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 commands/codingthefuturewithai/rag-retriever/rag-getting-startedgit clone --depth 1 https://github.com/codingthefuturewithai/rag-retrieverWhat 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 | $0.00000 | $0.01864 |
| Opus 5 | $0.00000 | $0.00932 |
| Sonnet 5 | $0.00000 | $0.00373 |
| Haiku 4.5 | $0.00000 | $0.00186 |
Grade A, and why
rag-getting-started 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.
How it starts
The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RAG Retriever Getting Started Guide
Interactive guidance for new users to navigate the RAG Retriever ecosystem and get productive quickly.
Prerequisites
This command provides comprehensive guidance for new users. No specific technical prerequisites required.
Arguments
Use $ARGUMENTS to specify your experience level or specific needs:
- "new" - Complete beginner walkthrough
- "experienced" - Advanced user quickstart
- "mcp" - Focus on MCP server setup and usage
- "cli" - Focus on CLI operations and administration
- "admin" - Administrative operations guidance
- "help" - Show all available guidance options
Examples:
- "new" - Complete beginner guide
- "experienced" - Skip basics, show advanced features
- "mcp" - MCP server setup and usage
- "cli" - CLI operations and administration
- "admin" - Administrative tasks and maintenance
Implementation Approach
This command uses direct implementation to provide personalized guidance based on user experience and needs.
Your Task
1. Assess User Experience and Needs
- Determine user's experience level from $ARGUMENTS
- Identify specific focus areas (MCP, CLI, admin, etc.)
- Provide appropriate guidance level
2. Provide Tailored Guidance
For New Users ("new")
You are: New to RAG Retriever, need complete walkthrough I'll provide: Step-by-step guidance from zero to productive
-
System Overview
- Explain the three interfaces: MCP Server, CLI, Web UI
- Show capability differences and when to use each
- Provide decision matrix for interface selection
-
Quick Start Path Selection
- Path 1: "I want AI assistant integration" → MCP setup
- Path 2: "I want full control from start" → CLI setup
- Path 3: "I want to understand everything first" → Complete overview
-
Next Steps
- Direct to appropriate setup prompt
- Provide specific commands to get started
- Set expectations for learning timeline
For Experienced Users ("experienced")
You are: Familiar with RAG concepts, want to get productive quickly I'll provide: Advanced quickstart with focus on powerful features
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.
- 2d ago First seen · 222 lines · 0 tokens per session scan A 1b4c8a5acc77
rag-getting-started is a command published in the GitHub repository codingthefuturewithai/rag-retriever (27 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,864 tokens. 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.