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/gaopengbin/cesium-mcp/agents-mdgit clone --depth 1 https://github.com/gaopengbin/cesium-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/gaopengbin/cesium-mcp/agents-md)<a href="https://agentmods.dev/instructions/gaopengbin/cesium-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/gaopengbin/cesium-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 | $0.01112 | $0.01112 |
| Opus 5 | $0.00556 | $0.00556 |
| Sonnet 5 | $0.00222 | $0.00222 |
| Haiku 4.5 | $0.00111 | $0.00111 |
Grade B, and why
cesium-mcp AGENTS.md scanned grade B 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 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.
Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
- Commit `.env` files, `.vscode/mcp.json`, or any Ion tokens / API keys. Copies of this mod
1 near-identical copy found in the catalogue:
- cesium-mcp CLAUDE.md — 97% identical, 4 lines differ
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — cesium-mcp
AI agent integration for CesiumJS. A monorepo providing an MCP server that lets AI agents control a 3D globe (CesiumJS) in the browser via WebSocket, plus IDE tooling for Cesium API doc lookup and code generation.
Monorepo Structure
packages/
cesium-mcp-bridge/ # SDK — command execution layer (browser-side, controls Cesium viewer)
cesium-mcp-runtime/ # MCP stdio/HTTP server — bridges AI agents to browser via WebSocket
cesium-mcp-dev/ # IDE assistant — Cesium API doc queries and code generation
examples/ # browser-agent, dify-integration, emergency-response, minimal, video
docs/ # VitePress site (guide, api, design, examples, zh-CN)
.Codex-plugin/ # Codex plugin manifest
hooks/ # Plugin hooks (SessionStart, etc.)
skills/ # Plugin skills (/cesium-quickstart)
Commands
| Command | Purpose |
|---|---|
npm run build |
Build all packages (tsup) |
npm test / npx vitest run |
Run tests |
npm run lint |
ESLint all packages |
npm run typecheck |
tsc --noEmit across workspaces |
npm run clean |
Remove all dist/ |
npm run build -w packages/cesium-mcp-bridge |
Build one package |
npm run changeset |
Add a changeset for versioning |
Install: npm ci at root (workspaces + patch-package postinstall).
Code Conventions
- No semicolons. Single quotes. Trailing commas on multi-line.
- 2-space indent. ESM throughout.
import type { ... }separate from value imports.- Files: kebab-case. Symbols: camelCase functions/vars, PascalCase types/classes.
- Type suffixes:
XxxParams,XxxResult. - One file per domain under
src/commands/(camera.ts, layer.ts, scene.ts, etc.). - Commands are plain functions
(viewer: Cesium.Viewer, params: XxxParams) => result, not classes. - Tests: Vitest, colocated as
*.test.ts. Import source via./foo.js(NodeNext ESM). - Types in
types.tswith// ========== Section ==========banners. No zod in bridge.
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 · 84 lines · 1,112 tokens per session scan B b44e82917066
cesium-mcp AGENTS.md is an instructions file published in the GitHub repository gaopengbin/cesium-mcp (134 stars, last pushed yesterday), licensed MIT. It adds 1,112 tokens to every session, about $0.0056 per session on Opus 5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
geolens AGENTS.md
AGENTS.md instructions for geolens-io/geolens, covering repository guidelines, project structure & module organization, build, test, and development commands, running a single test and working from a git worktree.
mazzap CLAUDE.md
Instructions for zymazza/mazzap, covering claude.md, what this is, commands, twin store and mcp server.
godot-mcp AGENTS.md
AGENTS.md instructions for sandraschi/godot-mcp, covering agents.md — godot-mcp context, essential paths, module registration, key dependencies and conventions.
cotlib CLAUDE.md
Instructions for NERVsystems/cotlib, covering claude.md, project overview, build and test commands, build without schema validation (no cgo required) and run all tests.
godot-mcp CLAUDE.md
Claude Code instructions for sandraschi/godot-mcp, covering godot-mcp — claude code guide, standards and key files.
godot-mcp copilot-instructions.md
Copilot instructions for sandraschi/godot-mcp: You have access to a Godot 4 game engine control server with 49 tools across 10 domains: engine control, asset import/export, game building, fleet coordination, itch.io shipping, Steam publishing, animation, particles, HTML5 export, and cross-server MCP bridging.