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/frontsail-ai/aspicio/agents-mdgit clone --depth 1 https://github.com/frontsail-ai/aspicioWrote 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/frontsail-ai/aspicio/agents-md)<a href="https://agentmods.dev/instructions/frontsail-ai/aspicio/agents-md"><img src="https://agentmods.dev/badge/instructions/frontsail-ai/aspicio/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 | $0.02864 | $0.02864 |
| Opus 5 | $0.01432 | $0.01432 |
| Sonnet 5 | $0.00573 | $0.00573 |
| Haiku 4.5 | $0.00286 | $0.00286 |
Grade C, and why
aspicio AGENTS.md scanned grade C with 1 finding 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 3d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
`rm -rf dist && vp build`, and confirm the artifact — a size delta or a How it starts
The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Aspicio — agent guide
Aspicio (Latin: "I look at") — a TypeScript-first 2D drawing viewer (DXF and vector PDF) for the web, with a headless pipeline that also serves AI agents: an HTTP API, an MCP server, and installable skills/plugins. Live demo: https://aspicio.frontsail.app.
Tech stack
| What | Choice |
|---|---|
| Language / runtime | TypeScript; bun (package manager + runtime backend) |
| Toolchain | Vite+ (vp) — dev, build, test (vitest), lint/format (oxlint/oxfmt), pack (tsdown) |
| Rendering | Three.js WebGL (viewer); resvg WASM/native for headless PNG |
| Parsing | DXF: dxf-parser + custom entity handlers; PDF: own zero-dependency parser |
| E2E | Playwright e2e suites: demo + every example app (react/elements/vue/svelte/vanilla/widget) |
| Hosting / deploy | Vercel (custom domains on frontsail.app), prebuilt artifacts deployed from GitHub Actions |
| Agent protocol | MCP (official SDK; stdio + Streamable HTTP) + MCP Apps in-chat viewer |
Architecture in 30 seconds
parse → DrawingDocument → tessellate → { WebGL render | SVG | describe }.
Everything up to WebGL is headless (browser/Node/Workers). Core is
framework-free; embed UI lives once in the Lit web components
(packages/elements), with packages/react, packages/vue, and
packages/svelte as thin veneers over them; the API Worker and MCP
server expose the same pipeline to agents.
Details: docs/architecture.md.
Layout
Everything under packages/ publishes (INV-9) except where marked
private; apps/ and tools/ never publish. A private member of
packages/ may point its exports at source, because no consumer
outside this repo resolves it.
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.
- 3d ago First seen · 169 lines · 2,864 tokens per session scan C 87531b9e74b8
aspicio AGENTS.md is an instructions file published in the GitHub repository frontsail-ai/aspicio (4 stars, last pushed 3d ago), licensed MIT. It adds 2,864 tokens to every session, about $0.0143 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
Autocad-MCP CLAUDE.md
Instructions for U-C4N/Autocad-MCP, covering claude.md, project overview, running the server, stdio mode (default, for mcp clients like claude desktop) and http mode.
techdrawai-skills CLAUDE.md
Claude Code instructions for MeltFlexDevs/techdrawai-skills, covering notes for agents working in this repository, layout and rules.
AutoCAD-MCP CLAUDE.md
Claude Code instructions for codesknight/AutoCAD-MCP, covering 项目约定, 日志规则（重要，必须遵守）, 架构原则, 环境 and ⚠️ 安全注意事项.
langgraph AGENTS.md
AGENTS.md instructions for langchain-ai/langgraph, covering agents instructions, corridor security analysis, libraries and dependency map.
AstrBot copilot-instructions.md
Copilot instructions for AstrBotDevs/AstrBot, covering astrbot development instructions, working effectively, bootstrap and install dependencies, running the application and dashboard build (vue.js/node.js).
ai-business-skills CLAUDE.md
Claude Code instructions for minhnv0807/ai-business-skills, covering claude.md — fullstack marketing skills, identity, nguyen tac cot loi, cach su dung skill and tu dong nhan dien.