Borrowing it
Nothing to install: this file belongs to RaviTeja-438/zap-rag-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/RaviTeja-438/zap-rag-mcp/main/.grok/skills/operating-zap-intellij/SKILL.mdgit clone --depth 1 https://github.com/RaviTeja-438/zap-rag-mcpWrote 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/raviteja-438/zap-rag-mcp/operating-zap-intellij)<a href="https://agentmods.dev/skills/raviteja-438/zap-rag-mcp/operating-zap-intellij"><img src="https://agentmods.dev/badge/skills/raviteja-438/zap-rag-mcp/operating-zap-intellij/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/raviteja-438/zap-rag-mcp/operating-zap-intellij"><img src="https://agentmods.dev/badge/skills/raviteja-438/zap-rag-mcp/operating-zap-intellij.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 | $0.00087 | $0.01009 |
| Opus 5 | $0.00044 | $0.00504 |
| Sonnet 5 | $0.00017 | $0.00202 |
| Haiku 4.5 | $0.00009 | $0.00101 |
Grade A, and why
operating-zap-intellij 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 11d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operating ZAP in IntelliJ (UI fallback)
Use when MCP is unavailable. When MCP works, use searching-zap-rag instead.
STRICT priority (same policy as MCP skill)
TIER 1 — ZAP UI (mandatory first)
Zap Search → Zap it (PLAIN → HYBRID → HYBRID_RERANK)
Index Project / Zap Jobs / re-embed / Kill Switch as needed
Human pastes hits back to the agent
TIER 2 — Native IDE search (only after Tier 1 exhausted)
Search Everywhere / Find in Files — only if Zap Search failed after index check
TIER 3 — Agent own capabilities (last resort)
Memory, guesses, web — only after Tier 1 and Tier 2 failed
MUST NOT
- Answer codebase facts from memory while ZAP UI is available and unused
- Tell the human to skip Zap Search and only use Find in Files first
- Enable Tier 3 before Index Project was attempted when the index is empty
When this skill applies
- No
zap_rag_*MCP tools - MCP OFF /
/healthfails - Index, re-embed, kill, settings recovery
- Human-only IntelliJ workflow
Instructions (Tier 1 — agent → human)
1. Craft a precise query (as if zap_rag_search)
2. Human: Zap Search → PLAIN → paste query → "Zap it"
3. Escalate: HYBRID → HYBRID_RERANK if weak
4. Human pastes display name, source_file, line, snippet
5. Answer ONLY from those facts
6. Empty → Index Project; watch Zap Jobs; Zap it again
7. Stuck → Kill Switch
8. MCP enabled + host:port shared → switch to searching-zap-rag (still Tier 1 ZAP)
9. ONLY if ZAP UI exhausted → suggest native Find in Files (Tier 2)
10. ONLY if that fails → cautious agent reasoning (Tier 3) with uncertainty
UI map
| Place | Action |
|---|---|
| Zap Search | Query + mode → Zap it → click class/method |
| Zap Jobs | Progress + ⏹ Kill Switch |
| Settings → ZAP RAG | Providers, S-tier, MCP, Apply, re-embed |
| Tools → ZAP RAG → Index Project | Ctrl+Alt+R |
| Tools → ZAP RAG → Kill Switch | Emergency |
Settings ops
- Embedding required; chat for summaries / HYBRID_RERANK
- Test Connection before long index
- Apply after every change
- Restart loads
ZAP-RAG.xml(not a wipe) - Model must match vectors → re-embed or re-index
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 117 lines · 87 tokens per session scan A 52d75a3cd1b3
operating-zap-intellij is a skill published in the GitHub repository RaviTeja-438/zap-rag-mcp (0 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 87 tokens to every session and 1,009 once invoked, about $0.0004 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 2026-09-01.
Other skills, from other repositories
embeddings
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.
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…
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
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.
azure-search-documents-dotnet
Azure AI Search SDK for .NET (Azure.Search.Documents). Use for building search applications with full-text, vector, semantic, and hybrid search. Covers SearchClient (queries, document CRUD), SearchIndexClient (index management), and SearchIndexerClient (indexers, skillsets). Triggers: "Azure Search .NET"…
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.