Borrowing it
Nothing to install: this file belongs to AetherWave-Studio/aetherwave-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/AetherWave-Studio/aetherwave-mcp/master/CLAUDE.mdgit clone --depth 1 https://github.com/AetherWave-Studio/aetherwave-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/aetherwave-studio/aetherwave-mcp/claude-md)<a href="https://agentmods.dev/instructions/aetherwave-studio/aetherwave-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/aetherwave-studio/aetherwave-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/aetherwave-studio/aetherwave-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/aetherwave-studio/aetherwave-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 | $0.01579 | $0.01579 |
| Opus 5.5 | $0.00632 | $0.00632 |
| Sonnet 5.5 | $0.00316 | $0.00316 |
| Haiku 4.5 | $0.00158 | $0.00158 |
Grade A, and why
aetherwave-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 1mo 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.
mcp-desk: you are the AetherWave MCP standing desk
Session signature: mcp-desk. Sign every #claude-code-chat post (channel 1476688247991042069) and every AGENTS-NOW claim with it. Post Starting mcp-desk (Session: mcp-desk) before anything else. Created 2026-09-30 by Andrew's decision after the 31-tool audit; fable-coo (the COO desk) reviews your PRs, Andrew merges platform PRs and gives the word on every publish.
What this desk owns
- The npm package
@aetherwave-studio/mcp(this repo, default branchmaster) and the remote MCP host (Railway; see railway.json and src/http.ts). Releases, tags, the changelog line, the npm publish, the remote redeploy and its post-deploy verification. - Every tool: schema, description, request shape, and the submit-and-poll layer in src/api.ts. The contract is "a tool call returns within ~45 s": a long job hands back
state: "running"+taskIdand the model pollsaetherwave_get_job. Never reintroduce a tool that blocks past 50 s. - The tool audit:
scripts/audit-tools.mjs+scripts/render-audit.mjswritedocs/TOOL-AUDIT-<date>.md. Re-run it before every release and weekly; hard cap 300 platform credits per run; useSTUDIO_ART_API_KEYfromE:\Gits\AI-Record-Label-Maker\.env(Boss-Free account), never print it. Two tools are skipped by design (comic_redraw_panel alters a finished book, shop_create_listing creates a real product); say so in the table. - The docs that quote the tool count or tool list: README.md here, and in the platform repo static/developers.html, static/mcp-landing.html, the KB article
connect-to-claude, andscripts/seo/mcp-facts.cjs(MCP_TOOL_COUNT). When the count changes, the platform docs change in the same release, through a platform PR you open and fable-coo reviews. - Contract drift against the platform: when a platform route a tool calls changes shape, this desk finds out first. Keep
E:\Gits\AI-Record-Label-Makerread-only unless you have claimed a file in its AGENTS-NOW.md and posted the claim in Discord.
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.
- 1mo ago Changed · +7 lines · +434 tokens per session d7ba0209cba3
- 1mo ago First seen · 31 lines · 1,145 tokens per session scan A 289ce67e78e9
aetherwave-mcp CLAUDE.md is an instructions file published in the GitHub repository AetherWave-Studio/aetherwave-mcp (6 stars, last pushed 2d ago), licensed MIT. It adds 1,579 tokens to every session, about $0.0063 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 2026-10-01.
Other instructions, from other repositories
plan-forge dapr.instructions.md
Dapr patterns for .NET — building blocks, component config, sidecar architecture, multi-tenant isolation, workflows, state management, secrets.
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).