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/randomsynergy17/arcane-mcp-server/claude-mdgit clone --depth 1 https://github.com/RandomSynergy17/Arcane-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/randomsynergy17/arcane-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/randomsynergy17/arcane-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/randomsynergy17/arcane-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 | $0.01135 | $0.01135 |
| Opus 5 | $0.00567 | $0.00567 |
| Sonnet 5 | $0.00227 | $0.00227 |
| Haiku 4.5 | $0.00113 | $0.00113 |
Grade A, and why
Arcane-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 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arcane MCP Server
MCP server for Docker management via the Arcane platform. 180 tools, 2 resources, 4 prompts, companion skill, Claude Code plugin.
Not affiliated with the Arcane project.
Build & Test
npm install
npm run build # TypeScript → dist/
npm test # vitest (50 tests)
npm run dev # stdio mode
npm run dev:tcp # HTTP mode
npm run update-api-spec # Refresh OpenAPI spec from live instance
Architecture
src/index.ts— stdio entry point (default)src/tcp-server.ts— HTTP/Streamable transport (--tcp flag)src/server.ts— McpServer factory, wires tools + resources + promptssrc/client/arcane-client.ts— HTTP client with retry, SSL bypass, size limitssrc/auth/auth-manager.ts— JWT (auto-refresh) + API key authsrc/config.ts— Config from env vars > config file > defaultssrc/constants.ts— All shared constants (timeouts, limits, versions)
Tools (180 across 25 modules in src/tools/)
All tools use server.registerTool() with:
title— human-readable namedescription— what it does and returnsannotations—readOnlyHint,destructiveHint,idempotentHint,openWorldHintinputSchema— Zod schemas with.describe()on every paramtoolHandler()wrapper fromsrc/utils/tool-helpers.ts— handles client init, error formatting,isError: trueon failures
Adding a new tool
- Find or create the tool module in
src/tools/ - Use
server.registerTool()with the config object pattern (not deprecatedserver.tool()) - Classify annotations: list/get = readOnly, delete/prune = destructive, external calls = openWorld
- Use
toolHandler()wrapper — return a plain string, it handles the MCP response envelope - Register in
src/tools/index.ts - Verify:
npm run build && grep -rc 'register("arcane_' dist/tools/*.js | awk -F: '{sum+=$2} END {print sum}'(expect 180)
Resources & Prompts
src/resources/index.ts— 3 resources (arcane://environments,arcane://version,arcane://tools-config-notice)src/prompts/index.ts— 5 prompts (deploy-stack, troubleshoot-container, security-audit, cleanup-environment, arcane_configure_tools)- Prompts reference real tool names — cross-check if adding/renaming tools
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 · 90 lines · 1,135 tokens per session scan A d1554ed44f41
Arcane-MCP-Server CLAUDE.md is an instructions file published in the GitHub repository RandomSynergy17/Arcane-MCP-Server (13 stars, last pushed 3mo ago), licensed MIT. It adds 1,135 tokens to every session, about $0.0057 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 2026-08-30.
Other instructions, from other repositories
appwrite AGENTS.md
AGENTS.md instructions for appwrite/appwrite, covering appwrite, commands, stack, layout and libraries.
selfhost-ai CLAUDE.md
Claude Code instructions for kossakovsky/selfhost-ai, covering claude.md, project overview, core architecture, key files and installation flow.
openlakeforge AGENTS.md
AGENTS.md instructions for malon64/openlakeforge, covering agent and contributor guide, what this project is, non-goals, orientation — read in this order and repository map.
docker-zoneminder CLAUDE.md
Instructions for jantman/docker-zoneminder, covering claude.md, project overview, build and test, ci/cd and architecture.
mitos CLAUDE.md
Instructions for mitos-run/mitos, covering claude.md, project overview, operating principles, commands and architecture.
MoaV AGENTS.md
AGENTS.md instructions for MotherofallVPNs/MoaV, covering what moav is, install & run, everyday operations, dashboards & access — what to hand the owner and where things live.