SKILLS & AGENTS/Skill 与 Agent·MCP-SERVER
ooples/token-optimizer-mcp
Measure token savings per AI coding agent, optimize context, and share a live local knowledge graph across 16 CLI clients.
怎么装:Install: /plugin marketplace add ooples/token-optimizer-mcp
02 / 现在的位置02 / Why now
首次发现FIRST SEEN
03 OCT 202603 OCT 2026
增长GROWTH
+0.6%+0.6%
538 → 541 stars · 7 个快照538 → 541 stars · 7 snapshots
状态STATUS
持续活跃Active
03 / 它能帮你做什么03 / What it helps you do
04 / 安装04 / Install
$ README 里给出的安装方式。The installation method given in the README.
$ README 里给出的安装方式。The installation method given in the README.
两种装法选一个即可 —— 上面那条给命令行用户,下面那条给写代码的用户。Pick one of the two — the first is for command-line users, the second for people writing code.
05 / 限制与风险05 / Limits and risk
风险不是警告,是可信度的一部分。以下结论只基于文档静态扫描,我们不会执行项目里的任何代码。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.
限制LIMITS
需检查Needs review
静态扫描STATIC SCAN
01安装时执行脚本Runs a script during installpackage.json
postinstall: node scripts/postinstall.cjs
这里只做静态扫描:读 README、SKILL.md 和依赖清单,不执行代码。没有命中不代表安全。This is static scanning only: we read the README, SKILL.md and dependency list, and never execute code. No findings does not mean safe.
依赖:Dependencies:@babel/parser, @iarna/toml, @modelcontextprotocol/sdk, @typescript-eslint/typescript-estree, async-mutex, better-sqlite3, chalk, chart.js, cors, d3-force, diff, express
{
"agents": [
{
"agent": "claude-code",
"evidence": "tree: .claude-plugin/"
},
{
"agent": "claude-desktop",
"evidence": "readme: …tion files are available for [Claude Desktop](./examples/claude_desktop_co…"
},
{
"agent": "codex",
"evidence": "readme: …parison (2026-09-15).** Local Codex CLI 0.154.0, `gpt-6-astra`, and i…"
},
{
"agent": "windsurf",
"evidence": "readme: …routed at all: Cursor, Cline, Windsurf, Kilo, Roo and Zed run the as…"
},
{
"agent": "cline",
"evidence": "readme: …not be routed at all: Cursor, Cline, Windsurf, Kilo, Roo and Zed…"
},
{
"agent": "gemini-cli",
"evidence": "readme: …e, Codex, GitHub Copilot CLI, Gemini CLI, Qwen Code, and Cursor. Nat…"
},
{
"agent": "opencode",
"evidence": "readme: …`claude`, `codex`, `gemini`, `opencode`, `qwen`, `crush`, `droid`, `…"
},
{
"agent": "copilot",
"evidence": "readme: …uation:** Claude Code, Codex, GitHub Copilot CLI, Gemini CLI, Qwen Code,…"
}
],
"apiKey": "environment: ```bash export ORCAROUTER_API_KEY=sk-orca-… # the API-key choice",
"docker": null,
"taxonomy": {
"scores": {
"design": 0,
"ai-tools": 7,
"dev-tools": 2,
"indie-web": 0,
"skill-agent": 6,
"productivity": 3
},
"primary": "skill-agent",
"secondary": "mcp-server"
},
"localRuntime": null,
"skillMdTotal": 2,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 2,
"agent": 0,
"media": 0,
"design": 0,
"browser": 0,
"devtool": 2,
"security": 0,
"marketing": 0,
"productivity": 0
},
"classification": [
{
"signal": "2 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "server.json (MCP registry manifest)",
"weight": 0.85
},
{
"signal": "package.json depends on @modelcontextprotocol/sdk + MCP framing",
"weight": 0.8
},
{
"signal": "Claude Code plugin manifest",
"weight": 0.7
},
{
"signal": "README ships an mcpServers config for this server",
"weight": 0.7
},
{
"signal": "MCP topic + README",
"weight": 0.6
},
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme",
"integrations/codex/plugin/skills/token-optimization/SKILL.md",
"plugin/skills/token-optimization/SKILL.md"
],
"skillMdFetched": 2
}