Borrowing it
Nothing to install: this file belongs to suapapa/openscad-wasm-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/suapapa/openscad-wasm-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/suapapa/openscad-wasm-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/suapapa/openscad-wasm-mcp/agents-md)<a href="https://agentmods.dev/instructions/suapapa/openscad-wasm-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/suapapa/openscad-wasm-mcp/agents-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 | $0.01428 | $0.01428 |
| Opus 5 | $0.00714 | $0.00714 |
| Sonnet 5 | $0.00286 | $0.00286 |
| Haiku 4.5 | $0.00143 | $0.00143 |
Grade A, and why
openscad-wasm-mcp AGENTS.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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Development notes for agents working on openscad-wasm-mcp.
Project Contract
This project is an OpenSCAD MCP server that runs OpenSCAD through openscad-wasm in Node.js. Do not add a native OpenSCAD binary dependency, do not automate the browser-based OpenSCAD UI, and do not expose arbitrary shell commands or raw OpenSCAD CLI args.
The server should remain runnable through Docker Compose with:
docker compose up --build
The default MCP transport is Streamable HTTP on /mcp, port 3333. Keep server creation separate from transport wiring so stdio can be added later.
Development Commands
npm install
npm run dev
npm test
npm run build
npm run lint
Use the mock backend for local development that should not depend on real WASM behavior:
OPENSCAD_BACKEND=mock npm run dev
Before handing off code changes, run at least:
npm test
npm run build
Run npm run lint when touching TypeScript, config, or formatting-sensitive files.
Runtime Configuration
Environment defaults are documented in .env.example:
PORT=3333HOST=0.0.0.0WORKSPACE_DIR=/workspaceARTIFACT_DIR=/workspace/artifactsJOB_TMP_DIR=/tmp/openscad-jobsMAX_RENDER_MS=30000MAX_OUTPUT_MB=50MAX_INPUT_MB=10MAX_PARALLEL_JOBS=2CLEANUP_JOBS=trueOPENSCAD_BACKEND=wasm|mockPUBLIC_BASE_URL=http://127.0.0.1:3333PREVIEW_TTL_SECONDS=3600PREVIEW_ENABLED=trueMCP_AUTH_TOKEN(optional; when set,/mcprequiresAuthorization: Bearer <token>)
Docker Compose binds only 127.0.0.1:3333:3333 and uses a read-only root filesystem, /tmp tmpfs, cap_drop: ALL, and no-new-privileges.
Architecture Map
src/index.ts: process entry point; loads config, creates dependencies, starts HTTP transport.src/config.ts: env parsing and runtime limits.src/server/createMcpServer.ts: MCP server construction and tool registration.src/server/transport.ts: Streamable HTTP wiring.src/tools/: zod schemas and MCP tool handlers.src/openscad/OpenScadRunner.ts: runner interface and shared runner result types.src/openscad/OpenScadWasmRunner.ts: real server-sideopenscad-wasmintegration boundary.src/openscad/MockOpenScadRunner.ts: deterministic runner for tests and development.src/openscad/args.ts: allowlisted OpenSCAD CLI-compatible args builder.src/workspace/: job workspace, artifact storage, path safety, and workspace tools.src/security/: size limits, semaphore, and sanitization helpers.test/: vitest coverage for safety, formats, diagnostics, workspace, and mock tool flows.
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 · 136 lines · 1,428 tokens per session scan A 1f80dfa1b510
openscad-wasm-mcp AGENTS.md is an instructions file published in the GitHub repository suapapa/openscad-wasm-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 1,428 tokens to every session, about $0.0071 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.