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 skills/thisisyoyodev/claude-rag/confignpx skills add ThisisYoYoDev/claude-rag --skill configgit clone --depth 1 https://github.com/ThisisYoYoDev/claude-ragWhat 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 | $0.00022 | $0.00702 |
| Opus 5 | $0.00011 | $0.00351 |
| Sonnet 5 | $0.00004 | $0.00140 |
| Haiku 4.5 | $0.00002 | $0.00070 |
Grade B, and why
config scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat ~/.claude/plugins/claude-rag/config.json 2>/dev/null || echo '{"connection":{"endpoint":"https://api.clauderag.io"}}' Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s <endpoint>/health How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RAG Configuration
Configure the Claude RAG plugin settings.
Instructions
-
Read current config:
cat ~/.claude/plugins/claude-rag/config.json 2>/dev/null || echo '{"connection":{"endpoint":"https://api.clauderag.io"}}' -
If "$ARGUMENTS" matches a section name, go directly to that section. Otherwise, show the main menu.
Main Menu
Use AskUserQuestion:
- header: "Claude RAG Configuration"
- question: "What would you like to configure?"
- options:
- "Connection — endpoint & API key"
- "Capture — what to record (prompts, tools, agents...)"
- "RAG Mode — auto injection behavior"
- "Privacy — secret redaction & exclusions"
- "Show current config"
- "Reset to defaults"
- "Test connection"
Section: Connection
Use AskUserQuestion:
- question: "Connection type?"
- options: ["Local (Docker — for development only)", "Cloud (custom endpoint)"]
If Cloud: ask for endpoint URL and API key. Write updated config.
Section: Capture
Use AskUserQuestion with multiSelect:
- question: "What should be captured?"
- multiSelect: true
- options:
- "User prompts"
- "AI outputs"
- "Tool calls (input)"
- "Tool results (output)"
- "Sub-agent activity"
- "Multimodal files"
Then ask for excluded tools (comma-separated, default: "AskUserQuestion").
Section: RAG Mode
Use AskUserQuestion:
- question: "RAG injection mode?"
- options:
- "Off — capture only, no injection"
- "Manual — only /claude-rag:search and /claude-rag:ask"
- "Auto — inject context on every prompt (recommended)"
- "Aggressive — auto + Claude can search on its own"
If auto or aggressive, ask for:
- Threshold (0.4-0.9, default 0.6)
- Max context tokens (500-4000, default 2000)
Section: Privacy
Use AskUserQuestion with multiSelect:
- question: "Privacy settings?"
- multiSelect: true
- options:
- "Redact secrets (passwords, tokens, API keys)"
- "Exclude .env files"
- "Exclude credentials files"
Ask for additional exclusion patterns if needed.
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 · 112 lines · 22 tokens per session scan B d68add7bfb1d
config is a skill published in the GitHub repository ThisisYoYoDev/claude-rag (9 stars, last pushed 5mo ago), licensed MIT. It adds 22 tokens to every session and 702 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
9router-embeddings
Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.
potpie-source-ingestion
Use when the user explicitly asks to ingest, refresh, or deeply understand a repository, PR, issue, ticket, runbook, incident report, document, or web link into Potpie. The harness performs todo-driven discovery, uses local/GitHub/integration tools and read-only subagents when available, builds evidence-backed…
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
generate-rag-dataset
Generate a synthetic evaluation dataset from your RAG knowledge base. Creates diverse Q&A pairs with expected answers and relevant context, ready for LangWatch experiments and platform import. Use when you need test data for your RAG pipeline.
embeddings
Vector embeddings configuration and semantic search.