# context-mode

This skill routes data analysis, searches, and page retrieval through context-mode tools. It helps keep large raw inputs out of an agent’s context.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf (Devin Desktop), Claude.ai · ★ 34370 repo stars
- Author: Mert Koseoğlu
- License: Elastic-2.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/mksglu/context-mode/tree/HEAD/configs/copilot-cli/skills/context-mode/SKILL.md
- Updated: 2026-10-24
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/context-mode-2

## What it does

For analyzing, counting, filtering, comparing, or transforming data, the skill directs the agent to write code with `ctx_execute` and print only the result. Large files go through `ctx_execute_file`; `ctx_batch_execute` can handle a group of commands and search queries in one call.

For web pages, it uses `ctx_fetch_and_index` followed by `ctx_search`, so the full HTML is not added to context. The routing rules block `curl`, `wget`, and inline HTTP requests using `fetch` or `requests`. The context-mode tools must be available to the agent for these rules to work.

The skill recommends writing artifacts to files and returning a path with a brief description instead of dumping the contents inline. That matters for large reports: their full contents stay out of the conversation.

## Install

### Claude Code (native platform)

1. **Plugin marketplace**
In the agent chat (not a shell):
```text
/plugin marketplace add mksglu/context-mode
```
In the agent chat (not a shell):
```text
/plugin install context-mode@context-mode
```
This installs the whole context-mode plugin with all its skills

2. **Skills CLI (Vercel)**
```bash
npx skills add mksglu/context-mode --skill context-mode -a claude-code
```

3. **Manually: put the files in place**
- File: `~/.claude/skills/context-mode/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/context-mode/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add mksglu/context-mode --skill context-mode -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/context-mode/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add mksglu/context-mode --skill context-mode -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/context-mode/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install mksglu/context-mode configs/copilot-cli/skills/context-mode
```

2. **Manually: put the files in place**
- File: `.github/skills/context-mode/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add mksglu/context-mode --skill context-mode -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/mksglu/context-mode --path configs/copilot-cli/skills/context-mode
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/context-mode/SKILL.md` — The legacy .windsurf/skills/ path still works

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/mksglu/context-mode/tree/HEAD/configs/copilot-cli/skills/context-mode/SKILL.md

## When to use it
- count and filter records without reading the full dataset
- compare data with a script
- process a large file through `ctx_execute_file`
- search a web page without placing its HTML in context
- save analysis results to a file and return its path

## Example prompts
- Count the records in this data and print only the result.
- Find answers to my questions on this page without adding its HTML to context.
- Process this large file and save the result to a separate file.

## Similar
- [datasets](https://affpapa.org/en/nevibecode/skills/brightdata-datasets.md) — skill · 180 installs
- [scraping-instagram-users-by-keyword](https://affpapa.org/en/nevibecode/skills/scraping-instagram-users-by-keyword.md) — skill · 889 installs
- [TakoData-tako-mcp](https://affpapa.org/en/nevibecode/mcp/takodata-tako-mcp.md) — MCP server · ★ 7 repo stars
- [Upscrape](https://affpapa.org/en/nevibecode/mcp/upscrape.md) — MCP server · ★ 1 repo stars
- [parallel-findall](https://affpapa.org/en/nevibecode/skills/parallel-findall.md) — skill · 13000 installs
- [planetscale-autonomous-execution-mode](https://affpapa.org/en/nevibecode/skills/planetscale-autonomous-execution-mode.md) — skill · 2000 installs

## Other versions with the same name
- [context-mode · mksglu](https://affpapa.org/en/nevibecode/skills/context-mode.md) — 3000 installs
- [context-mode · mksglu](https://affpapa.org/en/nevibecode/skills/mert-koseoglu-context-mode.md) — ★ 34370 repo stars

From the same set: [mksglu/context-mode](https://affpapa.org/en/nevibecode/by/mksglu/context-mode.md) — 14 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
