superragskills AGENTS.md

Instructions for building RAG applications. RAG, or retrieval-augmented generation, lets an AI answer using information retrieved from a chosen document or data collection.

In plain words
What is it for?
Use them when designing, building, evaluating, improving, or deploying a RAG app, including basic, hybrid, reranked, agentic, graph, multimodal, structured-data, local, or cloud setups.
Why use it?
They help decide how the application should retrieve information and how to check that answers are grounded, access-controlled, observable, and safe when no answer is available.

Instructions file for CodexOpenCode

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 instructions/aryanacoder/superragskills/agents-md
Clone the repo
git clone --depth 1 https://github.com/Aryanacoder/superragskills

Made for: Codex, OpenCode.

Per session 168 This file is loaded in full into every session.
When invoked 168 The same file — it is already loaded in full.
Security scan A 0 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 $0.00168 $0.00168
Opus 5 $0.00084 $0.00084
Sonnet 5 $0.00034 $0.00034
Haiku 4.5 $0.00017 $0.00017

Measured 2d ago against content hash e5c7e418a1cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

superragskills AGENTS.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 2d 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.

AGENTS.md · 13 lines

What it actually says

Agent Instructions

When the user asks to design, build, evaluate, improve, or deploy a RAG app, use the skill at skills/superrag-build/SKILL.md.

Important behavior:

  • Interview before implementation unless the user has already supplied enough detail.
  • Ask questions in small batches.
  • Select the correct RAG type before coding: basic, hybrid, reranked, agentic, GraphRAG, multimodal, structured-data, local/offline, AWS, Azure, or self-hosted.
  • Produce a concrete architecture, backlog, evaluation plan, and deployment plan before broad implementation.
  • Prioritize source grounding, citations, retrieval evaluation, access control, observability, and safe no-answer behavior.
  • For existing repos, inspect ingestion, indexing, retrieval, prompts, UI, and tests before changing code.
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. 2d ago First seen · 13 lines · 168 tokens per session scan A e5c7e418a1cc

Subscribe to this mod's changes

superragskills AGENTS.md is an instructions file published in the GitHub repository Aryanacoder/superragskills (3 stars, last pushed 2mo ago), licensed MIT. It adds 168 tokens to every session, about $0.0008 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.

Related

Other instructions, from other repositories

GPT-RAG config-python.instructions.md

Instructions for Azure/GPT-RAG, a project described as: Sharing the learning along the way we been gathering to enable Azure OpenAI at enterprise scale in a secure manner. GPT-RAG core is a Retrieval-Augmented Generation pattern running in Azure, using Azure Cognitive Search for retrieval and Azure OpenAI large…

Azure/GPT-RAG · 180 tokens

GPT-RAG release.instructions.md

Instructions for Azure/GPT-RAG, a project described as: Sharing the learning along the way we been gathering to enable Azure OpenAI at enterprise scale in a secure manner. GPT-RAG core is a Retrieval-Augmented Generation pattern running in Azure, using Azure Cognitive Search for retrieval and Azure OpenAI large…

Azure/GPT-RAG · 207 tokens

pdf-brain AGENTS.md

Instructions for joelhooks/pdf-brain, covering pdf-brain agent notes, libsql quirks, ai sdk pattern, key files and docs.

joelhooks/pdf-brain · 531 tokens

rag-code-mcp copilot-instructions.md

Instructions for doITmagic/rag-code-mcp, covering copilot instructions - ragcode mcp, ⚖️ the golden rule, project overview, architecture & patterns and developer workflows.

doITmagic/rag-code-mcp · 568 tokens

gpt-rag-mcp AGENTS.md

Instructions for Azure/gpt-rag-mcp, covering gpt-rag mcp engineering-agent contract, priority, what this repository is, repository boundaries and how to work.

Azure/gpt-rag-mcp · 1,862 tokens

gemini-cli-extension GEMINI.md

Instructions for pinecone-io/gemini-cli-extension, covering pinecone extension for gemini cli, available agent skills, key concepts & setup and available mcp tools.

pinecone-io/gemini-cli-extension · 569 tokens