返回资讯中心
外部精选
软件工程
#开发者实时流

Show HN: Code-mode – keep MCP tool results out of Claude Code's context

code-mode is a Claude Code plugin. Claude writes one JavaScript program that calls your MCP tools in a sandbox,

Hacker News 最新gabe4coding2026/10/20 · 26 天前8 分钟阅读

以下正文同步自 Hacker News 最新,版权归原站所有,已转换为易读排版。

code-mode is a Claude Code plugin. Claude writes one JavaScript program that calls your MCP tools in a sandbox, filters and joins the data there, and sends back only the answer.

Measured: the same 30/30 correct answers at 43% lower cost per task with Haiku 5.5. How we measured · If it saves you tokens, ⭐ the repo.

Install · Demo · Measured · Example · How it works · Config

Needs Claude Code and Node.js 22.13+. No dependencies. In a Claude Code session:

/plugin marketplace add gabe4coding/claude-code-mode /plugin install code-mode@claude-code-mode

Start a new session and ask for anything that needs several MCP calls. Using auto mode with Claude Code older than 2.1.301? Add allow rules first: Permissions.

code-mode-explainer-github.mp4

Without code-mode With code-mode

Claude calls tools one by one Claude writes one program

Every full result lands in context Results are filtered in a sandbox

Context fills with raw JSON Only the answer comes back

Why

Fewer tokens. Intermediate data never enters the context. See Measured.

Sandboxed. Separate Node process, no file system, CPU limit. No network on macOS and on Linux where unshare -rn works.

Learns your tools. Hints per MCP server (formats, required args, limits). Claude proposes fixes. You approve.

Reusable functions. Programs that work can become saved functions for later sessions, after you read and approve the code.

Your permissions still apply. Every MCP call inside the program gets the normal permission check.

Measured

The bench in bench/ runs six tasks in headless Claude Code against a fake MCP server. Each task has traps: pages, nested fields, bots and results larger than 20,000 characters.

Haiku 5.5, without and with code-mode (5 runs of each task, plugin 0.6.0 and 0.6.1, 2026-10-10). In 0.6.0 the code-mode start line did not reach the model, so Haiku called most tools directly.

Opus 5.5, output projection off and on: duplicate MCP calls per task went from 1.37 to 0.10. Cost and correct answers did not change. Refer to PR #11.

Limits: these are bench tasks in headless runs. Interactive sessions were not measured. Most input tokens are the fixed context of Claude Code, so the input saving is smaller than the cost saving. To run the bench again, refer to Development.

"Which of my open Jira issues have no update in the last 14 days?"

const issues = await call("mcp__claude_ai_Jira__searchJiraIssuesUsingJql", { cloudId: "example.atlassian.net", jql: "assignee = currentUser() AND statusCategory != Done", }) const cutoff = Date.now() - 14 * 24 * 3600 * 1000 return issues.issues .filter(i => Date.parse(i.fields.updated) < cutoff) .map(i => ({ key: i.key, title: i.fields.summary }))

Claude sees a short list of keys and titles, not every full issue.

Page

Installation Requirements, install, local folder, update

Usage The three tools, how to write a program, the result

Hints Write hints, approve proposals, the safety rules

Saved functions Approve or write functions that programs use again

Permissions Manual and auto mode, allow rules

Configuration Every option and its default

How it works One run from start to end, the four sandbox layers

Troubleshooting Common errors and known limits

Development Layout, tests, releases

Contributing / feedback

Issues and PRs welcome. If code-mode saves you tokens, a ⭐ helps others find it.

正文由 探How 从来源站点 RSS 同步,内容未经改写;遇到排版缺失或需要图片、视频时请以原文为准。

打开原文
去社区讨论 →