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 skills add winsenlabs/platos --skill platos_raggit clone --depth 1 https://github.com/winsenlabs/platosWrote 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/skills/winsenlabs/platos/platos_rag)<a href="https://agentmods.dev/skills/winsenlabs/platos/platos_rag"><img src="https://agentmods.dev/badge/skills/winsenlabs/platos/platos_rag/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/skills/winsenlabs/platos/platos_rag"><img src="https://agentmods.dev/badge/skills/winsenlabs/platos/platos_rag.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 | $0.00070 | $0.01087 |
| Opus 5 | $0.00035 | $0.00544 |
| Sonnet 5 | $0.00014 | $0.00217 |
| Haiku 4.5 | $0.00007 | $0.00109 |
Grade A, and why
Platos RAG 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 8d 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.
What it actually says
You have a retrieval-augmented-generation (RAG) toolbelt backed by Platos long-term memory. Every chunk is scoped to (org, project, env, user) — other users and other scopes never see it.
rag_ingest_document — bring content into memory.
sourceaccepts a single URL, a singleattachmentId:<id>ref, or an array.- URLs are fetched via the built-in
fetch_urlpath (orparallel_extractwhenPARALLEL_API_KEYis set). attachmentId:*pulls the bytes from the agent's MinIO workspace.- Content is split sentence-aware into
chunkSizeblocks withoverlapcarried forward. - If more than 5 sources are passed, the call is queued via
agent_batchand returns{ batchRunId }immediately — check the batch progress stream for completion.
rag_retrieve — fetch the top matching chunks for a query.
- Returns
{ chunks: [{ content, sourceUrl, chunkIndex, score }], totalChunks, reranked }. filterTagsnarrows to chunks that were ingested with at least one of the supplied tags.rerank: trueis a no-op today (returns a warning) — the simple cosine search still runs.
rag_delete_source / rag_list_sources / rag_reindex — housekeeping.
When to use:
- The user asks a question that depends on specific documents ("given the handbook above…").
- You want to ground your answer in user-supplied material rather than the model's training data.
Guidelines:
- Cite every chunk you rely on with
[1](sourceUrl)footnotes. - Prefer
topK=8for exploratory queries, drop to 3–5 for tight factual lookups. - Use
filterTagswhen the user has multiple document sets — keeps retrieval relevant.
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.
- 8d ago First seen · 64 lines · 70 tokens per session scan A c33a6bcd8dc5
Platos RAG is a skill published in the GitHub repository winsenlabs/platos (24 stars, last pushed yesterday), licensed Apache-2.0. It adds 70 tokens to every session and 1,087 once invoked, about $0.0003 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 2026-09-04.
Other skills, from other repositories
molecular-rag
Retrieve structurally similar compounds with known properties from ChEMBL/ZINC to ground predictions and inform optimization. Based on MolRAG (Xian 2025, ACL).
browserwing-admin
Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.
wegent-knowledge
Knowledge base management and search tools for Wegent. Provides capabilities to list, create, update, and search knowledge bases and documents using RAG retrieval. Use this skill when the user wants to manage knowledge bases, documents, or search for information programmatically.
local-embedding
Run embedding on-device with ONNX Runtime. Build from source, model selection, offline mode. Use when setting up local embedding without an API key.
memori
You have access to Memori, agent-native memory infrastructure: an LLM-agnostic layer that structures memory from not just natural language, but also from agent trace that comes from execution.
dify
Use when building LLM applications with visual workflow — RAG knowledge bases, AI agents, chatbots with drag-and-drop orchestration. Dify: open-source LLM app platform supporting 30+ models (OpenAI, Claude, DeepSeek, Ollama, Qwen, GLM) with Docker deployment.