Borrowing it
Nothing to install: this file belongs to cesmii/i3X-MCP-Server. 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/cesmii/i3X-MCP-Server/main/CLAUDE.mdgit clone --depth 1 https://github.com/cesmii/i3X-MCP-ServerWrote 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/cesmii/i3x-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/cesmii/i3x-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/cesmii/i3x-mcp-server/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 | $0.01668 | $0.01668 |
| Opus 5 | $0.00834 | $0.00834 |
| Sonnet 5 | $0.00334 | $0.00334 |
| Haiku 4.5 | $0.00167 | $0.00167 |
Grade A, and why
i3X-MCP-Server 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 8d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Context for Claude (and humans) contributing to this codebase. Read once before making changes.
What this is
An MCP server that wraps any i3X 1.0 compliant manufacturing data source for use from Claude / other MCP clients. Published as i3x-mcp on npm; end users install via npx -y i3x-mcp@latest in their Claude Desktop config.
Audience
End users of i3X-compliant systems — plant engineers, operators, maintenance — not i3X client developers. Every design decision flows from that: tool names, descriptions, input shapes, and error messages should make sense to someone who knows their plant, not someone who's read the i3X spec.
When in doubt: would a plant engineer recognize the input/output? If a tool requires the user (or model) to know about elementId, namespaceUri, or maxDepth, push that complexity inside the tool.
Locked-in design decisions
These aren't up for casual revision — they shape the whole surface. If you want to revisit one, raise it explicitly.
- Opinionated tool surface, not a thin 1:1 wrapper of i3X endpoints. ~12 tools, each composed from one or more i3X calls.
- Read-only by default;
update_valueandwrite_historyonly register when--enable-writesis passed. Setpoint writes can affect live equipment. - Connection is runtime-configurable via the
connecttool. Env vars (I3X_BASE_URL, etc.) are an optional bootstrap, not a requirement. The server always starts; data tools refuse with a friendly "callconnectfirst" message until connected. - Catalog cached locally + fuzzy-searched with fuse.js. i3X has no pagination or full-text search; this is how we make discovery work.
- Subscriptions are not exposed as a lifecycle. The single
watch_valuestool creates a subscription, polls/syncfor a bounded duration (max fromruntime.watchMaxDurationSec), and tears it down infinally. Prevents orphaned subscriptions on the i3X server. - History aggregation is server-side.
get_historyacceptsaggregation: raw|avg|min|max|countand abucketinterval. Raw mode is capped to protect the LLM's context window. - Times accept relative strings (
1h,last 30m,yesterday) and RFC 3339. Centralized insrc/time.ts. - Values are enriched with units inline when the ObjectType schema declares them. Centralized in
src/units.ts.
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.
- 8d ago First seen · 91 lines · 1,668 tokens per session scan A 587da8a4bd10
i3X-MCP-Server CLAUDE.md is an instructions file published in the GitHub repository cesmii/i3X-MCP-Server (2 stars, last pushed 2mo ago), licensed MIT. It adds 1,668 tokens to every session, about $0.0083 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
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.