# AI use cases for Aside Codemode (lidge-jun/aside-codemode)

Repo: [lidge-jun/aside-codemode](https://github.com/lidge-jun/aside-codemode) | Use cases: 4 | Page: https://dedupedai.com/use-cases/lidge-jun-aside-codemode/

aside-codemode is a JavaScript code-mode tool for Aside that runs ripgrep-backed search, file tools and batched browsing inside one sandboxed call so only the filtered answer reaches the model.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Find every file that mentions a term in one call: https://dedupedai.com/use-cases/lidge-jun-aside-codemode/find-text-across-a-project-in-one-call/
- Turn many web pages into typed rows in one call: https://dedupedai.com/use-cases/lidge-jun-aside-codemode/batch-read-web-pages-into-typed-rows/
- Count matches in a huge tree without flooding output: https://dedupedai.com/use-cases/lidge-jun-aside-codemode/count-matches-in-a-very-large-tree/
- List files of one type across a large folder fast: https://dedupedai.com/use-cases/lidge-jun-aside-codemode/list-files-by-name-pattern-quickly/

## How to find every file that mentions a term in one call with Aside Codemode

Repo: [lidge-jun/aside-codemode](https://github.com/lidge-jun/aside-codemode) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Search a whole project with ripgrep and return only the matching paths to the model.

**Who it is for:** A developer in Aside who needs to locate every file that mentions a term, such as TODO, across a large local folder.

**The problem:** Doing this natively means many separate reads and bash calls, and every matched file's content can flood the model context.

**The outcome:** The agent gets the list of matching paths in one call, with the file contents kept out of the context.

### Steps

1. Run `npm install -g aside-codemode`
2. Run `codemode --install-mcp`
3. Run `codemode --doctor` and confirm the state reads activated
4. Start a new Aside session so the mcp__aside-codemode__execute_code tool is attached
5. Ask the agent to run a search over the project folder and return only the paths

### Prompt to paste into your agent

```text
Use the aside-codemode execute_code tool to search <project folder> for the text <term> with the search content action, and return the unique file paths only. Verify that the result contains paths and no file bodies.
```

### Caveat

The 55s to 1s folder comparison is an operator report that the README says was not independently reproduced, so measure your own folder before relying on the number.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/lidge-jun-aside-codemode/find-text-across-a-project-in-one-call/

## How to turn many web pages into typed rows in one call with Aside Codemode

Repo: [lidge-jun/aside-codemode](https://github.com/lidge-jun/aside-codemode) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Fetch a list of URLs in one browser batch and return a few extracted fields per page.

**Who it is for:** A researcher or analyst in Aside who has a list of pages and needs the same few facts from each.

**The problem:** Reading each page natively adds one round trip per page and puts whole pages or accessibility trees into the model context.

**The outcome:** The agent gets one typed row per page, such as a title and first link, instead of raw HTML.

### Steps

1. Run `npm install -g aside-codemode`
2. Run `codemode --install-mcp`
3. Turn on browsing in Aside
4. Run `codemode --doctor` and confirm the state reads activated
5. Ask the agent to run browse.exec over your URL list with the fields you want

### Prompt to paste into your agent

```text
Use the aside-codemode execute_code tool to call browse.exec on the URLs in <url list>, extracting the title and first link, and return the items array. Verify that each row has a status and that pages that failed are reported rather than hidden.
```

### Caveat

The README's five-page measurement dropped two pages that answered with a captcha, so expect some pages to fail and check the status on each row.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/lidge-jun-aside-codemode/batch-read-web-pages-into-typed-rows/

## How to count matches in a huge tree without flooding output with Aside Codemode

Repo: [lidge-jun/aside-codemode](https://github.com/lidge-jun/aside-codemode) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Get a match count and file count from a very large tree in one short result.

**Who it is for:** An engineer in Aside checking how often a symbol or pattern appears across a repository with a very large file count.

**The problem:** A plain recursive grep can emit millions of lines, which buries the answer before it arrives.

**The outcome:** The agent returns a compact count, such as total matching lines and matching files, in a few hundred bytes.

### Steps

1. Run `npm install -g aside-codemode`
2. Run `codemode --install-mcp`
3. Run `codemode --doctor` and confirm the state reads activated
4. Ask the agent to run search.count over the tree with the pattern you want

### Prompt to paste into your agent

```text
Use the aside-codemode execute_code tool to run search.count for <pattern> under <root folder> and return the matching line count and file count. Verify the totals against a small known subfolder before trusting the full-tree figure.
```

### Caveat

The 2,966 ms count and 127,000-file figure come from one controlled measurement against codemode 0.8.1, so timings on your tree will differ.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/lidge-jun-aside-codemode/count-matches-in-a-very-large-tree/

## How to list files of one type across a large folder fast with Aside Codemode

Repo: [lidge-jun/aside-codemode](https://github.com/lidge-jun/aside-codemode) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Return every path matching a file pattern from a big tree without listing noise.

**Who it is for:** A developer or writer in Aside who wants an inventory of files of one type, such as every Markdown note, from a large folder.

**The problem:** Building the list with find through bash is slower on large trees, and the agent has to parse noisy output.

**The outcome:** The agent gets the matching paths as a clean list, returned in the same call.

### Steps

1. Run `npm install -g aside-codemode`
2. Run `codemode --install-mcp`
3. Run `codemode --doctor` and confirm the state reads activated
4. Ask the agent to use the file search actions in execute_code to list paths matching the pattern you want (inferred, check the README)

### Prompt to paste into your agent

```text
Use the aside-codemode execute_code tool to list every file matching <pattern> under <root folder> and return the paths. Verify the path count against a find run on a small subfolder.
```

### Caveat

The README's listing timing is from one tree of 39,831 paths, and the exact file-name action is not named in the README, so confirm the action name with --doctor or the tool description first.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/lidge-jun-aside-codemode/list-files-by-name-pattern-quickly/
