scan-loader — Claude Code subagent: what it does, how to install
A restricted helper subagent shipped with the claude-security plugin. It reads one JSON file from a run directory and hands the content back untouched.
/plugin install claude-security@claude-plugins-officialWhat scan-loader does
scan-loader is a piece of the Claude Security scan pipeline. The dispatch gives it a directory and a file name, and it reads <directory>/<file name>, then returns that JSON through structured output exactly as stored: every row, every field, nothing added, dropped or reworded.
Its toolset is cut down to Read. It opens nothing else and does nothing else. Whatever sits inside the file counts as data written by an earlier scan stage, not as instructions for the agent to follow.
It runs on sonnet with low effort. Calling it yourself makes little sense — the orchestrator is supposed to launch it, and without a directory and file name passed in there is nothing for it to load.
What it helps with
- pull a single JSON file out of a scan run directory
- return file contents with no fields lost or paraphrased
- keep the agent limited to the Read tool
- treat scan output as data rather than instructions
Example prompts for the agent
- Run the scan-loader subagent on directory
runs/2024-05-01and filefindings.json - Load
runs/latest/report.jsonwith scan-loader and return the JSON unchanged
How to install scan-loader
1Plugin marketplace
/plugin install claude-security@claude-plugins-official2Manually: put the files in place
.claude/agents/scan-loader.mdFor all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention
Manually: put the files in place
.codex/agents/scan-loader.tomlCodex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/
Manually: put the files in place
.cursor/agents/scan-loader.mdCursor also reads .claude/agents/
Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean
Questions about scan-loader
How do I install scan-loader in Claude Code?
Through the marketplace: run /plugin install claude-security@claude-plugins-official, and the agent lands at .claude/agents/scan-loader.md.
What does scan-loader do?
It reads one JSON file from the directory and file name it is given, then returns the content through structured output without edits.
Can I invoke scan-loader directly?
It is meant to be dispatched by the Claude Security scan workflow. With no directory or file name from the orchestrator, it has nothing to read.
