AI 工具AI TOOLS· CHAT-AGENT
mocasus/paleo
一套帮AI助手省token的技能包,压缩输出、修剪对话、控制预算。A collection of 7 token-saving modes for LLM agent users, compressing output, trimming context, and capping budgets across multiple platforms.
根据公开文档整理,未运行实测;费用以项目官网为准。Based on public documentation, without runtime testing. Check the project site for pricing.
能力CAPABILITIES
自动压缩对话历史节省开销
设定输出上限防止超支
将长输出总结成简短版本
让AI回复更简洁无废话
自动修剪过长上下文窗口
Compress output to reduce token usage
Trim context automatically in long sessions
Enforce hard token budgets per task
Summarize lengthy conversations or logs
Minify JSON output for structured data
上手GET STARTED
git clone https://github.com/mocasus/paleo.git选择与你的环境对应的方式。命令来自项目文档,未运行实测。Choose the option for your environment. Commands come from project documentation and have not been run-tested.
使用限制LIMITATIONS
以下要求与风险来自文档静态检查,未执行项目代码;扫描没有命中,不代表使用安全。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
未知Unknown
静态扫描STATIC SCAN
在 README、SKILL.md 和依赖清单中没有匹配到已知风险模式。No known risk patterns matched in the README, SKILL.md or dependency list.
静态扫描未发现明显风险,但不代表安全。The static scan did not find any known risk patterns in the documentation, but this does not guarantee the code is safe. Review before use.
项目动态PROJECT ACTIVITY
首次发现FIRST SEEN
03 OCT 202603 OCT 2026
增长GROWTH
+5.0%+5.0%
20 → 21 stars · 50 个快照20 → 21 stars · 50 snapshots
状态STATUS
持续活跃Active
项目在2026年7月发布,近期有更新,适合早期采用者。7 token-saving modes in one collection
{
"agents": [
{
"agent": "claude-code",
"evidence": "tree: .claude-plugin/"
},
{
"agent": "windsurf",
"evidence": "readme: …ursor, GitHub Copilot, Cline, Windsurf + **40+ agents** via `npx ski…"
},
{
"agent": "cline",
"evidence": "readme: …Code, Cursor, GitHub Copilot, Cline, Windsurf + **40+ agents** vi…"
},
{
"agent": "gemini-cli",
"evidence": "readme: …standard: Claude Code, Codex, Gemini CLI, Qwen Code, OpenCode, Cursor,…"
},
{
"agent": "opencode",
"evidence": "readme: …Codex, Gemini CLI, Qwen Code, OpenCode, Cursor, GitHub Copilot, Clin…"
},
{
"agent": "copilot",
"evidence": "readme: …Qwen Code, OpenCode, Cursor, GitHub Copilot, Cline, Windsurf + **40+ agen…"
}
],
"apiKey": "ur own stack: ```bash export IDROUTER_API_KEY=your_key python3 bench/benchmark.py --m",
"docker": null,
"taxonomy": {
"scores": {
"design": 0,
"ai-tools": 7,
"dev-tools": 4,
"indie-web": 0,
"skill-agent": 11,
"productivity": 6
},
"primary": "ai-tools",
"secondary": "chat-agent"
},
"localRuntime": null,
"skillMdTotal": 7,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 0,
"agent": 0,
"media": 0,
"design": 0,
"browser": 0,
"devtool": 1,
"security": 0,
"marketing": 0,
"productivity": 0
},
"classification": [
{
"signal": "7 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "skills/ directory with 7 markdown files",
"weight": 0.75
},
{
"signal": "README describes a Claude / Agent Skill",
"weight": 0.7
},
{
"signal": "Claude Code plugin manifest",
"weight": 0.7
},
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme",
"skills/paleo-auto/SKILL.md",
"skills/paleo-budget/SKILL.md",
"skills/paleo-converse/SKILL.md",
"skills/paleo-json/SKILL.md",
"skills/paleo-summary/SKILL.md",
"skills/paleo-trim-context/SKILL.md",
"skills/paleo/SKILL.md"
],
"skillMdFetched": 7
}