agentmods.dev

LightRAG: Settings file for Claude Code

.claude/settings.json

LightRAG is a settings file for Claude Code from HKUDS/LightRAG. Its token cost is not measured, scanned A, original, MIT.

A project setting that runs setup when a session starts and allows two forms of one test command.

In plain words
What is it for?
It is for running session-start.sh at session start and allowing ./scripts/test.sh commands.
Why use it?
It automates startup preparation and explicitly permits the project's test script to run with or without arguments.

Settings file for Claude Code

Written for Claude Code: $CLAUDE_PROJECT_DIR variable.

This is HKUDS/LightRAG's own configuration. It tells Claude Code how to work on LightRAG itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything LightRAG configures →

One of 2 entries in settings.json upstream. Installing this one merges just its entry into your config; the other 1 are separate, each on its own page.

not rated 41krepo +113 yesterday A scan tokens not measured original MIT
▶ Claude Code + LightRAG = UNSTOPPABLE Chase AI · about LightRAG · on YouTube →
View source ↗ HKUDS/LightRAG arxiv.org
About the project

LightRAG is a retrieval-augmented generation system that combines language models with retrieved information and knowledge-graph data to answer questions using relevant sources. It is for building applications that search document or knowledge collections before generating responses.

HKUDS/LightRAG · 40,557 stars · on GitHub · arxiv.org

Reuse

Borrowing it

Nothing to install: this file belongs to HKUDS/LightRAG. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/HKUDS/LightRAG/main/.claude/settings.json
Clone the repo
git clone --depth 1 https://github.com/HKUDS/LightRAG

Made for: Claude Code.

Wrote 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.

agentmods badge for LightRAG

README.md
[![agentmods](https://agentmods.dev/badge/settings/hkuds/lightrag/settings/github.svg)](https://agentmods.dev/settings/hkuds/lightrag/settings)
Your own site
<a href="https://agentmods.dev/settings/hkuds/lightrag/settings"><img src="https://agentmods.dev/badge/settings/hkuds/lightrag/settings/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.

agentmods 80×15 button for LightRAG

Your own site · 80×15
<a href="https://agentmods.dev/settings/hkuds/lightrag/settings"><img src="https://agentmods.dev/badge/settings/hkuds/lightrag/settings.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

LightRAG 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 2mo ago.

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.

.claude/settings.json · 21 lines

What it actually says

{
  "permissions": {
    "allow": [
      "Bash(./scripts/test.sh)",
      "Bash(./scripts/test.sh *)"
    ]
  },
  "hooks": {
    "SessionStart": [
      {
        "hooks": [
          {
            "type": "command",
            "command": "$CLAUDE_PROJECT_DIR/.claude/hooks/session-start.sh"
          }
        ]
      }
    ]
  }
}
Same file

What else settings.json configures

This page is one entry in a file that holds 2. Installing the file brings all of them; each is measured and scanned on its own page.

Changes

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.

  1. 2mo ago First seen · 21 lines scan A 15464d165fc2

Subscribe to this mod's changes

LightRAG is a settings file published in the GitHub repository HKUDS/LightRAG (40,557 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-30.

LLMgenaigraphragknowledge-graphlarge-language-modelsretrieval-augmented-generation
Related

LightRAG compared with settings from other repositories

LightRAG next to 6 settings from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
LightRAGHKUDS/LightRAGSettings file41kyesterdayMITA—Claude Code
supabasesupabase/supabaseSettings file115ktodayApache-2.0A—Claude Code
supersetapache/supersetSettings file75ktodayApache-2.0A—Claude Code
RuViewruvnet/RuViewSettings file103ktodayMITA—Claude Code
claude-cookbooksanthropics/claude-cookbooksSettings file54k2d agoMITA—Claude Code
ormprisma/ormSettings file48kyesterdayApache-2.0A—Claude Code
claude-code-best-practiceshanraisshan/claude-code-best-practiceSettings file69kyesterdayMITA—Claude Code