What is local-rag-core-maintainer?

A maintenance and verification guide for the local-rag-core project. RAG, or retrieval-augmented generation, lets an AI look up information from a local knowledge base while working.

Use it to inspect project health and knowledge packs, search project goals, maintain MCP integration, manage pack lifecycle operations, and assess release readiness.

It sets checks and boundaries for changing project code, documentation, integrations, packs, backups, and releases. It helps keep knowledge-base data protected and changes consistent with the project's documented design.

How linkwut-create/local-rag-core configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to linkwut-create/local-rag-core. 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/linkwut-create/local-rag-core/master/.claude/skills/local-rag-core-maintainer/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/linkwut-create/local-rag-core

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/linkwut-create/local-rag-core/local-rag-core-maintainer/github.svg)](https://agentmods.dev/skills/linkwut-create/local-rag-core/local-rag-core-maintainer)

Your own site

<a href="https://agentmods.dev/skills/linkwut-create/local-rag-core/local-rag-core-maintainer"><img src="https://agentmods.dev/badge/skills/linkwut-create/local-rag-core/local-rag-core-maintainer/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/linkwut-create/local-rag-core/local-rag-core-maintainer"><img src="https://agentmods.dev/badge/skills/linkwut-create/local-rag-core/local-rag-core-maintainer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 709 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.

Model	Per session	Once invoked
Fable 5.1	$0.00052	$0.00709
Opus 5	$0.00026	$0.00354
Sonnet 5	$0.00010	$0.00142
Haiku 4.5	$0.00005	$0.00071

Measured 8d ago against content hash 011d8cf287e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

local-rag-core-maintainer 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 8d 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/skills/local-rag-core-maintainer/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

local-rag-core Maintainer

Use this skill before changing local-rag-core or judging whether it is ready for normal use.

Required First Steps

Call kb.health.
Call kb.list_packs.

Search the knowledge base for project goals:

kb.search "local-rag-core project purpose and design goals"

Search for the concrete topic being changed, for example:

kb.search "diagnostics health strict backend cache"
kb.search "pack lifecycle export import boundaries"
kb.search "MCP read only tool schema"

Summarize the retrieved context before proposing or editing files.

If MCP is unavailable, state that explicitly and fall back to reading AGENTS.md, CLAUDE.md, PROJECT_STATUS.md, README.md, and the relevant source or test files.

Hard Boundaries

Treat MCP as read-only.
Do not modify storage/, data/packs/, or data/private_kb/ directly.
Do not bypass the pack lifecycle. Use rag pack ... commands for pack build, export, import, enable, and disable flows.
Do not change MCP tool schemas without updating AGENTS.md, CLAUDE.md, and MCP_INTEGRATION.md.
Do not expose secrets, real tokens, private documents, or local-only runtime caches in public docs or release notes.
Keep local settings such as .claude/settings.local.json and .codex/config.toml machine-local unless the user explicitly asks to share sanitized examples.

Normal Verification Lanes

For small documentation or hook-only changes:

python scripts/hooks/local_rag_core_skill_gate.py
git diff --check

For code or behavior changes:

ruff check .
pytest -m "not real_model"

For release or readiness checks:

ruff check .
pytest
rag health --strict
rag integrity --deep
python scripts/run_eval.py
python scripts/ops_verify.py

Use the smallest lane that proves the change. Report skipped checks clearly.

GitHub and Release Work

Before pushing or publishing, run a tracked-file privacy check:

Read the full file on GitHub · 97 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.

8d ago First seen · 97 lines · 52 tokens per session scan A 011d8cf287e3

Subscribe to this mod's changes

local-rag-core-maintainer is a skill published in the GitHub repository linkwut-create/local-rag-core (0 stars, last pushed 2mo ago), licensed MIT. It adds 52 tokens to every session and 709 once invoked, about $0.0003 per session on Opus 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 AI RAG and vectors fastapi knowledge-base local-first mcp

memobase

A Russian-language skill for searching a local knowledge base built from documents and other sources such as web pages, YouTube, audio, and Obsidian notes.

maximskorohod/memobase · 25 tokens

rag-knowledge

Work with the RAG knowledge base — ingest documents, run semantic search, manage collections, or add a sync source/connector (Google Drive, S3). Use when populating or debugging the knowledge base, tuning retrieval, or adding a new document source. This project uses {{ cookiecutter.vectorstore }} + {{…

vstorm-co/full-stack-ai-agent-template · 76 tokens

wegent-knowledge

Knowledge base management and search tools for Wegent. Provides capabilities to list, create, update, and search knowledge bases and documents using RAG retrieval. Use this skill when the user wants to manage knowledge bases, documents, or search for information programmatically.

wecode-ai/Wegent · 51 tokens

karpathy-llm-wiki

Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.

Astro-Han/karpathy-llm-wiki · 67 tokens

starcat-ui-prototype

A design skill for creating macOS interface prototypes and visual designs for Starcat, a GitHub star-management and AI knowledge-organising app. It follows Apple’s Liquid Glass design language for macOS 26.

starcat-app/Starcat · 85 tokens

backlot

Emulate enterprise SaaS knowledge APIs — Slack, Gmail, Google Drive (with Docs, Sheets, Slides), GitHub, Jira, Confluence, Notion, Amazon S3, HubSpot, Linear, Fireflies — over a corpus you supply, then point a real client (vendor SDK, MCP server, LlamaIndex reader, fsspec, mirage) at it. Applies in ANY directory, an…

brekkylab/backlot · 192 tokens

local-rag-core: Skill for Claude Code