search

search is a skill for Claude Code, Codex from ThisisYoYoDev/claude-rag. It costs 25 tokens per session (449 once invoked), scanned B, original, MIT.

A command that soft-deletes Claude RAG data, meaning it hides records from search while keeping them restorable. It can target a session, a project, or all stored data.

In plain words
What is it for?
Forgetting one session, removing a project from search, or soft-deleting all RAG data after confirmation.
Why use it?
It provides a way to remove unwanted historical records without immediately destroying them permanently.

Skill for Claude CodeCodex

Part of the claude-rag plugin — 9 skills, 19 commands, 6 hooks, 1 MCP server shipped together

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.

agentmods
npx agentmods add skills/thisisyoyodev/claude-rag/search
Any agent
npx skills add ThisisYoYoDev/claude-rag --skill search
Clone the repo
git clone --depth 1 https://github.com/ThisisYoYoDev/claude-rag

Made for: Claude Code, Codex.

Or install claude-rag, the plugin that ships this one along with the rest of its 9 skills, 19 commands, 6 hooks, 1 MCP server.

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 search

README.md
[![agentmods](https://agentmods.dev/badge/skills/thisisyoyodev/claude-rag/search.svg)](https://agentmods.dev/skills/thisisyoyodev/claude-rag/search)
Your own site
<a href="https://agentmods.dev/skills/thisisyoyodev/claude-rag/search"><img src="https://agentmods.dev/badge/skills/thisisyoyodev/claude-rag/search.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 449 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. Scan, not verified.
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 $0.00025 $0.00449
Opus 5 $0.00013 $0.00225
Sonnet 5 $0.00005 $0.00090
Haiku 4.5 $0.00003 $0.00045

Measured 3d ago against content hash 2ea906929bfb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

search scanned grade B with 2 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 3d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat ~/.claude/plugins/claude-rag/config.json 2>/dev/null || echo '{"connection":{"endpoint":"https://api.clauderag.io"}}'

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

allowed-tools: Bash(curl *)
skills/search/SKILL.md · 47 lines

What it actually says

Search the RAG database for content matching the user's query: "$ARGUMENTS"

Instructions

  1. Read the plugin config to get the backend endpoint:

    cat ~/.claude/plugins/claude-rag/config.json 2>/dev/null || echo '{"connection":{"endpoint":"https://api.clauderag.io"}}'
    
  2. Execute the search query against the backend:

    curl -s -X POST <endpoint>/api/v1/search \
      -H "Content-Type: application/json" \
      -d '{"query": "<user_query>", "limit": 10, "threshold": 0.5}'
    
  3. Display results in a clear, organized format:

    • Group by relevance score (high to low)
    • For each result show:
      • Content type icon: Prompt=💬, AI Response=🤖, Tool Result=🔧, Error=❌
      • Score (as percentage)
      • Tool name (if applicable)
      • Agent type + sub-agent indicator
      • Project name
      • Date
      • Content preview (first 200 chars)
    • If no results: suggest broadening the query or checking filters
  4. If the user provides filters in their query, parse them:

    • "in project X" → {"filters": {"project_id": "X"}}
    • "from sub-agents" → {"filters": {"is_sub_agent": true}}
    • "only tools" → {"filters": {"content_types": ["tool_call", "tool_result"]}}
    • "bash results" → {"filters": {"tool_names": ["Bash"]}}
    • "code files" → {"filters": {"tool_categories": ["file"]}}
  5. Show total results count and search latency at the bottom.

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. 3d ago First seen · 47 lines · 25 tokens per session scan B 2ea906929bfb

Subscribe to this mod's changes

search is a skill published in the GitHub repository ThisisYoYoDev/claude-rag (9 stars, last pushed 5mo ago), licensed MIT. It adds 25 tokens to every session and 449 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

9router-embeddings

Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.

decolua/9router · 66 tokens

extracting-keywords

Use when extracting keywords (YAKE/RAKE) from documents — and, secondarily, when detecting document language or generating embeddings for RAG and search. Covers the keyword config (and its feature gating), --detect-language, and the standalone embed command with real flags.

xberg-io/xberg · 63 tokens

gpt-image-2

面向 GPT Image 2 的图像生成 / 编辑技能。可在 3 种环境下使用:(A) Garden 本地模式,通过 OpenAI 兼容接口直接出图并落盘;(B) Host-Native 模式,把本 Skill 当作提示词工程指引,把渲染好的 prompt 交给宿主 Agent 自带的图像工具出图;(C) Advisor 模式,宿主无任何图像工具时退化为高质量 prompt 顾问。涵盖 18 大类、80+ 个结构化模板,覆盖海报 / UI / 产品 / 信息图 / 学术图 / 技术架构图 / 漫画 / 头像 / 流程板 / 电影分镜 / IP 周边 / 编辑工作流等场景。.

ConardLi/garden-skills · 177 tokens

wax

Swift framework guidance for Wax on-device memory/RAG. Use when writing Swift code with the public Memory facade, experimental PhotoMemory / VideoMemory, BuiltInMultimodalEmbeddings, embedding providers, retrieval modes, or hybrid search. For agent operators using the Wax MCP server tools, use the separate wax-mcp…

christopherkarani/Wax · 68 tokens

session-rag-eval

Run and debug Chatbox session attachment RAG model evaluation with synthetic and real long-file fixtures.

chatboxai/chatbox · 25 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