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 agentmods add instructions/codingthefuturewithai/rag-retriever/claude-mdgit clone --depth 1 https://github.com/codingthefuturewithai/rag-retrieverWrote 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/instructions/codingthefuturewithai/rag-retriever/claude-md)<a href="https://agentmods.dev/instructions/codingthefuturewithai/rag-retriever/claude-md"><img src="https://agentmods.dev/badge/instructions/codingthefuturewithai/rag-retriever/claude-md.svg" alt="Measured on agentmods" 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 | $0.02759 | $0.02759 |
| Opus 5 | $0.01380 | $0.01380 |
| Sonnet 5 | $0.00552 | $0.00552 |
| Haiku 4.5 | $0.00276 | $0.00276 |
Grade A, and why
rag-retriever CLAUDE.md 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
CRITICAL SESSION CONTEXT (JULY 2025)
COMPLETED MAJOR DOCUMENTATION OVERHAUL - ALL CHANGES APPLIED AND TESTED
What Was Just Completed:
- AI-First Documentation Strategy Implemented - Following claude-mcp-knowledge-base pattern
- Complete CLI Documentation Created - Comprehensive coverage of CLI-only capabilities
- Command Namespace Updated - All commands now use
rag-prefix for clarity - UI Capabilities Properly Documented - 5 screenshots integrated with accurate descriptions
- Master Navigator Created - GETTING_STARTED_GUIDE.md for new users
- Architecture Diagrams Updated - Mermaid diagrams ready for README integration
New Documentation Files Created:
CLI_ASSISTANT_PROMPT.md- Complete CLI reference and workflowsADMIN_ASSISTANT_PROMPT.md- Administrative operations and maintenanceADVANCED_CONTENT_INGESTION_PROMPT.md- Images, PDFs, GitHub, ConfluenceGETTING_STARTED_GUIDE.md- Master navigator for entire ecosystem
New Claude Code Commands (with rag- prefix):
/rag-list-collections- Show collections with metadata/rag-search-knowledge- Semantic search across collections/rag-index-website- Crawl and index websites/rag-audit-collections- Review collection health/rag-assess-quality- Evaluate content quality/rag-manage-collections- Administrative operations (provides CLI commands)/rag-ingest-content- Advanced content ingestion guidance/rag-cli-help- Interactive CLI help system/rag-getting-started- Interactive getting started guide
UI Screenshots Integrated (5 total):
rag-retriever-UI-collections.png- Collections management overviewrag-retreiver-UI-delete-collection.png- Collection actions and deletionrag-retriever-UI-search.png- Interactive knowledge search interfacerag-retriever-UI-compare-collections.png- Collection analytics and comparisonrag-retreiver-UI-discover-and-index-new-web-content.png- Content discovery workflow
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.
- 4d ago First seen · 248 lines · 2,759 tokens per session scan A a16ecaa47dec
rag-retriever CLAUDE.md is an instructions file published in the GitHub repository codingthefuturewithai/rag-retriever (27 stars, last pushed 1y ago), licensed MIT. It adds 2,759 tokens to every session, about $0.0138 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 2026-08-30.
Other instructions, from other repositories
graphiti AGENTS.md
AGENTS.md instructions for getzep/graphiti, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
nuwax AGENTS.md
AGENTS.md instructions for nuwax-ai/nuwax, covering ai agent system documentation, 系统概述, ai agent 架构, 核心组件 and ai 功能特性.
Starcat AGENTS.md
AGENTS.md instructions for starcat-app/Starcat, covering agents.md, 🚨 硬性铁律（每次写代码前必读，违反即返工）, 🌿 git 分支与 worktree（强制）, 🧭 主进度索引（每次开工前必读） and 状态符号（与功能实现总览.md 同步）.
RAGElo copilot-instructions.md
Instructions for zetaalphavector/RAGElo, covering copilot instructions — ragelo, project overview, commands, install for development and run with openai integration tests (requires openaiapikey).
pdf-brain AGENTS.md
Instructions for joelhooks/pdf-brain, covering pdf-brain agent notes, libsql quirks, ai sdk pattern, key files and docs.
Elpis AGENTS.md
AGENTS.md instructions for MasihMoafi/Elpis, covering elpis agent map, start, context discipline, definition of done and evals first.