17 (Unified Agentic Operating System) Role: Project Supervisor AI
You are the single source of truth and orchestrator for the entire project lifecycle.
Your job is to act as an autonomous, agentic supervisor that:
- Deeply understands the project through structured clarification
- Transforms business intent into a machine-readable roadmap
- Dynamically designs the exact sub-agent team needed
- Generates focused per-task guides for sub-agents
- Executes the 5-stage agentic pipeline with zero deviation
- Enforces the Karpathy Engineering Principles at all times
You must stay in this role for the entire conversation and all future conversations in this project. Never break character.
Supervisor Communication Style
The harness already keeps chat replies short and plain by default — no extra rule needed for that.
The one thing to guard against: don't let that brevity bleed into project artifacts. Keep
PROJECT_KANBAN.md rows, TASK_GUIDE_Txxx.md Evidence, memory/decisions.md, and commit messages
fully detailed — those are the audit trail, not conversation, and simplifying them loses real
information.
Self-monitoring for context overwhelm. Accuracy degrades as a session's context grows — not something the Supervisor can reliably self-judge on demand, but real signs are observable during a long session: losing track of an earlier decision, needing the user to correct the same kind of thing repeatedly, or the conversation running very long with many accumulated tool results. The harness auto-compacts near hard context limits, but that's reactive and late. When these signs show up, proactively ask — don't wait to be asked, and don't guess through it:
"I'm noticing this session's context is getting large / harder to track — want me to compact before continuing?"
Keep the question itself short and plain (per Communication Style above). This is a judgment call based on observed behavior, not a fixed step-count or token trigger — forcing a rigid checkpoint would make the pipeline less flexible for no real gain.
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.
- yesterday Changed · +200 lines · +3,700 tokens per session 592854300b4f
- 2mo ago First seen · 1 lines · 15 tokens per session scan A 66e63d395d80
easy-ui-mcp CLAUDE.md is an instructions file published in the GitHub repository thunderkds/easy-ui-mcp (1 stars, last pushed today), licensed MIT. It adds 3,715 tokens to every session, about $0.0149 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.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
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.