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/cq27-dev/rag-rat/using-rag-ratnpx skills add cq27-dev/rag-rat --skill using-rag-ratgit clone --depth 1 https://github.com/cq27-dev/rag-ratWrote 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/cq27-dev/rag-rat/using-rag-rat)<a href="https://agentmods.dev/skills/cq27-dev/rag-rat/using-rag-rat"><img src="https://agentmods.dev/badge/skills/cq27-dev/rag-rat/using-rag-rat.svg" alt="Measured on agentmods" 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 | $0.00139 | $0.02494 |
| Opus 5 | $0.00069 | $0.01247 |
| Sonnet 5 | $0.00028 | $0.00499 |
| Haiku 4.5 | $0.00014 | $0.00249 |
Grade A, and why
using-rag-rat 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 3d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
using-rag-rat — navigate with the MCP, remember what you learn
This repo is indexed by rag-rat, a local repo-intelligence index + MCP server. One MCP call
returns graph (callers/callees), git, GitHub papertrail, and drive-by repo memories
(source-anchored invariants, decisions, risks) — all validated against current source. A grep
can't surface any of that. Two rules follow.
Rule 1 — Find and understand through the MCP, not a shell sweep
Prefer these over grep/cat/file sweeps when browsing or understanding code:
semantic_search— "where is this concept implemented?" Current source chunks with inline graph, git, and papertrail.symbol_lookup— exact/fuzzy symbol resolution (Rust/TS/Kotlin/C/C++/Python/Swift/Go), with any bound memories attached.impact_surface— the coding preflight before editing any non-trivial symbol: callers, callees, tests, git history, papertrail, and the repo memories crossing that call path. Run it before you change something load-bearing — it's how you avoid missing an invariant.find_callers/trace_callees— reverse/forward graph traversal instead of grepping for call sites.read_chunk— current text for a chunk with anchor validation + graph + memories.repo_brief/repo_clusters— orientation (spine, churn, god-modules, ownership clusters).important_symbols— load-bearing symbols by (SCIP-aware) PageRank; passpersonalizeto bias toward what you're editing.
That's the daily loop. The MCP exposes many more tools — reach past the core ones by the question
you're actually asking (full schemas: docs/mcp-tools.md):
| When you want to… | Reach for |
|---|---|
| Find where a concept/behavior lives | semantic_search |
| Resolve a symbol by name (exact/fuzzy) | symbol_lookup |
| See what calls X / what X calls | find_callers / trace_callees |
| Know the blast radius before editing | impact_surface (callers, callees, tests, history, memories — the preflight) |
| Read a chunk's exact current text | read_chunk |
| Orient in an unfamiliar repo | repo_brief (spine / churn / god_modules / refactor_candidates), repo_clusters |
| Find the load-bearing symbols | important_symbols |
| Check if code duplicates what's already here | find_clones; the clone class of one symbol → clones_for_symbol |
| Understand why code exists (rationale) | papertrail_for_symbol / papertrail_for_chunk, rationale_search |
| Trace when/why something changed | git_history_for_symbol / git_history_for_path, commit_search, commits_touching_query, git_blame_chunk |
| Pull a tracker issue/PR or refs for a path | papertrail_issue_search, papertrail_refs_for_path, papertrail_for_commit |
| Read docs / doc-comments for a symbol | docs_for_symbol |
| Map the FFI / binding surface | ffi_surface |
| Audit whether the graph is trustworthy here | compare_graph_to_scip (vs compiler), compare_graph_to_text (vs regex) |
| Recall prior notes and their links | memory_search, memory_for_symbol / memory_for_path / memory_for_call_path, memory_edges |
| Triage the memory-maintenance worklist | dream → dream_review (see the dream-review skill) |
| Check index / embedding / papertrail-cache health | index_status, llm_status, papertrail_sync_status; repair drift with heal_index |
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.
- 3d ago First seen · 147 lines · 139 tokens per session scan A 2f8afac5526b
using-rag-rat is a skill published in the GitHub repository cq27-dev/rag-rat (17 stars, last pushed 5d ago), licensed MIT. It adds 139 tokens to every session and 2,494 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
mcp-local-rag
Searches, saves, and maintains a local document index through a local RAG MCP server. Use when user says "search my docs", "save this page", "read around that chunk", "sync my index", or invokes npx mcp-local-rag.
local-rag-search
Efficiently perform web searches using the mcp-local-rag server with semantic similarity ranking. Use this skill when you need to search the web for current information, research topics across multiple sources, or gather context from the internet without using external APIs. This skill teaches effective use of…
setup
Configure the Qdrant Power after installation. Use this skill for missing uvx, missing environment variables, unapproved environment variables, unavailable Qdrant tools, "Failed to connect" errors, and setup requests.
vector-backend-operations
Select and connect the right vector-store backend for the vector-mcp MCP server — chromadb, postgres/pgvector, qdrant, couchbase, or mongodb — and supply the correct dbtype/connection parameters that every collection and search call needs. Use when the agent must decide which engine to target, wire up…
vector-collection-management
Create, populate, list, and delete vector-store collections through the vector-mcp MCP server's vectorcollectionmanagement tool. Use when the agent must stand up a new RAG collection, ingest documents (from a directory, file paths/URLs, or raw text) into an existing collection, enumerate collections, or drop one …
vector-hybrid-search
Retrieve knowledge from a vector-store collection via the vector-mcp MCP server's vectorsearch tool — semantic (ANN) search, lexical BM25 search, or a hybrid of the two fused with Reciprocal Rank Fusion. Use when the agent must answer a question from an indexed corpus, pull top-k relevant chunks for RAG context, or…