AutoRAG Agent is a librarian-style system that searches files on a computer, checks the original documents, and organizes findings into numbered knowledge units using multiple retrieval methods. It helps an agent answer questions from local documents without first copying them into a centralized vector database, while the repository also maintains the earlier AutoRAG tool for optimizing retrieval-augmented-generation pipelines. The catalogue entries provide skills and instructions for working with AutoRAG Agent.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Marker-Inc-Korea/AutoRAG --skill organizegit clone --depth 1 https://github.com/Marker-Inc-Korea/AutoRAGWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/marker-inc-korea/autorag/organize)<a href="https://agentmods.dev/skills/marker-inc-korea/autorag/organize"><img src="https://agentmods.dev/badge/skills/marker-inc-korea/autorag/organize/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/marker-inc-korea/autorag/organize"><img src="https://agentmods.dev/badge/skills/marker-inc-korea/autorag/organize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00070 | $0.00567 |
| Opus 5.5 | $0.00028 | $0.00227 |
| Sonnet 5.5 | $0.00014 | $0.00113 |
| Haiku 4.5 | $0.00007 | $0.00057 |
Grade A, and why
organize scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Organizing files and folders
Use this skill when the user asks you to act on files or folders — tidy or sort a folder, move or copy files into folders, bulk or pattern rename, rename files according to what their content says, convert formats, create folder structures, archive, or move files to the trash. This is a file-organization task, not a document search: the answer is the change on disk, not information found in the files.
How to do it
- Work with
bash(ls,mkdir,mv,cp, and a boundedfind). Read a file (withreadorbash) only when its content decides the new name or folder, then carry the change out withbashor the file tools. - Use the converter tools for format conversions, the duplicate scan when the request is about duplicates, and the file-name discovery tools to locate files by name.
- Do not search document contents, the user's datasources, or the web in this turn: content retrieval and the web tools are not part of this task. The turn prompt lists the exact tools to use and the ones to leave alone.
Rules
- Plan first. List what you found, decide every target path, and check that no two targets share a name and that no target already exists before you move anything. Never overwrite an existing file.
- Touch only what the request names. When the request does not name a folder, ask which one instead of guessing, unless the conversation already says.
- Never delete permanently — no
rm,rmdir,unlink,find -delete,shred, or PowerShellRemove-Item. Move what must go to the OS trash instead (macOS/usr/bin/trash, Linuxgio trash, Windows Recycle Bin). - Confirm afterwards. List the destination folder to check the changes really happened.
- Finish with a report, as your final message and with no tool call: every change as old path → new path (one per line), what you skipped and why, and anything that still needs the user. Write in the language of the request.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 44 lines · 70 tokens per session scan A dff298dec930
organize is a skill published in the GitHub repository Marker-Inc-Korea/AutoRAG (5,191 stars, last pushed yesterday), licensed Apache-2.0. It adds 70 tokens to every session and 567 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-26.
Other skills, from other repositories
copilotkit-channels
Use for the CODE half of a managed Intelligence Channel with Slack or Microsoft Teams: customising the Channel a CLI-scaffolded project already ships, or — for a project the CLI did not generate — writing the Channel declaration, the long-running host, and the awaited activation call. Teams provider setup is in scope…
setup-slack-channel
Use for the PROVIDER half of getting a locally running CopilotKit Channels agent to answer in Slack, when no Slack app exists yet — setting up a Channels bot in Slack for the first time, creating the Slack app and its tokens, attaching it to a managed Intelligence Channel, or when a Channel reports setuprequired, sits…
channels-setup
Use when a developer wants to build their first CopilotKit Channels agent and get it answering in Slack or Microsoft Teams: "set up a channel", "connect my agent to Slack", "get my agent into Teams", or starting from nothing and wanting a working channel end to end. Covers the whole path: inspecting or scaffolding the…
tmux
Manage long-running shell sessions with tmux — start a detached session, run a long task, reattach later, capture output. Use when a task takes longer than a single tool call (build, test, log tail).
slack-tools
Slack workspace management and automation specialist.
kortix-teams
How to CONNECT Microsoft Teams (kortix channels connect --platform teams, prints a tenant-admin consent URL) and how to answer in Teams as a teammate. Covers the live Adaptive Card stream (teams step with --detail/--output/--source, teams send to finalize the answer), sending and downloading files (the consent-card…