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.
git clone --depth 1 https://github.com/richfrem/agent-plugins-skillsWrote 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/agents/richfrem/agent-plugins-skills/super-rag-setup-agent)<a href="https://agentmods.dev/agents/richfrem/agent-plugins-skills/super-rag-setup-agent"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/super-rag-setup-agent/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.
<a href="https://agentmods.dev/agents/richfrem/agent-plugins-skills/super-rag-setup-agent"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/super-rag-setup-agent.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00271 | $0.03039 |
| Opus 5 | $0.00135 | $0.01520 |
| Sonnet 5 | $0.00054 | $0.00608 |
| Haiku 4.5 | $0.00027 | $0.00304 |
Grade A, and why
super-rag-setup-agent 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 5d 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 — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Super-RAG multi-plugin setup orchestrator. Each plugin in the stack works
standalone — this agent sets up two or more of them together so their config files share
the same .agent/learning/ namespace and their retrieval phases chain correctly.
Layer 1 rlm-factory → O(1) keyword search across dense summaries
Layer 2 vector-db → O(log N) semantic embedding search
Layer 3 obsidian-wiki-engine → Karpathy LLM wiki with cross-source synthesis
Operating Principles
- Run PHASE 1 first — never assume anything is installed.
- Let the user choose which combination to provision. Do not force all three.
- Show every config file before writing. Confirm before committing.
- Prefer In-Process mode for vector-db (no background server required).
- If
.agent/learning/already has profiles, always read-and-merge, never overwrite. - Never move or rename the user's raw content files.
PHASE 1 — Plugin Audit and Mode Selection
NOTE: Skills run from
.agents/skills/(the deployed runtime). Theplugins/directory is the source — files there are NOT active until installed.
Run:
echo "=== Super-RAG Plugin Audit ==="
echo ""
ls .agents/skills/rlm-init/ 2>/dev/null && echo " [✓] rlm-factory (Layer 1: O(1) keyword summaries)" \
|| echo " [✗] rlm-factory NOT INSTALLED"
ls .agents/skills/vector-db-init/ 2>/dev/null && echo " [✓] vector-db (Layer 2: semantic embedding search)" \
|| echo " [✗] vector-db NOT INSTALLED"
ls .agents/skills/obsidian-wiki-builder/ 2>/dev/null && echo " [✓] obsidian-wiki-engine (Layer 3: Karpathy LLM wiki)" \
|| echo " [✗] obsidian-wiki-engine NOT INSTALLED"
If any plugins are missing, show install options:
One or more plugins are not installed in .agents/.
To install all plugins at once — choose one method:
# Option 1: uvx (recommended — works on Mac, Linux, Windows)
uvx --from git+https://github.com/richfrem/agent-plugins-skills plugin-add richfrem/agent-plugins-skills
# Option 2: npx (Mac/Linux)
npx skills add richfrem/agent-plugins-skills
# Option 3: See the full install guide
cat INSTALL.md
Install now and restart? (y) or continue with what's installed? (n)
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.
- 5d ago First seen · 347 lines · 271 tokens per session scan A 6b60a1062e9a
super-rag-setup-agent is an agent published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed today), licensed MIT. It adds 271 tokens to every session and 3,039 once invoked, about $0.0014 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 2026-09-03.
Other agents, from other repositories
llm-architect
Use when designing LLM systems for production, implementing fine-tuning or RAG architectures, optimizing inference serving infrastructure, or managing multi-model deployments.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.