agentmods.dev

local-rag

local-rag is a skill for Claude Code, Codex from zongzi-zongzhi/local-Rag. It costs 82 tokens per session (3,399 once invoked), scanned A, original, MIT.

A skill for searching and managing local documents with a local retrieval system, which finds relevant passages in saved files or text.

In plain words
What is it for?
Ingesting PDFs, DOCX, text, Markdown, or raw web content; searching saved documents; expanding search results with neighboring text; and managing the document collection.
Why use it?
It helps locate information in ingested documents and read nearby passages when one result lacks enough context. It also covers adding, listing, checking, and deleting saved content.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 0repo 4mo ago A scan 82 tokens original MIT

Good fit Ingesting PDFs, DOCX, text, Markdown, or raw web content; searching saved documents; expanding search results with neighboring text; and managing the document collection.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zongzi-zongzhi/local-rag/local-rag
View source ↗ zongzi-zongzhi/local-Rag
Install

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.

Any agent
npx skills add zongzi-zongzhi/local-Rag --skill local-rag
Clone the repo
git clone --depth 1 https://github.com/zongzi-zongzhi/local-Rag

Made for: Claude Code, Codex.

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 local-rag

README.md
[![agentmods](https://agentmods.dev/badge/skills/zongzi-zongzhi/local-rag/local-rag/github.svg)](https://agentmods.dev/skills/zongzi-zongzhi/local-rag/local-rag)
Your own site
<a href="https://agentmods.dev/skills/zongzi-zongzhi/local-rag/local-rag"><img src="https://agentmods.dev/badge/skills/zongzi-zongzhi/local-rag/local-rag/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 local-rag

Your own site · 80×15
<a href="https://agentmods.dev/skills/zongzi-zongzhi/local-rag/local-rag"><img src="https://agentmods.dev/badge/skills/zongzi-zongzhi/local-rag/local-rag.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,399 The whole file, excluding the scripts and references it only reads on demand.
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.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00082 $0.03399
Opus 5.5 $0.00033 $0.01360
Sonnet 5.5 $0.00016 $0.00680
Haiku 4.5 $0.00008 $0.00340

Measured 2mo ago against content hash e0822394adb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

local-rag 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.

skills/local-rag/SKILL.md · 254 lines

How it starts

The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.

local-Rag Skills

Tools

MCP Tool CLI Equivalent Use When
ingest_file npx local-rag ingest <path> [--visual] Local files (PDF, DOCX, TXT, MD). CLI for bulk/directory. PDF visual mode: see Visual content (PDFs).
ingest_data 鈥? Raw content (HTML, text) with source URL
query_documents npx local-rag query <text> Semantic + keyword hybrid search
delete_file npx local-rag delete <path> Remove ingested content
list_files npx local-rag list File ingestion status
status npx local-rag status Database stats
read_chunk_neighbors npx local-rag read-neighbors Read N chunks adjacent to a known chunkIndex (context expansion; call after query_documents or grep)

Workflow

  1. For search requests, formulate a focused hybrid query, choose limit by intent, then filter results by score AND topical relevance.
  2. When a retrieved hit lacks enough surrounding context for a grounded answer, expand only that chunk via read_chunk_neighbors.
  3. For ingestion, choose ingest_file for local files and ingest_data for raw/web content.
  4. For PDFs, ask once about ingest mode unless the current request already specifies one (text-only, visual fast, or visual quality). See decision protocol in Ingestion.

Search: Core Rules

Hybrid search combines vector (semantic) and keyword (BM25).

Score Interpretation

Lower = better match. Use this to filter noise.

Score Action
< 0.3 Use directly
0.3-0.5 Include if mentions same concept/entity
0.5-0.7 Include only if directly relevant to the question
> 0.7 Skip unless no better results

Limit Selection

Intent Limit
Specific answer (function, error) 5
General understanding 10
Comprehensive survey 20

Query Formulation

Situation Why Transform Action
Specific term mentioned Keyword search needs exact match KEEP term
Vague query Vector search needs semantic signal ADD context
Error stack or code block Long text dilutes relevance EXTRACT core keywords
Multiple distinct topics Single query conflates results SPLIT queries
Few/poor results Term mismatch EXPAND (see below)

Read the full file on GitHub · 254 lines

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 · 254 lines · 0 tokens per session scan A e0822394adb4

Subscribe to this mod's changes

local-rag is a skill published in the GitHub repository zongzi-zongzhi/local-Rag (0 stars, last pushed 4mo ago), licensed MIT. It adds 82 tokens to every session and 3,399 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 2026-08-31.

Data and AIDocumentsRAG and vectors
Related

local-rag compared with skills from other repositories

local-rag next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
local-ragzongzi-zongzhi/local-RagSkill04mo agoMITA82Claude Code, Codex
markitdownK-Dense-AI/scientific-agent-skillsSkill56k5d agoMITA62Claude Code, Codex
agents-llamaindexdavila7/claude-code-templatesSkill33ktodayMITA72Claude Code, Codex
xberg-picking-a-formatxberg-io/xbergSkill9.6ktodayMITA51Claude Code
kb-retrieverConardLi/garden-skillsSkill15k12d agoMITA105Claude Code, Codex
cx-knowledge-base-ingestionGoogleCloudPlatform/professional-servicesSkill3.1kyesterdayApache-2.0A48Gemini CLI
azure-aimicrosoft/skillsSkill3.2ktodayMITA66Claude Code